Changes
2 changed files (+784/-248)
-
-
@@ -1,283 +1,747 @@{ "cells": [ { "cell_type": "code", "execution_count": null, "metadata": { "collapsed": false }, "outputs": [], "source": [ "%matplotlib inline" ] }, "cells": [ { "cell_type": "code", "execution_count": null, "metadata": { "collapsed": false, "jupyter": { "outputs_hidden": false } }, "outputs": [], "source": [ "%matplotlib inline" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "\n", "`Learn the Basics <intro.html>`_ ||\n", "**Quickstart** ||\n", "`Tensors <tensorqs_tutorial.html>`_ ||\n", "`Datasets & DataLoaders <data_tutorial.html>`_ ||\n", "`Transforms <transforms_tutorial.html>`_ ||\n", "`Build Model <buildmodel_tutorial.html>`_ ||\n", "`Autograd <autogradqs_tutorial.html>`_ ||\n", "`Optimization <optimization_tutorial.html>`_ ||\n", "`Save & Load Model <saveloadrun_tutorial.html>`_\n", "\n", "Quickstart\n", "===================\n", "This section runs through the API for common tasks in machine learning. Refer to the links in each section to dive deeper.\n", "\n", "Working with data\n", "-----------------\n", "PyTorch has two `primitives to work with data <https://pytorch.org/docs/stable/data.html>`_:\n", "``torch.utils.data.DataLoader`` and ``torch.utils.data.Dataset``.\n", "``Dataset`` stores the samples and their corresponding labels, and ``DataLoader`` wraps an iterable around\n", "the ``Dataset``.\n", "\n", "\n" ] }, { "cell_type": "code", "execution_count": 3, "metadata": { "collapsed": false, "jupyter": { "outputs_hidden": false } }, "outputs": [], "source": [ "import torch\n", "from torch import nn\n", "from torch.utils.data import DataLoader\n", "from torchvision import datasets\n", "from torchvision.transforms import ToTensor, Lambda, Compose\n", "import matplotlib.pyplot as plt" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "PyTorch offers domain-specific libraries such as `TorchText <https://pytorch.org/text/stable/index.html>`_,\n", "`TorchVision <https://pytorch.org/vision/stable/index.html>`_, and `TorchAudio <https://pytorch.org/audio/stable/index.html>`_,\n", "all of which include datasets. For this tutorial, we will be using a TorchVision dataset.\n", "\n", "The ``torchvision.datasets`` module contains ``Dataset`` objects for many real-world vision data like\n", "CIFAR, COCO (`full list here <https://pytorch.org/vision/stable/datasets.html>`_). In this tutorial, we\n", "use the FashionMNIST dataset. Every TorchVision ``Dataset`` includes two arguments: ``transform`` and\n", "``target_transform`` to modify the samples and labels respectively.\n", "\n" ] }, { "cell_type": "code", "execution_count": 4, "metadata": { "collapsed": false, "jupyter": { "outputs_hidden": false } }, "outputs": [ { "cell_type": "markdown", "metadata": {}, "source": [ "\n`Learn the Basics <intro.html>`_ ||\n**Quickstart** ||\n`Tensors <tensorqs_tutorial.html>`_ ||\n`Datasets & DataLoaders <data_tutorial.html>`_ ||\n`Transforms <transforms_tutorial.html>`_ ||\n`Build Model <buildmodel_tutorial.html>`_ ||\n`Autograd <autogradqs_tutorial.html>`_ ||\n`Optimization <optimization_tutorial.html>`_ ||\n`Save & Load Model <saveloadrun_tutorial.html>`_\n\nQuickstart\n===================\nThis section runs through the API for common tasks in machine learning. Refer to the links in each section to dive deeper.\n\nWorking with data\n-----------------\nPyTorch has two `primitives to work with data <https://pytorch.org/docs/stable/data.html>`_:\n``torch.utils.data.DataLoader`` and ``torch.utils.data.Dataset``.\n``Dataset`` stores the samples and their corresponding labels, and ``DataLoader`` wraps an iterable around\nthe ``Dataset``.\n\n\n" ] "name": "stdout", "output_type": "stream", "text": [ "Downloading http://fashion-mnist.s3-website.eu-central-1.amazonaws.com/train-images-idx3-ubyte.gz\n", "Downloading http://fashion-mnist.s3-website.eu-central-1.amazonaws.com/train-images-idx3-ubyte.gz to data/FashionMNIST/raw/train-images-idx3-ubyte.gz\n" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "collapsed": false "data": { "application/vnd.jupyter.widget-view+json": { "model_id": "47918efb82854fc7a269ce73230391b0", "version_major": 2, "version_minor": 0 }, "outputs": [], "source": [ "import torch\nfrom torch import nn\nfrom torch.utils.data import DataLoader\nfrom torchvision import datasets\nfrom torchvision.transforms import ToTensor, Lambda, Compose\nimport matplotlib.pyplot as plt" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "PyTorch offers domain-specific libraries such as `TorchText <https://pytorch.org/text/stable/index.html>`_,\n`TorchVision <https://pytorch.org/vision/stable/index.html>`_, and `TorchAudio <https://pytorch.org/audio/stable/index.html>`_,\nall of which include datasets. For this tutorial, we will be using a TorchVision dataset.