versions/master/api/python/docs/_sources/tutorials/getting-started/crash-course/6-train-nn.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "04797215",
   "metadata": {},
   "source": [
    "<!--- Licensed to the Apache Software Foundation (ASF) under one -->\n",
    "<!--- or more contributor license agreements.  See the NOTICE file -->\n",
    "<!--- distributed with this work for additional information -->\n",
    "<!--- regarding copyright ownership.  The ASF licenses this file -->\n",
    "<!--- to you under the Apache License, Version 2.0 (the -->\n",
    "<!--- \"License\"); you may not use this file except in compliance -->\n",
    "<!--- with the License.  You may obtain a copy of the License at -->\n",
    "\n",
    "<!---   http://www.apache.org/licenses/LICENSE-2.0 -->\n",
    "\n",
    "<!--- Unless required by applicable law or agreed to in writing, -->\n",
    "<!--- software distributed under the License is distributed on an -->\n",
    "<!--- \"AS IS\" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY -->\n",
    "<!--- KIND, either express or implied.  See the License for the -->\n",
    "<!--- specific language governing permissions and limitations -->\n",
    "<!--- under the License. -->\n",
    "\n",
    "# Step 6: Train a Neural Network\n",
    "\n",
    "Now that you have seen all the necessary components for creating a neural network, you are\n",
    "now ready to put all the pieces together and train a model end to end.\n",
    "\n",
    "## 1. Data preparation\n",
    "\n",
    "The typical process for creating and training a model starts with loading and\n",
    "preparing the datasets. For this Network you will use a [dataset of leaf\n",
    "images](https://data.mendeley.com/datasets/hb74ynkjcn/1) that consists of healthy\n",
    "and diseased examples of leafs from twelve different plant species. To get this\n",
    "dataset you have to download and extract it with the following commands."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "230ca647",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Import all the necessary libraries to train\n",
    "import time\n",
    "import os\n",
    "import zipfile\n",
    "\n",
    "import mxnet as mx\n",
    "from mxnet import np, npx, gluon, init, autograd\n",
    "from mxnet.gluon import nn\n",
    "from mxnet.gluon.data.vision import transforms\n",
    "\n",
    "import matplotlib.pyplot as plt\n",
    "import matplotlib.pyplot as plt\n",
    "import numpy as np\n",
    "\n",
    "from prepare_dataset import process_dataset #utility code to rearrange the data\n",
    "\n",
    "mx.np.random.seed(42)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "6ff6356c",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Downloading hb74ynkjcn-1.zip from https://prod-dcd-datasets-cache-zipfiles.s3.eu-west-1.amazonaws.com/hb74ynkjcn-1.zip...\n"
     ]
    }
   ],
   "source": [
    "# Download dataset\n",
    "url = 'https://prod-dcd-datasets-cache-zipfiles.s3.eu-west-1.amazonaws.com/hb74ynkjcn-1.zip'\n",
    "zip_file_path = mx.gluon.utils.download(url)\n",
    "\n",
    "os.makedirs('plants', exist_ok=True)\n",
    "\n",
    "with zipfile.ZipFile(zip_file_path, 'r') as zf:\n",
    "    zf.extractall('plants')\n",
    "\n",
    "os.remove(zip_file_path)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "d75b699e",
   "metadata": {},
   "source": [
    "#### Data inspection\n",
    "\n",
    "If you take a look at the dataset you find the following structure for the directories:"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "406ae69b",
   "metadata": {},
   "source": [
    "```\n",
    "plants\n",
    "|-- Alstonia Scholaris (P2)\n",
    "|-- Arjun (P1)\n",
    "|-- Bael (P4)\n",
    "    |-- diseased\n",
    "        |-- 0016_0001.JPG\n",
    "        |-- .\n",
    "        |-- .\n",
    "        |-- .\n",
    "        |-- 0016_0118.JPG\n",
    "|-- .\n",
    "|-- .\n",
    "|-- .\n",
    "|-- Mango (P0)\n",
    "    |-- diseased\n",
    "    |-- healthy\n",
    "```\n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "7d9e2dd6",
   "metadata": {},
   "source": [
    "Each plant species has its own directory, for each of those directories you might\n",
    "find subdirectories with examples of diseased leaves, healthy\n",
    "leaves, or both. With this dataset you can formulate different classification\n",
    "problems; for example, you can create a multi-class classifier that determines\n",
    "the species of a plant based on the leaves; you can instead create a binary\n",
    "classifier that tells you whether the plant is healthy or diseased. Additionally, you can create\n",
    "a multi-class, multi-label classifier that tells you both: what species a\n",
    "plant is and whether the plant is diseased or healthy. In this example you will stick to\n",
    "the simplest classification question, which is whether a plant is healthy or not.\n",
    "\n",
    "To do this, you need to manipulate the dataset in two ways. First, you need to\n",
    "combine all images with labels consisting of healthy and diseased, regardless of the species, and then you\n",
    "need to split the data into train, validation, and test sets. We prepared a\n",
    "small utility script that does this to get the dataset ready for you.\n",
    "Once you run this utility code on the data, the structure will be\n",
    "already organized in folders containing the right images in each of the classes,\n",
    "you can use the `ImageFolderDataset` class to import the images from the file to MXNet."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "5a3eed54",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Call the utility function to rearrange the images\n",
    "process_dataset('plants')"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "fc875793",
   "metadata": {},
   "source": [
    "The dataset is located in the `datasets` folder and the new structure\n",
    "looks like this:"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "44abbbb6",
   "metadata": {},
   "source": [
    "```\n",
    "datasets\n",
    "|-- test\n",
    "    |-- diseased\n",
    "    |-- healthy\n",
    "|-- train\n",
    "|-- validation\n",
    "    |-- diseased\n",
    "    |-- healthy\n",
    "        |-- image1.JPG\n",
    "        |-- image2.JPG\n",
    "        |-- .\n",
    "        |-- .\n",
    "        |-- .\n",
    "        |-- imagen.JPG\n",
    "```\n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "f905ea5a",
   "metadata": {},
   "source": [
    "Now, you need to create three different Dataset objects from the `train`,\n",
    "`validation`, and `test` folders, and the `ImageFolderDataset` class takes\n",
    "care of inferring the classes from the directory names. If you don't remember\n",
    "how the `ImageFolderDataset` works, take a look at [Step 5](5-datasets.md)\n",
    "of this course for a deeper description."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "0918bdf5",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Use ImageFolderDataset to create a Dataset object from directory structure\n",
    "train_dataset = gluon.data.vision.ImageFolderDataset('./datasets/train')\n",
    "val_dataset = gluon.data.vision.ImageFolderDataset('./datasets/validation')\n",
    "test_dataset = gluon.data.vision.ImageFolderDataset('./datasets/test')"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "75e8bbf8",
   "metadata": {},
   "source": [
    "The result from this operation is a different Dataset object for each folder.\n",
    "These objects hold a collection of images and labels and as such they can be\n",
    "indexed, to get the $i$-th element from the dataset. The $i$-th element is a\n",
    "tuple with two objects, the first object of the tuple is the image in array\n",
    "form and the second is the corresponding label for that image."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "09bff458",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "[03:58:42] /work/mxnet/src/storage/storage.cc:202: Using Pooled (Naive) StorageManager for CPU\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Data type: uint8\n",
      "Label: 0\n",
      "Label description: diseased\n",
      "Image shape: (4000, 6000, 3)\n"
     ]
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "sample_idx = 888 # choose a random sample\n",
    "sample = train_dataset[sample_idx]\n",
    "data = sample[0]\n",
    "label = sample[1]\n",
    "\n",
    "plt.imshow(data.asnumpy())\n",
    "print(f\"Data type: {data.dtype}\")\n",
    "print(f\"Label: {label}\")\n",
    "print(f\"Label description: {train_dataset.synsets[label]}\")\n",
    "print(f\"Image shape: {data.shape}\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "6b5ce74a",
   "metadata": {},
   "source": [
    "As you can see from the plot, the image size is very large 4000 x 6000 pixels.\n",
    "Usually, you downsize images before passing them to a neural network to reduce the training time.\n",
    "It is also customary to make slight modifications to the images to improve generalization. That is why you add\n",
    "transformations to the data in a process called Data Augmentation.\n",
    "\n",
    "You can augment data in MXNet using `transforms`. For a complete list of all\n",
    "the available transformations in MXNet check out\n",
    "[available transforms](../../../api/gluon/data/vision/transforms/index.rst).\n",
    "It is very common to use more than one transform per image, and it is also\n",
    "common to process transforms sequentially. To this end, you can use the `transforms.Compose` class.\n",
    "This class is very useful to create a transformation pipeline for your images.\n",
    "\n",
    "You have to compose two different transformation pipelines, one for training\n",
    "and the other one for validating and testing. This is because each pipeline\n",
    "serves different pursposes. You need to downsize, convert to tensor and normalize\n",
    "images across all the different datsets; however, you typically do not want to randomly flip\n",
    "or add color jitter to the validation or test images since you could reduce performance."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "251a018b",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Import transforms as compose a series of transformations to the images\n",
    "from mxnet.gluon.data.vision import transforms\n",
    "\n",
    "jitter_param = 0.05\n",
    "\n",
    "# mean and std for normalizing image value in range (0,1)\n",
    "mean = [0.485, 0.456, 0.406]\n",
    "std = [0.229, 0.224, 0.225]\n",
    "\n",
    "training_transformer = transforms.Compose([\n",
    "    transforms.Resize(size=224, keep_ratio=True),\n",
    "    transforms.CenterCrop(128),\n",
    "    transforms.RandomFlipLeftRight(),\n",
    "    transforms.RandomColorJitter(contrast=jitter_param),\n",
    "    transforms.ToTensor(),\n",
    "    transforms.Normalize(mean, std)\n",
    "])\n",
    "\n",
    "validation_transformer = transforms.Compose([\n",
    "    transforms.Resize(size=224, keep_ratio=True),\n",
    "    transforms.CenterCrop(128),\n",
    "    transforms.ToTensor(),\n",
    "    transforms.Normalize(mean, std)\n",
    "])"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "53e79166",
   "metadata": {},
   "source": [
    "With your augmentations ready, you can create the `DataLoaders` to use them. To\n",
    "do this the `gluon.data.DataLoader` class comes in handy. You have to pass the dataset with\n",
    "the applied transformations (notice the `.transform_first()` method on the datasets)\n",
    "to `gluon.data.DataLoader`. Additionally, you need to decide the batch size,\n",
    "which is how many images you will be passing to the network,\n",
    "and whether you want to shuffle the dataset."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "9ec371ba",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Create data loaders\n",
    "batch_size = 4\n",
    "train_loader = gluon.data.DataLoader(train_dataset.transform_first(training_transformer),\n",
    "                                     batch_size=batch_size,\n",
    "                                     shuffle=True,\n",
    "                                     try_nopython=True)\n",
    "validation_loader = gluon.data.DataLoader(val_dataset.transform_first(validation_transformer),\n",
    "                                          batch_size=batch_size,\n",
    "                                          try_nopython=True)\n",
    "test_loader = gluon.data.DataLoader(test_dataset.transform_first(validation_transformer),\n",
    "                                    batch_size=batch_size,\n",
    "                                    try_nopython=True)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "6da13057",
   "metadata": {},
   "source": [
    "Now, you can inspect the transformations that you made to the images. A prepared\n",
    "utility function has been provided for this."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "2517642e",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Function to plot batch\n",
    "def show_batch(batch, columns=4, fig_size=(9, 5), pad=1):\n",
    "    labels = batch[1].asnumpy()\n",
    "    batch = batch[0] / 2 + 0.5     # unnormalize\n",
    "    batch = np.clip(batch.asnumpy(), 0, 1) # clip values\n",
    "    size = batch.shape[0]\n",
    "    rows = int(size / columns)\n",
    "    fig, axes = plt.subplots(rows, columns, figsize=fig_size)\n",
    "    for ax, img, label in zip(axes.flatten(), batch, labels):\n",
    "        ax.imshow(np.transpose(img, (1, 2, 0)))\n",
    "        ax.set(title=f\"Label: {label}\")\n",
    "    fig.tight_layout(h_pad=pad, w_pad=pad)\n",
    "    plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "8c6169e2",
   "metadata": {},
   "outputs": [],
   "source": [
    "for batch in train_loader:\n",
    "    a = batch\n",
    "    break"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "3af55164",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 900x500 with 4 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "show_batch(a)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "8fff677c",
   "metadata": {},
   "source": [
    "You can see that the original images changed to have different sizes and variations\n",
    "in color and lighting. These changes followed the specified transformations you stated\n",
    "in the pipeline. You are now ready to go to the next step: **Create the\n",
    "architecture**.\n",
    "\n",
    "## 2. Create Neural Network\n",
    "\n",
    "Convolutional neural networks are a great tool to capture the spatial\n",
    "relationship of pixel values within images, for this reason they have become the\n",
    "gold standard for computer vision. In this example you will create a small convolutional neural\n",
    "network using what you learned from [Step 2](2-create-nn.md) of this crash course series.\n",
    "First, you can set up two functions that will generate the two types of blocks\n",
    "you intend to use, the convolution block and the dense block. Then you can create an\n",
    "entire network based on these two blocks using a custom class."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "d20cb2c1",
   "metadata": {},
   "outputs": [],
   "source": [
    "# The convolutional block has a convolution layer, a max pool layer and a batch normalization layer\n",
    "def conv_block(filters, kernel_size=2, stride=2, batch_norm=True):\n",
    "    conv_block = nn.HybridSequential()\n",
    "    conv_block.add(nn.Conv2D(channels=filters, kernel_size=kernel_size, activation='relu'),\n",
    "              nn.MaxPool2D(pool_size=4, strides=stride))\n",
    "    if batch_norm:\n",
    "        conv_block.add(nn.BatchNorm())\n",
    "    return conv_block\n",
    "\n",
    "# The dense block consists of a dense layer and a dropout layer\n",
    "def dense_block(neurons, activation='relu', dropout=0.2):\n",
    "    dense_block = nn.HybridSequential()\n",
    "    dense_block.add(nn.Dense(neurons, activation=activation))\n",
    "    if dropout:\n",
    "        dense_block.add(nn.Dropout(dropout))\n",
    "    return dense_block"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "8a4756d9",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Create neural network blueprint using the blocks\n",
    "class LeafNetwork(nn.HybridBlock):\n",
    "    def __init__(self):\n",
    "        super(LeafNetwork, self).__init__()\n",
    "        self.conv1 = conv_block(32)\n",
    "        self.conv2 = conv_block(64)\n",
    "        self.conv3 = conv_block(128)\n",
    "        self.flatten = nn.Flatten()\n",
    "        self.dense1 = dense_block(100)\n",
    "        self.dense2 = dense_block(10)\n",
    "        self.dense3 = nn.Dense(2)\n",
    "\n",
    "    def forward(self, batch):\n",
    "        batch = self.conv1(batch)\n",
    "        batch = self.conv2(batch)\n",
    "        batch = self.conv3(batch)\n",
    "        batch = self.flatten(batch)\n",
    "        batch = self.dense1(batch)\n",
    "        batch = self.dense2(batch)\n",
    "        batch = self.dense3(batch)\n",
    "\n",
    "        return batch"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "4d2fdd9f",
   "metadata": {},
   "source": [
    "You have concluded the architecting part of the network, so now you can actually\n",
    "build a model from that architecture for training. As you have seen\n",
    "previously on [Step 4](4-components.md) of this\n",
    "crash course series, to use the network you need to initialize the parameters and\n",
    "hybridize the model."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "f3d80177",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "--------------------------------------------------------------------------------\n",
      "        Layer (type)                                Output Shape         Param #\n",
      "================================================================================\n",
      "               Input                            (4, 3, 128, 128)               0\n",
      "        Activation-1                           (4, 32, 127, 127)               0\n",
      "            Conv2D-2                           (4, 32, 127, 127)             416\n",
      "         MaxPool2D-3                             (4, 32, 62, 62)               0\n",
      "         BatchNorm-4                             (4, 32, 62, 62)             128\n",
      "        Activation-5                             (4, 64, 61, 61)               0\n",
      "            Conv2D-6                             (4, 64, 61, 61)            8256\n",
      "         MaxPool2D-7                             (4, 64, 29, 29)               0\n",
      "         BatchNorm-8                             (4, 64, 29, 29)             256\n",
      "        Activation-9                            (4, 128, 28, 28)               0\n",
      "           Conv2D-10                            (4, 128, 28, 28)           32896\n",
      "        MaxPool2D-11                            (4, 128, 13, 13)               0\n",
      "        BatchNorm-12                            (4, 128, 13, 13)             512\n",
      "          Flatten-13                                  (4, 21632)               0\n",
      "       Activation-14                                    (4, 100)               0\n",
      "            Dense-15                                    (4, 100)         2163300\n",
      "          Dropout-16                                    (4, 100)               0\n",
      "       Activation-17                                     (4, 10)               0\n",
      "            Dense-18                                     (4, 10)            1010\n",
      "          Dropout-19                                     (4, 10)               0\n",
      "            Dense-20                                      (4, 2)              22\n",
      "      LeafNetwork-21                                      (4, 2)               0\n",
      "================================================================================\n",
      "Parameters in forward computation graph, duplicate included\n",
      "   Total params: 2206796\n",
      "   Trainable params: 2206348\n",
      "   Non-trainable params: 448\n",
      "Shared params in forward computation graph: 0\n",
      "Unique parameters in model: 2206796\n",
      "--------------------------------------------------------------------------------\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "[03:58:49] /work/mxnet/src/storage/storage.cc:202: Using Pooled (Naive) StorageManager for GPU\n"
     ]
    }
   ],
   "source": [
    "# Create the model based on the blueprint provided and initialize the parameters\n",
    "device = mx.gpu()\n",
    "\n",
    "initializer = mx.initializer.Xavier()\n",
    "\n",
    "model = LeafNetwork()\n",
    "model.initialize(initializer, device=device)\n",
    "model.summary(mx.np.random.uniform(size=(4, 3, 128, 128), device=device))\n",
    "model.hybridize()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "3c1da9c3",
   "metadata": {},
   "source": [
    "## 3. Choose Optimizer and Loss function\n",
    "\n",
    "With the network created you can move on to choosing an optimizer and a loss\n",
    "function. The network you created uses these components to make an informed decision on how\n",
    "to tune the parameters to fit the final objective better. You can use the `gluon.Trainer` class to\n",