\n\nThe ``torchvision.datasets`` module contains ``Dataset`` objects for many real-world vision data like\nCIFAR, COCO (`full list here <https://pytorch.org/vision/stable/datasets.html>`_). In this tutorial, we\nuse the FashionMNIST dataset. Every TorchVision ``Dataset`` includes two arguments: ``transform`` and\n``target_transform`` to modify the samples and labels respectively.\n\n" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "collapsed": false }, "outputs": [], "source": [ "# Download training data from open datasets.\ntraining_data = datasets.FashionMNIST(\n root=\"data\",\n train=True,\n download=True,\n transform=ToTensor(),\n)\n\n# Download test data from open datasets.\ntest_data = datasets.FashionMNIST(\n root=\"data\",\n train=False,\n download=True,\n transform=ToTensor(),\n)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "We pass the ``Dataset`` as an argument to ``DataLoader``. This wraps an iterable over our dataset, and supports\nautomatic batching, sampling, shuffling and multiprocess data loading. Here we define a batch size of 64, i.e. each element\nin the dataloader iterable will return a batch of 64 features and labels.\n\n" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "collapsed": false }, "outputs": [], "source": [ "batch_size = 64\n\n# Create data loaders.\ntrain_dataloader = DataLoader(training_data, batch_size=batch_size)\ntest_dataloader = DataLoader(test_data, batch_size=batch_size)\n\nfor X, y in test_dataloader:\n print(\"Shape of X [N, C, H, W]: \", X.shape)\n print(\"Shape of y: \", y.shape, y.dtype)\n break" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Read more about `loading data in PyTorch <data_tutorial.html>`_.\n\n\n" "text/plain": [ " 0%| | 0/26421880 [00:00<?, ?it/s]" ] }, "metadata": {}, "output_type": "display_data" }, { "cell_type": "markdown", "metadata": {}, "source": [ "--------------\n\n\n" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Creating Models\n------------------\nTo define a neural network in PyTorch, we create a class that inherits\nfrom `nn.Module <https://pytorch.org/docs/stable/generated/torch.nn.Module.html>`_. We define the layers of the network\nin the ``__init__`` function and specify how data will pass through the network in the ``forward`` function. To accelerate\noperations in the neural network, we move it to the GPU if available.\n\n" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "collapsed": false }, "outputs": [], "source": [ "# Get cpu or gpu device for training.\ndevice = \"cuda\" if torch.cuda.is_available() else \"cpu\"\nprint(\"Using {} device\".format(device))\n\n# Define model\nclass NeuralNetwork(nn.Module):\n def __init__(self):\n super(NeuralNetwork, self).__init__()\n self.flatten = nn.Flatten()\n self.linear_relu_stack = nn.Sequential(\n nn.Linear(28*28, 512),\n nn.ReLU(),\n nn.Linear(512, 512),\n nn.ReLU(),\n nn.Linear(512, 10),\n nn.ReLU()\n )\n\n def forward(self, x):\n x = self.flatten(x)\n logits = self.linear_relu_stack(x)\n return logits\n\nmodel = NeuralNetwork().to(device)\nprint(model)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Read more about `building neural networks in PyTorch <buildmodel_tutorial.html>`_.\n\n\n" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "--------------\n\n\n" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Optimizing the Model Parameters\n----------------------------------------\nTo train a model, we need a `loss function <https://pytorch.org/docs/stable/nn.html#loss-functions>`_\nand an `optimizer <https://pytorch.org/docs/stable/optim.html>`_.\n\n" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "collapsed": false }, "outputs": [], "source": [ "loss_fn = nn.CrossEntropyLoss()\noptimizer = torch.optim.SGD(model.parameters(), lr=1e-3)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "In a single training loop, the model makes predictions on the training dataset (fed to it in batches), and\nbackpropagates the prediction error to adjust the model's parameters.