    "help with optimizing these parameters. The `gluon.Trainer` class needs two things to work\n",
    "properly: the parameters needing to be tuned and the optimizer with its\n",
    "corresponding hyperparameters. The trainer uses the error reported by the loss\n",
    "function to optimize these parameters.\n",
    "\n",
    "For this particular dataset you will use Stochastic Gradient Descent as the\n",
    "optimizer and Cross Entropy as the loss function."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "db61ddf0",
   "metadata": {},
   "outputs": [],
   "source": [
    "# SGD optimizer\n",
    "optimizer = 'sgd'\n",
    "\n",
    "# Set parameters\n",
    "optimizer_params = {'learning_rate': 0.001}\n",
    "\n",
    "# Define the trainer for the model\n",
    "trainer = gluon.Trainer(model.collect_params(), optimizer, optimizer_params)\n",
    "\n",
    "# Define the loss function\n",
    "loss_fn = gluon.loss.SoftmaxCrossEntropyLoss()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "2005f458",
   "metadata": {},
   "source": [
    "Finally, you have to set up the training loop, and you need to create a function to evaluate the performance of the network on the validation dataset."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "95d1c7ab",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Function to return the accuracy for the validation and test set\n",
    "def test(val_data):\n",
    "    acc = gluon.metric.Accuracy()\n",
    "    for batch in val_data:\n",
    "        data = batch[0]\n",
    "        labels = batch[1]\n",
    "        outputs = model(data.to_device(device))\n",
    "        acc.update([labels], [outputs])\n",
    "\n",
    "    _, accuracy = acc.get()\n",
    "    return accuracy"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "33d6b651",
   "metadata": {},
   "source": [
    "## 4. Training Loop\n",
    "\n",
    "Now that you have everything set up, you can start training your network. This might\n",
    "take some time to train depending on the hardware, number of layers, batch size and\n",
    "images you use. For this particular case, you will only train for 2 epochs."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "id": "2f42f862",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "[03:58:51] /work/mxnet/src/operator/cudnn_ops.cc:421: Auto-tuning cuDNN op, set MXNET_CUDNN_AUTOTUNE_DEFAULT to 0 to disable\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "[03:58:52] /work/mxnet/src/operator/cudnn_ops.cc:421: Auto-tuning cuDNN op, set MXNET_CUDNN_AUTOTUNE_DEFAULT to 0 to disable\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[1] Batch[5] Speed: 1.2117561585375851 samples/sec                   batch loss = 0.8407745957374573 | accuracy = 0.45\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[1] Batch[10] Speed: 1.2600317763951179 samples/sec                   batch loss = 0.6950667500495911 | accuracy = 0.6\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[1] Batch[15] Speed: 1.262876134951749 samples/sec                   batch loss = 0.16495956480503082 | accuracy = 0.6166666666666667\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[1] Batch[20] Speed: 1.2658993500361686 samples/sec                   batch loss = 0.9710271954536438 | accuracy = 0.5875\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[1] Batch[25] Speed: 1.2636251830319851 samples/sec                   batch loss = 0.8496341109275818 | accuracy = 0.6\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[1] Batch[30] Speed: 1.2626422335708292 samples/sec                   batch loss = 0.6572840809822083 | accuracy = 0.575\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[1] Batch[35] Speed: 1.262363394957624 samples/sec                   batch loss = 0.5903766751289368 | accuracy = 0.5428571428571428\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[1] Batch[40] Speed: 1.2612925085888125 samples/sec                   batch loss = 0.5169366002082825 | accuracy = 0.58125\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[1] Batch[45] Speed: 1.2586043407599812 samples/sec                   batch loss = 0.7783154249191284 | accuracy = 0.6\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[1] Batch[50] Speed: 1.2591356708160246 samples/sec                   batch loss = 0.8414345979690552 | accuracy = 0.59\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[1] Batch[55] Speed: 1.2622587316453076 samples/sec                   batch loss = 0.39347484707832336 | accuracy = 0.6045454545454545\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[1] Batch[60] Speed: 1.259024455843083 samples/sec                   batch loss = 0.6124871373176575 | accuracy = 0.6125\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[1] Batch[65] Speed: 1.2627991403712975 samples/sec                   batch loss = 0.6423971056938171 | accuracy = 0.6269230769230769\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[1] Batch[70] Speed: 1.2625957677509934 samples/sec                   batch loss = 0.6456457376480103 | accuracy = 0.6285714285714286\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[1] Batch[75] Speed: 1.2569808289103817 samples/sec                   batch loss = 0.48864680528640747 | accuracy = 0.63\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[1] Batch[80] Speed: 1.2614926159607853 samples/sec                   batch loss = 0.8163663148880005 | accuracy = 0.6375\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[1] Batch[85] Speed: 1.2603451845472566 samples/sec                   batch loss = 0.7628596425056458 | accuracy = 0.6352941176470588\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[1] Batch[90] Speed: 1.2587507069455706 samples/sec                   batch loss = 0.21568706631660461 | accuracy = 0.6361111111111111\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[1] Batch[95] Speed: 1.259375931974608 samples/sec                   batch loss = 0.7214741706848145 | accuracy = 0.6263157894736842\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[1] Batch[100] Speed: 1.2595401600226785 samples/sec                   batch loss = 0.28124821186065674 | accuracy = 0.6325\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[1] Batch[105] Speed: 1.2647009891708403 samples/sec                   batch loss = 0.662185788154602 | accuracy = 0.6309523809523809\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[1] Batch[110] Speed: 1.2561870552777334 samples/sec                   batch loss = 0.8813420534133911 | accuracy = 0.625\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[1] Batch[115] Speed: 1.2627784199764653 samples/sec                   batch loss = 1.1359597444534302 | accuracy = 0.6217391304347826\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[1] Batch[120] Speed: 1.263076269717103 samples/sec                   batch loss = 0.4332994520664215 | accuracy = 0.6291666666666667\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[1] Batch[125] Speed: 1.2575660245519422 samples/sec                   batch loss = 0.481771856546402 | accuracy = 0.63\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[1] Batch[130] Speed: 1.2607005247728935 samples/sec                   batch loss = 0.9104111194610596 | accuracy = 0.6230769230769231\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[1] Batch[135] Speed: 1.2556771940013876 samples/sec                   batch loss = 0.3003590703010559 | accuracy = 0.6259259259259259\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[1] Batch[140] Speed: 1.257888958558277 samples/sec                   batch loss = 0.44806337356567383 | accuracy = 0.6303571428571428\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[1] Batch[145] Speed: 1.2650251184593269 samples/sec                   batch loss = 0.9731339812278748 | accuracy = 0.6275862068965518\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[1] Batch[150] Speed: 1.2658260931105452 samples/sec                   batch loss = 0.7989111542701721 | accuracy = 0.625\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[1] Batch[155] Speed: 1.2566912121659506 samples/sec                   batch loss = 0.5889948010444641 | accuracy = 0.6241935483870967\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[1] Batch[160] Speed: 1.2580514782908117 samples/sec                   batch loss = 1.0139918327331543 | accuracy = 0.625\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[1] Batch[165] Speed: 1.2601242397253165 samples/sec                   batch loss = 0.45098966360092163 | accuracy = 0.6272727272727273\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[1] Batch[170] Speed: 1.2619692409018395 samples/sec                   batch loss = 1.2195454835891724 | accuracy = 0.6294117647058823\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[1] Batch[175] Speed: 1.257507866912004 samples/sec                   batch loss = 0.5146313905715942 | accuracy = 0.6342857142857142\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[1] Batch[180] Speed: 1.2595949122240246 samples/sec                   batch loss = 0.45457881689071655 | accuracy = 0.6388888888888888\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[1] Batch[185] Speed: 1.2587306858189538 samples/sec                   batch loss = 0.5231857895851135 | accuracy = 0.6364864864864865\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[1] Batch[190] Speed: 1.2630439396164814 samples/sec                   batch loss = 0.350179523229599 | accuracy = 0.6394736842105263\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[1] Batch[195] Speed: 1.2577441127545546 samples/sec                   batch loss = 1.007402777671814 | accuracy = 0.6397435897435897\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[1] Batch[200] Speed: 1.2592403839203896 samples/sec                   batch loss = 0.9171308279037476 | accuracy = 0.64\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[1] Batch[205] Speed: 1.2584326163652642 samples/sec                   batch loss = 0.8950124382972717 | accuracy = 0.6414634146341464\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[1] Batch[210] Speed: 1.2561466122924982 samples/sec                   batch loss = 0.28655946254730225 | accuracy = 0.638095238095238\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[1] Batch[215] Speed: 1.25593052159335 samples/sec                   batch loss = 0.6185159087181091 | accuracy = 0.6395348837209303\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[1] Batch[220] Speed: 1.2547902724004891 samples/sec                   batch loss = 0.6935330033302307 | accuracy = 0.6363636363636364\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[1] Batch[225] Speed: 1.2614158848236938 samples/sec                   batch loss = 0.5271984338760376 | accuracy = 0.6344444444444445\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[1] Batch[230] Speed: 1.259850769267276 samples/sec                   batch loss = 0.5704729557037354 | accuracy = 0.6347826086956522\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[1] Batch[235] Speed: 1.2586212419551717 samples/sec                   batch loss = 0.3812594413757324 | accuracy = 0.6361702127659574\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[1] Batch[240] Speed: 1.2599345956898882 samples/sec                   batch loss = 0.7227175831794739 | accuracy = 0.6385416666666667\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[1] Batch[245] Speed: 1.2605096654985357 samples/sec                   batch loss = 0.48598140478134155 | accuracy = 0.6428571428571429\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[1] Batch[250] Speed: 1.261392933689118 samples/sec                   batch loss = 0.3495320975780487 | accuracy = 0.645\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[1] Batch[255] Speed: 1.2570650273457014 samples/sec                   batch loss = 0.16238412261009216 | accuracy = 0.6460784313725491\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[1] Batch[260] Speed: 1.2601780961678446 samples/sec                   batch loss = 0.282853901386261 | accuracy = 0.6519230769230769\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[1] Batch[265] Speed: 1.2592809318483862 samples/sec                   batch loss = 0.5361605882644653 | accuracy = 0.6528301886792452\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[1] Batch[270] Speed: 1.2609684882943466 samples/sec                   batch loss = 0.4548198878765106 | accuracy = 0.6555555555555556\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[1] Batch[275] Speed: 1.2589706034861714 samples/sec                   batch loss = 0.8159052133560181 | accuracy = 0.6554545454545454\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[1] Batch[280] Speed: 1.264306231720377 samples/sec                   batch loss = 0.7456441521644592 | accuracy = 0.65625\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[1] Batch[285] Speed: 1.2561571460285408 samples/sec                   batch loss = 0.8854629397392273 | accuracy = 0.6578947368421053\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[1] Batch[290] Speed: 1.2583954266012083 samples/sec                   batch loss = 0.9764561653137207 | accuracy = 0.653448275862069\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[1] Batch[295] Speed: 1.2620161352744728 samples/sec                   batch loss = 0.6067806482315063 | accuracy = 0.652542372881356\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[1] Batch[300] Speed: 1.2585989589104276 samples/sec                   batch loss = 0.6901727914810181 | accuracy = 0.6525\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[1] Batch[305] Speed: 1.2596041799070306 samples/sec                   batch loss = 0.8663436770439148 | accuracy = 0.6516393442622951\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[1] Batch[310] Speed: 1.262342023996454 samples/sec                   batch loss = 0.3564245402812958 | accuracy = 0.6548387096774193\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[1] Batch[315] Speed: 1.2609800508113476 samples/sec                   batch loss = 0.4036303162574768 | accuracy = 0.6547619047619048\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[1] Batch[320] Speed: 1.258629456666479 samples/sec                   batch loss = 0.8869490623474121 | accuracy = 0.65625\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[1] Batch[325] Speed: 1.2576116495451684 samples/sec                   batch loss = 0.40886107087135315 | accuracy = 0.6576923076923077\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[1] Batch[330] Speed: 1.2596941213429396 samples/sec                   batch loss = 0.35565879940986633 | accuracy = 0.6568181818181819\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[1] Batch[335] Speed: 1.2696119488644395 samples/sec                   batch loss = 2.598857879638672 | accuracy = 0.6582089552238806\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[1] Batch[340] Speed: 1.2640666573541182 samples/sec                   batch loss = 0.4242265224456787 | accuracy = 0.6602941176470588\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[1] Batch[345] Speed: 1.2628317431031209 samples/sec                   batch loss = 0.5970653295516968 | accuracy = 0.6594202898550725\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[1] Batch[350] Speed: 1.2630304375350017 samples/sec                   batch loss = 0.9351227879524231 | accuracy = 0.6585714285714286\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[1] Batch[355] Speed: 1.2608853770969737 samples/sec                   batch loss = 0.2976606786251068 | accuracy = 0.6612676056338028\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[1] Batch[360] Speed: 1.2636916177206194 samples/sec                   batch loss = 0.604040801525116 | accuracy = 0.6604166666666667\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[1] Batch[365] Speed: 1.2661687639274317 samples/sec                   batch loss = 0.6232295632362366 | accuracy = 0.6616438356164384\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[1] Batch[370] Speed: 1.2707490839506919 samples/sec                   batch loss = 0.1412576287984848 | accuracy = 0.6648648648648648\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[1] Batch[375] Speed: 1.266353120553725 samples/sec                   batch loss = 0.45004159212112427 | accuracy = 0.664\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[1] Batch[380] Speed: 1.264753139980445 samples/sec                   batch loss = 0.5365153551101685 | accuracy = 0.6644736842105263\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[1] Batch[385] Speed: 1.2641402822755679 samples/sec                   batch loss = 0.4807123839855194 | accuracy = 0.6649350649350649\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[1] Batch[390] Speed: 1.265913486637907 samples/sec                   batch loss = 0.24441587924957275 | accuracy = 0.6666666666666666\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[1] Batch[395] Speed: 1.2643907474045544 samples/sec                   batch loss = 0.5377245545387268 | accuracy = 0.6670886075949367\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[1] Batch[400] Speed: 1.2631496842091157 samples/sec                   batch loss = 0.48492205142974854 | accuracy = 0.66625\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[1] Batch[405] Speed: 1.2696088743889655 samples/sec                   batch loss = 0.8884551525115967 | accuracy = 0.6641975308641975\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[1] Batch[410] Speed: 1.2613111889123927 samples/sec                   batch loss = 0.8871831893920898 | accuracy = 0.6646341463414634\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[1] Batch[415] Speed: 1.2609069830590305 samples/sec                   batch loss = 0.7476733922958374 | accuracy = 0.6650602409638554\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[1] Batch[420] Speed: 1.267477241306368 samples/sec                   batch loss = 0.502937912940979 | accuracy = 0.6648809523809524\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[1] Batch[425] Speed: 1.2642218225975328 samples/sec                   batch loss = 0.4086722433567047 | accuracy = 0.6664705882352941\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[1] Batch[430] Speed: 1.2626343464933505 samples/sec                   batch loss = 0.4604116976261139 | accuracy = 0.6662790697674419\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[1] Batch[435] Speed: 1.2690874858783026 samples/sec                   batch loss = 0.9654018878936768 | accuracy = 0.6655172413793103\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[1] Batch[440] Speed: 1.2662694892003932 samples/sec                   batch loss = 0.45917895436286926 | accuracy = 0.6659090909090909\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[1] Batch[445] Speed: 1.266242060522225 samples/sec                   batch loss = 0.41664332151412964 | accuracy = 0.6662921348314607\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[1] Batch[450] Speed: 1.2639832324917184 samples/sec                   batch loss = 0.4053393006324768 | accuracy = 0.6655555555555556\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[1] Batch[455] Speed: 1.262953424139045 samples/sec                   batch loss = 0.4299033582210541 | accuracy = 0.6675824175824175\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[1] Batch[460] Speed: 1.2614882527533655 samples/sec                   batch loss = 0.659080445766449 | accuracy = 0.6679347826086957\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[1] Batch[465] Speed: 1.2642699325108437 samples/sec                   batch loss = 0.275171160697937 | accuracy = 0.6704301075268817\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[1] Batch[470] Speed: 1.2570180292890345 samples/sec                   batch loss = 0.5269567966461182 | accuracy = 0.6696808510638298\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[1] Batch[475] Speed: 1.263326123097298 samples/sec                   batch loss = 0.3419381380081177 | accuracy = 0.6710526315789473\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[1] Batch[480] Speed: 1.258286135398305 samples/sec                   batch loss = 0.45421817898750305 | accuracy = 0.6723958333333333\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[1] Batch[485] Speed: 1.257030178750432 samples/sec                   batch loss = 1.0598242282867432 | accuracy = 0.6721649484536083\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[1] Batch[490] Speed: 1.2628842151742727 samples/sec                   batch loss = 0.6258540153503418 | accuracy = 0.6724489795918367\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[1] Batch[495] Speed: 1.257636914395286 samples/sec                   batch loss = 0.4089224338531494 | accuracy = 0.6742424242424242\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[1] Batch[500] Speed: 1.265036660104928 samples/sec                   batch loss = 0.7401823997497559 | accuracy = 0.674\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[1] Batch[505] Speed: 1.2599658205721225 samples/sec                   batch loss = 0.39657890796661377 | accuracy = 0.6742574257425743\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[1] Batch[510] Speed: 1.2604296449355978 samples/sec                   batch loss = 0.6032729744911194 | accuracy = 0.6730392156862746\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[1] Batch[515] Speed: 1.2628212872331592 samples/sec                   batch loss = 0.38749903440475464 | accuracy = 0.6742718446601942\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[1] Batch[520] Speed: 1.261988700694164 samples/sec                   batch loss = 0.4940071702003479 | accuracy = 0.6745192307692308\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[1] Batch[525] Speed: 1.2585048311950953 samples/sec                   batch loss = 0.4013983905315399 | accuracy = 0.6752380952380952\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[1] Batch[530] Speed: 1.2579631860992246 samples/sec                   batch loss = 0.9785982370376587 | accuracy = 0.6759433962264151\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[1] Batch[535] Speed: 1.2621824770220973 samples/sec                   batch loss = 0.7318115234375 | accuracy = 0.6757009345794392\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[1] Batch[540] Speed: 1.2588830323856002 samples/sec                   batch loss = 0.6308591365814209 | accuracy = 0.6768518518518518\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[1] Batch[545] Speed: 1.25685210434053 samples/sec                   batch loss = 0.22763293981552124 | accuracy = 0.6779816513761467\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[1] Batch[550] Speed: 1.2603999120728935 samples/sec                   batch loss = 0.22123196721076965 | accuracy = 0.6795454545454546\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[1] Batch[555] Speed: 1.263492715222711 samples/sec                   batch loss = 0.34091323614120483 | accuracy = 0.6806306306306307\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[1] Batch[560] Speed: 1.2527241564847895 samples/sec                   batch loss = 0.24208460748195648 | accuracy = 0.68125\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[1] Batch[565] Speed: 1.2553553005585836 samples/sec                   batch loss = 0.5416485071182251 | accuracy = 0.6823008849557523\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[1] Batch[570] Speed: 1.2628149187426658 samples/sec                   batch loss = 0.6605169177055359 | accuracy = 0.6833333333333333\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[1] Batch[575] Speed: 1.2552407140167965 samples/sec                   batch loss = 0.5949068665504456 | accuracy = 0.6830434782608695\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[1] Batch[580] Speed: 1.2603543685925267 samples/sec                   batch loss = 0.4867265820503235 | accuracy = 0.6836206896551724\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[1] Batch[585] Speed: 1.2610759710129895 samples/sec                   batch loss = 0.2170935422182083 | accuracy = 0.6846153846153846\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[1] Batch[590] Speed: 1.2605312585863524 samples/sec                   batch loss = 0.4663027226924896 | accuracy = 0.684322033898305\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[1] Batch[595] Speed: 1.2591787636310143 samples/sec                   batch loss = 0.7614539861679077 | accuracy = 0.6852941176470588\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[1] Batch[600] Speed: 1.2575934557109352 samples/sec                   batch loss = 0.2279791533946991 | accuracy = 0.6854166666666667\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[1] Batch[605] Speed: 1.2571351071271082 samples/sec                   batch loss = 0.4409123659133911 | accuracy = 0.6859504132231405\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[1] Batch[610] Speed: 1.2615084565544623 samples/sec                   batch loss = 0.5236684083938599 | accuracy = 0.6856557377049181\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[1] Batch[615] Speed: 1.2559101200034855 samples/sec                   batch loss = 0.353786438703537 | accuracy = 0.6861788617886179\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[1] Batch[620] Speed: 1.262189029050061 samples/sec                   batch loss = 0.5264773964881897 | accuracy = 0.6858870967741936\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[1] Batch[625] Speed: 1.2615608187128786 samples/sec                   batch loss = 0.7498373985290527 | accuracy = 0.6852\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[1] Batch[630] Speed: 1.2565380780734718 samples/sec                   batch loss = 0.5353211760520935 | accuracy = 0.6861111111111111\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[1] Batch[635] Speed: 1.2595502779465924 samples/sec                   batch loss = 0.8991682529449463 | accuracy = 0.6858267716535433\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[1] Batch[640] Speed: 1.2648834881414082 samples/sec                   batch loss = 1.7493432760238647 | accuracy = 0.686328125\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[1] Batch[645] Speed: 1.2587968901807078 samples/sec                   batch loss = 0.720465898513794 | accuracy = 0.6872093023255814\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[1] Batch[650] Speed: 1.2586424871181547 samples/sec                   batch loss = 0.3069595992565155 | accuracy = 0.6884615384615385\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[1] Batch[655] Speed: 1.259567204556576 samples/sec                   batch loss = 0.6302878856658936 | accuracy = 0.6893129770992367\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[1] Batch[660] Speed: 1.262631780838784 samples/sec                   batch loss = 0.512580931186676 | accuracy = 0.6890151515151515\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[1] Batch[665] Speed: 1.2597347930861371 samples/sec                   batch loss = 0.776778519153595 | accuracy = 0.6894736842105263\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[1] Batch[670] Speed: 1.2602938699740822 samples/sec                   batch loss = 0.8710252046585083 | accuracy = 0.6899253731343283\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[1] Batch[675] Speed: 1.2642717426582641 samples/sec                   batch loss = 0.5822662115097046 | accuracy = 0.6911111111111111\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[1] Batch[680] Speed: 1.2684873009248339 samples/sec                   batch loss = 0.4336772859096527 | accuracy = 0.6908088235294118\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[1] Batch[685] Speed: 1.2698962100099869 samples/sec                   batch loss = 0.28341567516326904 | accuracy = 0.6908759124087591\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[1] Batch[690] Speed: 1.2630829261197474 samples/sec                   batch loss = 0.12648537755012512 | accuracy = 0.691304347826087\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[1] Batch[695] Speed: 1.260213498164763 samples/sec                   batch loss = 0.4368666410446167 | accuracy = 0.6928057553956835\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[1] Batch[700] Speed: 1.2577969172564412 samples/sec                   batch loss = 0.5403681397438049 | accuracy = 0.6928571428571428\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[1] Batch[705] Speed: 1.2644487810628 samples/sec                   batch loss = 1.188158392906189 | accuracy = 0.6925531914893617\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[1] Batch[710] Speed: 1.2657738537809726 samples/sec                   batch loss = 0.4219844937324524 | accuracy = 0.6929577464788732\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[1] Batch[715] Speed: 1.26430461202618 samples/sec                   batch loss = 0.6041598916053772 | accuracy = 0.6937062937062937\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[1] Batch[720] Speed: 1.2660933738067468 samples/sec                   batch loss = 0.3373050391674042 | accuracy = 0.6954861111111111\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[1] Batch[725] Speed: 1.2608137415731089 samples/sec                   batch loss = 0.3431106209754944 | accuracy = 0.6951724137931035\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[1] Batch[730] Speed: 1.265837171840635 samples/sec                   batch loss = 0.45366260409355164 | accuracy = 0.6958904109589041\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[1] Batch[735] Speed: 1.2657961051071804 samples/sec                   batch loss = 0.5519353747367859 | accuracy = 0.6965986394557823\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[1] Batch[740] Speed: 1.2599134015001014 samples/sec                   batch loss = 0.3560154139995575 | accuracy = 0.6972972972972973\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[1] Batch[745] Speed: 1.261615936477399 samples/sec                   batch loss = 0.5393974184989929 | accuracy = 0.696979865771812\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[1] Batch[750] Speed: 1.2618694832937762 samples/sec                   batch loss = 0.529081404209137 | accuracy = 0.6956666666666667\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[1] Batch[755] Speed: 1.2665639205676777 samples/sec                   batch loss = 0.328561395406723 | accuracy = 0.6963576158940398\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[1] Batch[760] Speed: 1.262263290121354 samples/sec                   batch loss = 0.5322239398956299 | accuracy = 0.6967105263157894\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[1] Batch[765] Speed: 1.2613233266780846 samples/sec                   batch loss = 0.4723161458969116 | accuracy = 0.6964052287581699\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[1] Batch[770] Speed: 1.2640637049164642 samples/sec                   batch loss = 0.37635189294815063 | accuracy = 0.6957792207792208\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[1] Batch[775] Speed: 1.267898414962233 samples/sec                   batch loss = 0.7176620960235596 | accuracy = 0.6958064516129032\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[1] Batch[780] Speed: 1.2670247700644348 samples/sec                   batch loss = 0.5387542843818665 | accuracy = 0.6955128205128205\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[1] Batch[785] Speed: 1.2694301000345254 samples/sec                   batch loss = 0.9078068733215332 | accuracy = 0.6945859872611465\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[Epoch 1] training: accuracy=0.694479695431472\n",
      "[Epoch 1] time cost: 643.0942394733429\n",