\n\n" ] "name": "stdout", "output_type": "stream", "text": [ "Extracting data/FashionMNIST/raw/train-images-idx3-ubyte.gz to data/FashionMNIST/raw\n", "\n", "Downloading http://fashion-mnist.s3-website.eu-central-1.amazonaws.com/train-labels-idx1-ubyte.gz\n", "Downloading http://fashion-mnist.s3-website.eu-central-1.amazonaws.com/train-labels-idx1-ubyte.gz to data/FashionMNIST/raw/train-labels-idx1-ubyte.gz\n" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "collapsed": false "data": { "application/vnd.jupyter.widget-view+json": { "model_id": "9abecd52d9144d53bd028f14a2cfd60b", "version_major": 2, "version_minor": 0 }, "outputs": [], "source": [ "def train(dataloader, model, loss_fn, optimizer):\n size = len(dataloader.dataset)\n for batch, (X, y) in enumerate(dataloader):\n X, y = X.to(device), y.to(device)\n\n # Compute prediction error\n pred = model(X)\n loss = loss_fn(pred, y)\n\n # Backpropagation\n optimizer.zero_grad()\n loss.backward()\n optimizer.step()\n\n if batch % 100 == 0:\n loss, current = loss.item(), batch * len(X)\n print(f\"loss: {loss:>7f} [{current:>5d}/{size:>5d}]\")" "text/plain": [ " 0%| | 0/29515 [00:00<?, ?it/s]" ] }, "metadata": {}, "output_type": "display_data" }, { "cell_type": "markdown", "metadata": {}, "source": [ "We also check the model's performance against the test dataset to ensure it is learning.\n\n" ] "name": "stdout", "output_type": "stream", "text": [ "Extracting data/FashionMNIST/raw/train-labels-idx1-ubyte.gz to data/FashionMNIST/raw\n", "\n", "Downloading http://fashion-mnist.s3-website.eu-central-1.amazonaws.com/t10k-images-idx3-ubyte.gz\n", "Downloading http://fashion-mnist.s3-website.eu-central-1.amazonaws.com/t10k-images-idx3-ubyte.gz to data/FashionMNIST/raw/t10k-images-idx3-ubyte.gz\n" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "collapsed": false "data": { "application/vnd.jupyter.widget-view+json": { "model_id": "df61f428b0c44a818d2ab0f64420d9b3", "version_major": 2, "version_minor": 0 }, "outputs": [], "source": [ "def test(dataloader, model, loss_fn):\n size = len(dataloader.dataset)\n num_batches = len(dataloader)\n model.eval()\n test_loss, correct = 0, 0\n with torch.no_grad():\n for X, y in dataloader:\n X, y = X.to(device), y.to(device)\n pred = model(X)\n test_loss += loss_fn(pred, y).item()\n correct += (pred.argmax(1) == y).type(torch.float).sum().item()\n test_loss /= num_batches\n correct /= size\n print(f\"Test Error: \\n Accuracy: {(100*correct):>0.1f}%, Avg loss: {test_loss:>8f} \\n\")" "text/plain": [ " 0%| | 0/4422102 [00:00<?, ?it/s]" ] }, "metadata": {}, "output_type": "display_data" }, { "cell_type": "markdown", "metadata": {}, "source": [ "The training process is conducted over several iterations (*epochs*). During each epoch, the model learns\nparameters to make better predictions. We print the model's accuracy and loss at each epoch; we'd like to see the\naccuracy increase and the loss decrease with every epoch.\n\n" ] "name": "stdout", "output_type": "stream", "text": [ "Extracting data/FashionMNIST/raw/t10k-images-idx3-ubyte.gz to data/FashionMNIST/raw\n", "\n", "Downloading http://fashion-mnist.s3-website.eu-central-1.amazonaws.com/t10k-labels-idx1-ubyte.gz\n", "Downloading http://fashion-mnist.s3-website.eu-central-1.amazonaws.com/t10k-labels-idx1-ubyte.gz to data/FashionMNIST/raw/t10k-labels-idx1-ubyte.gz\n" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "collapsed": false "data": { "application/vnd.jupyter.widget-view+json": { "model_id": "418ca86b3df24c84979a54ca66cebe56", "version_major": 2, "version_minor": 0 }, "outputs": [], "source": [ "epochs = 5\nfor t in range(epochs):\n print(f\"Epoch {t+1}\\n-------------------------------\")\n train(train_dataloader, model, loss_fn, optimizer)\n test(test_dataloader, model, loss_fn)\nprint(\"Done!\")" "text/plain": [ " 0%| | 0/5148 [00:00<?, ?it/s]" ] }, "metadata": {}, "output_type": "display_data" }, { "cell_type": "markdown", "metadata": {}, "source": [ "Read more about `Training your model <optimization_tutorial.html>`_.