      "[Epoch 1] validation: validation accuracy=0.7644444444444445\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[2] Batch[5] Speed: 1.2679289817762778 samples/sec                   batch loss = 0.5397403240203857 | accuracy = 0.75\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[2] Batch[10] Speed: 1.272866250465929 samples/sec                   batch loss = 0.948280394077301 | accuracy = 0.75\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[2] Batch[15] Speed: 1.268499193560338 samples/sec                   batch loss = 0.5206238627433777 | accuracy = 0.75\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[2] Batch[20] Speed: 1.2710240327799824 samples/sec                   batch loss = 0.6208543181419373 | accuracy = 0.7875\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[2] Batch[25] Speed: 1.2755901476774818 samples/sec                   batch loss = 0.10611335933208466 | accuracy = 0.8\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[2] Batch[30] Speed: 1.2712236762645583 samples/sec                   batch loss = 0.2262563407421112 | accuracy = 0.7916666666666666\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[2] Batch[35] Speed: 1.2711524985284233 samples/sec                   batch loss = 0.6930609345436096 | accuracy = 0.8142857142857143\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[2] Batch[40] Speed: 1.264101420963711 samples/sec                   batch loss = 0.3380635380744934 | accuracy = 0.825\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[2] Batch[45] Speed: 1.266135606456582 samples/sec                   batch loss = 0.4632367789745331 | accuracy = 0.8111111111111111\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[2] Batch[50] Speed: 1.2734662375633319 samples/sec                   batch loss = 0.8806115388870239 | accuracy = 0.81\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[2] Batch[55] Speed: 1.2723326311085987 samples/sec                   batch loss = 0.7208840847015381 | accuracy = 0.8\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[2] Batch[60] Speed: 1.2696818011162188 samples/sec                   batch loss = 0.07581078261137009 | accuracy = 0.8\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[2] Batch[65] Speed: 1.2702790777121855 samples/sec                   batch loss = 0.21203313767910004 | accuracy = 0.8\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[2] Batch[70] Speed: 1.270955476980942 samples/sec                   batch loss = 0.5215021371841431 | accuracy = 0.8\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[2] Batch[75] Speed: 1.2712049901332667 samples/sec                   batch loss = 1.070705771446228 | accuracy = 0.79\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[2] Batch[80] Speed: 1.265463276392116 samples/sec                   batch loss = 0.47908130288124084 | accuracy = 0.790625\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[2] Batch[85] Speed: 1.2663037050360229 samples/sec                   batch loss = 0.28132444620132446 | accuracy = 0.7852941176470588\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[2] Batch[90] Speed: 1.2675077878160201 samples/sec                   batch loss = 0.3856823742389679 | accuracy = 0.7833333333333333\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[2] Batch[95] Speed: 1.2655835557272783 samples/sec                   batch loss = 0.3750905990600586 | accuracy = 0.7868421052631579\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[2] Batch[100] Speed: 1.2727139765969901 samples/sec                   batch loss = 0.9113474488258362 | accuracy = 0.79\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[2] Batch[105] Speed: 1.2663812231679639 samples/sec                   batch loss = 0.4197746217250824 | accuracy = 0.7904761904761904\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[2] Batch[110] Speed: 1.275478528264064 samples/sec                   batch loss = 0.5012903213500977 | accuracy = 0.7909090909090909\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[2] Batch[115] Speed: 1.2657278256234725 samples/sec                   batch loss = 0.6082658767700195 | accuracy = 0.7891304347826087\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[2] Batch[120] Speed: 1.2717082626469367 samples/sec                   batch loss = 0.3968459367752075 | accuracy = 0.7875\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[2] Batch[125] Speed: 1.2674187378388255 samples/sec                   batch loss = 0.2526654005050659 | accuracy = 0.79\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[2] Batch[130] Speed: 1.269791062759885 samples/sec                   batch loss = 0.9633570313453674 | accuracy = 0.7846153846153846\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[2] Batch[135] Speed: 1.272482207890896 samples/sec                   batch loss = 0.6146144270896912 | accuracy = 0.7796296296296297\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[2] Batch[140] Speed: 1.267061227640173 samples/sec                   batch loss = 1.8042162656784058 | accuracy = 0.7767857142857143\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[2] Batch[145] Speed: 1.2666973200904503 samples/sec                   batch loss = 0.586370587348938 | accuracy = 0.7741379310344828\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[2] Batch[150] Speed: 1.2686924801465453 samples/sec                   batch loss = 0.32586824893951416 | accuracy = 0.7716666666666666\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[2] Batch[155] Speed: 1.2678804971702227 samples/sec                   batch loss = 0.24084599316120148 | accuracy = 0.7693548387096775\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[2] Batch[160] Speed: 1.266468502163054 samples/sec                   batch loss = 0.25556641817092896 | accuracy = 0.7703125\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[2] Batch[165] Speed: 1.2721240543452406 samples/sec                   batch loss = 0.7530019879341125 | accuracy = 0.7712121212121212\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[2] Batch[170] Speed: 1.2666229188982205 samples/sec                   batch loss = 0.318692147731781 | accuracy = 0.7691176470588236\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[2] Batch[175] Speed: 1.2728078278380586 samples/sec                   batch loss = 0.3775341212749481 | accuracy = 0.7714285714285715\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[2] Batch[180] Speed: 1.2651290008520302 samples/sec                   batch loss = 0.4126252830028534 | accuracy = 0.7694444444444445\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[2] Batch[185] Speed: 1.2677455072008634 samples/sec                   batch loss = 0.8102496266365051 | accuracy = 0.7662162162162162\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[2] Batch[190] Speed: 1.2713236660328695 samples/sec                   batch loss = 0.5861036777496338 | accuracy = 0.7671052631578947\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[2] Batch[195] Speed: 1.269096125777857 samples/sec                   batch loss = 0.17301079630851746 | accuracy = 0.7692307692307693\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[2] Batch[200] Speed: 1.267019985761407 samples/sec                   batch loss = 0.261074036359787 | accuracy = 0.76875\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[2] Batch[205] Speed: 1.268189003007044 samples/sec                   batch loss = 0.5001844763755798 | accuracy = 0.7695121951219512\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[2] Batch[210] Speed: 1.2661288222889537 samples/sec                   batch loss = 0.29652106761932373 | accuracy = 0.7714285714285715\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[2] Batch[215] Speed: 1.274298652961303 samples/sec                   batch loss = 0.6518102288246155 | accuracy = 0.7674418604651163\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[2] Batch[220] Speed: 1.2708700814355367 samples/sec                   batch loss = 0.34153062105178833 | accuracy = 0.7693181818181818\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[2] Batch[225] Speed: 1.2661095212519449 samples/sec                   batch loss = 0.31635040044784546 | accuracy = 0.7711111111111111\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[2] Batch[230] Speed: 1.2743250766962615 samples/sec                   batch loss = 0.6876500248908997 | accuracy = 0.7695652173913043\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[2] Batch[235] Speed: 1.2695987863709035 samples/sec                   batch loss = 0.6100889444351196 | accuracy = 0.7659574468085106\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[2] Batch[240] Speed: 1.2706704527518442 samples/sec                   batch loss = 0.19952930510044098 | accuracy = 0.7677083333333333\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[2] Batch[245] Speed: 1.2651874839374462 samples/sec                   batch loss = 0.45317843556404114 | accuracy = 0.7663265306122449\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[2] Batch[250] Speed: 1.2718971287502363 samples/sec                   batch loss = 0.6451046466827393 | accuracy = 0.768\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[2] Batch[255] Speed: 1.268740163363412 samples/sec                   batch loss = 0.25341954827308655 | accuracy = 0.7676470588235295\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[2] Batch[260] Speed: 1.267148791805761 samples/sec                   batch loss = 0.638837456703186 | accuracy = 0.7673076923076924\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[2] Batch[265] Speed: 1.2650846412693846 samples/sec                   batch loss = 0.35085564851760864 | accuracy = 0.7669811320754717\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[2] Batch[270] Speed: 1.2684251559408741 samples/sec                   batch loss = 0.868017852306366 | accuracy = 0.7666666666666667\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[2] Batch[275] Speed: 1.2658817752418383 samples/sec                   batch loss = 0.8266984820365906 | accuracy = 0.7654545454545455\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[2] Batch[280] Speed: 1.2733551828159906 samples/sec                   batch loss = 0.4120587408542633 | accuracy = 0.7669642857142858\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[2] Batch[285] Speed: 1.270725214455315 samples/sec                   batch loss = 1.014793872833252 | accuracy = 0.7675438596491229\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[2] Batch[290] Speed: 1.2671106065995847 samples/sec                   batch loss = 0.44852501153945923 | accuracy = 0.7681034482758621\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[2] Batch[295] Speed: 1.2704668460659576 samples/sec                   batch loss = 0.420880526304245 | accuracy = 0.7677966101694915\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[2] Batch[300] Speed: 1.2684345540198583 samples/sec                   batch loss = 0.654721200466156 | accuracy = 0.7641666666666667\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[2] Batch[305] Speed: 1.266592032538849 samples/sec                   batch loss = 0.5563826560974121 | accuracy = 0.7655737704918033\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[2] Batch[310] Speed: 1.2725128996044468 samples/sec                   batch loss = 0.6156508326530457 | accuracy = 0.7637096774193548\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[2] Batch[315] Speed: 1.272224378756879 samples/sec                   batch loss = 0.3573748767375946 | accuracy = 0.7658730158730159\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[2] Batch[320] Speed: 1.2721365940313851 samples/sec                   batch loss = 0.704727053642273 | accuracy = 0.7671875\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[2] Batch[325] Speed: 1.2688555965325603 samples/sec                   batch loss = 0.4216771423816681 | accuracy = 0.7676923076923077\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[2] Batch[330] Speed: 1.2693178274328 samples/sec                   batch loss = 0.451947420835495 | accuracy = 0.7681818181818182\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[2] Batch[335] Speed: 1.267518608719618 samples/sec                   batch loss = 0.42112496495246887 | accuracy = 0.7686567164179104\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[2] Batch[340] Speed: 1.2658169246529856 samples/sec                   batch loss = 0.45928695797920227 | accuracy = 0.7676470588235295\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[2] Batch[345] Speed: 1.2721476870367416 samples/sec                   batch loss = 0.5466926693916321 | accuracy = 0.7695652173913043\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[2] Batch[350] Speed: 1.2751424303672283 samples/sec                   batch loss = 0.14336776733398438 | accuracy = 0.7714285714285715\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[2] Batch[355] Speed: 1.267471208784202 samples/sec                   batch loss = 0.3525856137275696 | accuracy = 0.7704225352112676\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[2] Batch[360] Speed: 1.2690933417973767 samples/sec                   batch loss = 0.5668888688087463 | accuracy = 0.7708333333333334\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[2] Batch[365] Speed: 1.2674707300150612 samples/sec                   batch loss = 0.36127129197120667 | accuracy = 0.7719178082191781\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[2] Batch[370] Speed: 1.268827383993257 samples/sec                   batch loss = 0.44772055745124817 | accuracy = 0.7722972972972973\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[2] Batch[375] Speed: 1.2662100459722594 samples/sec                   batch loss = 0.47030264139175415 | accuracy = 0.7713333333333333\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[2] Batch[380] Speed: 1.2722916242625475 samples/sec                   batch loss = 0.27344655990600586 | accuracy = 0.7730263157894737\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[2] Batch[385] Speed: 1.2699047648026927 samples/sec                   batch loss = 0.2840173542499542 | accuracy = 0.7733766233766234\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[2] Batch[390] Speed: 1.2747976948623283 samples/sec                   batch loss = 0.48964521288871765 | accuracy = 0.7743589743589744\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[2] Batch[395] Speed: 1.2710722766166775 samples/sec                   batch loss = 0.5927525162696838 | accuracy = 0.7740506329113924\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[2] Batch[400] Speed: 1.2701309799558544 samples/sec                   batch loss = 0.40795236825942993 | accuracy = 0.773125\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[2] Batch[405] Speed: 1.2662110016070265 samples/sec                   batch loss = 0.3847126066684723 | accuracy = 0.7734567901234568\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[2] Batch[410] Speed: 1.2687582973584197 samples/sec                   batch loss = 0.05686186999082565 | accuracy = 0.775\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[2] Batch[415] Speed: 1.2684297590642002 samples/sec                   batch loss = 0.8264781832695007 | accuracy = 0.7746987951807229\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[2] Batch[420] Speed: 1.2649508181963287 samples/sec                   batch loss = 1.0252517461776733 | accuracy = 0.7732142857142857\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[2] Batch[425] Speed: 1.2683718388637373 samples/sec                   batch loss = 0.9566994309425354 | accuracy = 0.7717647058823529\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[2] Batch[430] Speed: 1.2688955184597075 samples/sec                   batch loss = 0.33574989438056946 | accuracy = 0.7726744186046511\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[2] Batch[435] Speed: 1.2638405024742767 samples/sec                   batch loss = 0.5357831716537476 | accuracy = 0.7701149425287356\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[2] Batch[440] Speed: 1.2689316998761413 samples/sec                   batch loss = 0.29635462164878845 | accuracy = 0.7710227272727272\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[2] Batch[445] Speed: 1.265879100859394 samples/sec                   batch loss = 0.25030258297920227 | accuracy = 0.7713483146067416\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[2] Batch[450] Speed: 1.2658895119118239 samples/sec                   batch loss = 0.33114463090896606 | accuracy = 0.77\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[2] Batch[455] Speed: 1.266133599864219 samples/sec                   batch loss = 0.41308751702308655 | accuracy = 0.7697802197802198\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[2] Batch[460] Speed: 1.2679493924131546 samples/sec                   batch loss = 0.3204061686992645 | accuracy = 0.7711956521739131\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[2] Batch[465] Speed: 1.2654435184020967 samples/sec                   batch loss = 0.6681140065193176 | accuracy = 0.7709677419354839\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[2] Batch[470] Speed: 1.2683076917029161 samples/sec                   batch loss = 0.32782962918281555 | accuracy = 0.7712765957446809\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[2] Batch[475] Speed: 1.2632513564511052 samples/sec                   batch loss = 0.6342236399650574 | accuracy = 0.7721052631578947\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[2] Batch[480] Speed: 1.2711998852547939 samples/sec                   batch loss = 0.23498670756816864 | accuracy = 0.7729166666666667\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[2] Batch[485] Speed: 1.266350348594733 samples/sec                   batch loss = 0.33923354744911194 | accuracy = 0.7716494845360825\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[2] Batch[490] Speed: 1.2670994098702277 samples/sec                   batch loss = 0.6169783473014832 | accuracy = 0.7704081632653061\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[2] Batch[495] Speed: 1.2624103186286535 samples/sec                   batch loss = 0.3935692608356476 | accuracy = 0.7717171717171717\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[2] Batch[500] Speed: 1.265530954570083 samples/sec                   batch loss = 0.22158144414424896 | accuracy = 0.772\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[2] Batch[505] Speed: 1.2690746222458194 samples/sec                   batch loss = 0.27750110626220703 | accuracy = 0.7722772277227723\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[2] Batch[510] Speed: 1.2684186349066855 samples/sec                   batch loss = 0.3431386649608612 | accuracy = 0.7725490196078432\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[2] Batch[515] Speed: 1.2664063636383536 samples/sec                   batch loss = 0.5514299273490906 | accuracy = 0.7733009708737864\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[2] Batch[520] Speed: 1.2738899505978216 samples/sec                   batch loss = 0.28555697202682495 | accuracy = 0.7740384615384616\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[2] Batch[525] Speed: 1.2643614943615418 samples/sec                   batch loss = 0.5617321729660034 | accuracy = 0.7738095238095238\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[2] Batch[530] Speed: 1.2669030686267202 samples/sec                   batch loss = 0.595504879951477 | accuracy = 0.7740566037735849\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[2] Batch[535] Speed: 1.2689652918975904 samples/sec                   batch loss = 0.671483039855957 | accuracy = 0.7738317757009345\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[2] Batch[540] Speed: 1.2708097242014063 samples/sec                   batch loss = 0.17383302748203278 | accuracy = 0.774074074074074\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[2] Batch[545] Speed: 1.2643524423912014 samples/sec                   batch loss = 0.5320215225219727 | accuracy = 0.7738532110091743\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[2] Batch[550] Speed: 1.2618272500484922 samples/sec                   batch loss = 1.0550318956375122 | accuracy = 0.7736363636363637\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[2] Batch[555] Speed: 1.26346845150029 samples/sec                   batch loss = 0.18514062464237213 | accuracy = 0.7747747747747747\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[2] Batch[560] Speed: 1.2623556063457515 samples/sec                   batch loss = 2.5367209911346436 | accuracy = 0.775\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[2] Batch[565] Speed: 1.2685481091640514 samples/sec                   batch loss = 0.2761897146701813 | accuracy = 0.7761061946902655\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[2] Batch[570] Speed: 1.2663014111791608 samples/sec                   batch loss = 0.3111046552658081 | accuracy = 0.7767543859649123\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[2] Batch[575] Speed: 1.2735179537379704 samples/sec                   batch loss = 0.4073621928691864 | accuracy = 0.7765217391304348\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[2] Batch[580] Speed: 1.273861126855634 samples/sec                   batch loss = 0.6206179261207581 | accuracy = 0.7754310344827586\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[2] Batch[585] Speed: 1.2631924815679196 samples/sec                   batch loss = 0.48506611585617065 | accuracy = 0.7756410256410257\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[2] Batch[590] Speed: 1.2598426332106674 samples/sec                   batch loss = 0.658402681350708 | accuracy = 0.7762711864406779\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[2] Batch[595] Speed: 1.2632882630533337 samples/sec                   batch loss = 0.19682744145393372 | accuracy = 0.7764705882352941\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[2] Batch[600] Speed: 1.2686770342392444 samples/sec                   batch loss = 0.1656409054994583 | accuracy = 0.7758333333333334\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[2] Batch[605] Speed: 1.2651506570901443 samples/sec                   batch loss = 0.713995099067688 | accuracy = 0.7760330578512397\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[2] Batch[610] Speed: 1.26925723345128 samples/sec                   batch loss = 0.5951725244522095 | accuracy = 0.7762295081967213\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[2] Batch[615] Speed: 1.2685644152036437 samples/sec                   batch loss = 0.696811854839325 | accuracy = 0.7764227642276422\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[2] Batch[620] Speed: 1.2648608874494123 samples/sec                   batch loss = 0.7674600481987 | accuracy = 0.7745967741935483\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[2] Batch[625] Speed: 1.2645833557888144 samples/sec                   batch loss = 0.28800585865974426 | accuracy = 0.774\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[2] Batch[630] Speed: 1.2628887781691442 samples/sec                   batch loss = 0.2308804988861084 | accuracy = 0.775\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[2] Batch[635] Speed: 1.2676663852101195 samples/sec                   batch loss = 0.4164401888847351 | accuracy = 0.7740157480314961\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[2] Batch[640] Speed: 1.2643104238893341 samples/sec                   batch loss = 0.6109464764595032 | accuracy = 0.774609375\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[2] Batch[645] Speed: 1.2693228211726706 samples/sec                   batch loss = 0.25409895181655884 | accuracy = 0.7748062015503876\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[2] Batch[650] Speed: 1.2663016023335818 samples/sec                   batch loss = 0.48241397738456726 | accuracy = 0.7742307692307693\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[2] Batch[655] Speed: 1.2708443783717904 samples/sec                   batch loss = 0.6689162254333496 | accuracy = 0.7713740458015267\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[2] Batch[660] Speed: 1.2626890829414308 samples/sec                   batch loss = 0.4472440481185913 | accuracy = 0.771969696969697\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[2] Batch[665] Speed: 1.2700302162922106 samples/sec                   batch loss = 0.27394452691078186 | accuracy = 0.7729323308270677\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[2] Batch[670] Speed: 1.27297963463671 samples/sec                   batch loss = 0.371197909116745 | accuracy = 0.7723880597014925\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[2] Batch[675] Speed: 1.2682980078671715 samples/sec                   batch loss = 0.5955603718757629 | accuracy = 0.7714814814814814\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[2] Batch[680] Speed: 1.263478061725949 samples/sec                   batch loss = 1.587622046470642 | accuracy = 0.7709558823529412\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[2] Batch[685] Speed: 1.2692849849688088 samples/sec                   batch loss = 0.9941589832305908 | accuracy = 0.7693430656934307\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[2] Batch[690] Speed: 1.2645051045341915 samples/sec                   batch loss = 0.10577966272830963 | accuracy = 0.7681159420289855\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[2] Batch[695] Speed: 1.2661786063928027 samples/sec                   batch loss = 0.7191821336746216 | accuracy = 0.7676258992805756\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[2] Batch[700] Speed: 1.2665697532210032 samples/sec                   batch loss = 0.6413692235946655 | accuracy = 0.7678571428571429\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[2] Batch[705] Speed: 1.2682728881113023 samples/sec                   batch loss = 0.5283220410346985 | accuracy = 0.7687943262411348\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[2] Batch[710] Speed: 1.2691752343276428 samples/sec                   batch loss = 0.4879496991634369 | accuracy = 0.7693661971830986\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[2] Batch[715] Speed: 1.2731947723873964 samples/sec                   batch loss = 0.3229662775993347 | accuracy = 0.7695804195804196\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[2] Batch[720] Speed: 1.2734630477312125 samples/sec                   batch loss = 1.2633661031723022 | accuracy = 0.7684027777777778\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[2] Batch[725] Speed: 1.2736015784956087 samples/sec                   batch loss = 0.7047713398933411 | accuracy = 0.7686206896551724\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[2] Batch[730] Speed: 1.2647476100746702 samples/sec                   batch loss = 0.4019237756729126 | accuracy = 0.7688356164383562\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[2] Batch[735] Speed: 1.2679527463365352 samples/sec                   batch loss = 0.3061882257461548 | accuracy = 0.7697278911564626\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[2] Batch[740] Speed: 1.2619609825372182 samples/sec                   batch loss = 0.23034590482711792 | accuracy = 0.7695945945945946\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[2] Batch[745] Speed: 1.2727598383857817 samples/sec                   batch loss = 0.735202968120575 | accuracy = 0.7697986577181208\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[2] Batch[750] Speed: 1.2696486515652794 samples/sec                   batch loss = 0.23050051927566528 | accuracy = 0.7696666666666667\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[2] Batch[755] Speed: 1.2685166492840463 samples/sec                   batch loss = 1.3658818006515503 | accuracy = 0.7685430463576159\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[2] Batch[760] Speed: 1.265403908831149 samples/sec                   batch loss = 0.3474471867084503 | accuracy = 0.7697368421052632\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[2] Batch[765] Speed: 1.2647665835737454 samples/sec                   batch loss = 0.24107645452022552 | accuracy = 0.7696078431372549\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[2] Batch[770] Speed: 1.2670440990165184 samples/sec                   batch loss = 0.6008711457252502 | accuracy = 0.7691558441558441\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[2] Batch[775] Speed: 1.269949559194579 samples/sec                   batch loss = 0.33554041385650635 | accuracy = 0.7690322580645161\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[2] Batch[780] Speed: 1.271180525616568 samples/sec                   batch loss = 0.21718209981918335 | accuracy = 0.7698717948717949\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch[2] Batch[785] Speed: 1.2687251000685815 samples/sec                   batch loss = 0.5990146398544312 | accuracy = 0.7697452229299363\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[Epoch 2] training: accuracy=0.7706218274111675\n",
      "[Epoch 2] time cost: 639.0972635746002\n",
      "[Epoch 2] validation: validation accuracy=0.7733333333333333\n"
     ]
    }
   ],
   "source": [
    "# Start the training loop\n",
    "epochs = 2\n",
    "accuracy = gluon.metric.Accuracy()\n",
    "log_interval = 5\n",
    "\n",
    "for epoch in range(epochs):\n",
    "    tic = time.time()\n",
    "    btic = time.time()\n",
    "    accuracy.reset()\n",
    "\n",
    "    for idx, batch in enumerate(train_loader):\n",
    "        data = batch[0]\n",
    "        label = batch[1]\n",
    "        with mx.autograd.record():\n",
    "            outputs = model(data.to_device(device))\n",
    "            loss = loss_fn(outputs, label.to_device(device))\n",
    "        mx.autograd.backward(loss)\n",
    "        trainer.step(batch_size)\n",
    "        accuracy.update([label], [outputs])\n",
    "        if log_interval and (idx + 1) % log_interval == 0:\n",
    "            _, acc = accuracy.get()\n",
    "\n",
    "            print(f\"\"\"Epoch[{epoch + 1}] Batch[{idx + 1}] Speed: {batch_size / (time.time() - btic)} samples/sec \\\n",
    "                  batch loss = {loss.mean().item()} | accuracy = {acc}\"\"\")\n",
    "            btic = time.time()\n",
    "\n",
    "    _, acc = accuracy.get()\n",
    "\n",
    "    acc_val = test(validation_loader)\n",
    "    print(f\"[Epoch {epoch + 1}] training: accuracy={acc}\")\n",
    "    print(f\"[Epoch {epoch + 1}] time cost: {time.time() - tic}\")\n",
    "    print(f\"[Epoch {epoch + 1}] validation: validation accuracy={acc_val}\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "41801c65",
   "metadata": {},
   "source": [
    "## 5. Test on the test set\n",
    "\n",
    "Now that your network is trained and has reached a decent accuracy, you can\n",
    "evaluate the performance on the test set. For that, you can use the `test_loader` data\n",
    "loader and the test function you created previously."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "id": "2f61d48c",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.7577777777777778"
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "test(test_loader)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "7149da64",
   "metadata": {},
   "source": [
    "You have a trained network that can confidently discriminate between plants that\n",
    "are healthy and the ones that are diseased. You can now start your garden and\n",
    "set cameras to automatically detect plants in distress! Or change your classification\n",
    "problem to create a model that classify the species of the plants! Either way you\n",
    "might be able to impress your botanist friends.\n",
    "\n",
    "## 6. Save the parameters\n",
    "\n",
    "If you want to preserve the trained weights of the network you can save the\n",
    "parameters in a file. Later, when you want to use the network to make predictions\n",
    "you can load the parameters back!"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "id": "340ca0ac",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Save parameters in the\n",
    "model.save_parameters('leaf_models.params')"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "4c06169e",
   "metadata": {},
   "source": [
    "This is the end of this tutorial, to see how you can speed up the training by\n",
    "using GPU hardware continue to the [next tutorial](./7-use-gpus.ipynb)"
   ]
  }
 ],
 "metadata": {
  "language_info": {
   "name": "python"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}