\n\n\n" ] "name": "stdout", "output_type": "stream", "text": [ "Extracting data/FashionMNIST/raw/t10k-labels-idx1-ubyte.gz to data/FashionMNIST/raw\n", "\n" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "--------------\n\n\n" ] }, "name": "stderr", "output_type": "stream", "text": [ "/home/ta180m/.local/lib/python3.9/site-packages/torchvision/datasets/mnist.py:498: UserWarning: The given NumPy array is not writeable, and PyTorch does not support non-writeable tensors. This means you can write to the underlying (supposedly non-writeable) NumPy array using the tensor. You may want to copy the array to protect its data or make it writeable before converting it to a tensor. This type of warning will be suppressed for the rest of this program. (Triggered internally at /build/python-pytorch/src/pytorch-1.9.0-opt/torch/csrc/utils/tensor_numpy.cpp:174.)\n", " return torch.from_numpy(parsed.astype(m[2], copy=False)).view(*s)\n" ] } ], "source": [ "# Download training data from open datasets.\n", "training_data = datasets.FashionMNIST(\n", " root=\"data\",\n", " train=True,\n", " download=True,\n", " transform=ToTensor(),\n", ")\n", "\n", "# Download test data from open datasets.\n", "test_data = datasets.FashionMNIST(\n", " root=\"data\",\n", " train=False,\n", " download=True,\n", " transform=ToTensor(),\n", ")" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "We pass the ``Dataset`` as an argument to ``DataLoader``. This wraps an iterable over our dataset, and supports\n", "automatic batching, sampling, shuffling and multiprocess data loading. Here we define a batch size of 64, i.e. each element\n", "in the dataloader iterable will return a batch of 64 features and labels.\n", "\n" ] }, { "cell_type": "code", "execution_count": 5, "metadata": { "collapsed": false, "jupyter": { "outputs_hidden": false } }, "outputs": [ { "cell_type": "markdown", "metadata": {}, "source": [ "Saving Models\n-------------\nA common way to save a model is to serialize the internal state dictionary (containing the model parameters).\n\n" ] }, "name": "stdout", "output_type": "stream", "text": [ "Shape of X [N, C, H, W]: torch.Size([64, 1, 28, 28])\n", "Shape of y: torch.Size([64]) torch.int64\n" ] } ], "source": [ "batch_size = 64\n", "\n", "# Create data loaders.\n", "train_dataloader = DataLoader(training_data, batch_size=batch_size)\n", "test_dataloader = DataLoader(test_data, batch_size=batch_size)\n", "\n", "for X, y in test_dataloader:\n", " print(\"Shape of X [N, C, H, W]: \", X.shape)\n", " print(\"Shape of y: \", y.shape, y.dtype)\n", " break" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Read more about `loading data in PyTorch <data_tutorial.html>`_.\n", "\n", "\n" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "--------------\n", "\n", "\n" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Creating Models\n", "------------------\n", "To define a neural network in PyTorch, we create a class that inherits\n", "from `nn.Module <https://pytorch.org/docs/stable/generated/torch.nn.Module.html>`_. We define the layers of the network\n", "in the ``__init__`` function and specify how data will pass through the network in the ``forward`` function. To accelerate\n", "operations in the neural network, we move it to the GPU if available.\n", "\n" ] }, { "cell_type": "code", "execution_count": 6, "metadata": { "collapsed": false, "jupyter": { "outputs_hidden": false } }, "outputs": [ { "cell_type": "code", "execution_count": null, "metadata": { "collapsed": false }, "outputs": [], "source": [ "torch.save(model.state_dict(), \"model.pth\")\nprint(\"Saved PyTorch Model State to model.pth\")" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Loading Models\n----------------------------\n\nThe process for loading a model includes re-creating the model structure and loading\nthe state dictionary into it.\n\n" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "collapsed": false }, "outputs": [], "source": [ "model = NeuralNetwork()\nmodel.load_state_dict(torch.load(\"model.pth\"))" ] }, "name": "stdout", "output_type": "stream", "text": [ "Using cpu device\n", "NeuralNetwork(\n", " (flatten): Flatten(start_dim=1, end_dim=-1)\n", " (linear_relu_stack): Sequential(\n", " (0): Linear(in_features=784, out_features=512, bias=True)\n", " (1): ReLU()\n", " (2): Linear(in_features=512, out_features=512, bias=True)\n", " (3): ReLU()\n", " (4): Linear(in_features=512, out_features=10, bias=True)\n", " (5): ReLU()\n", " )\n", ")\n" ] } ], "source": [ "# Get cpu or gpu device for training.\n", "device = \"cuda\" if torch.cuda.is_available() else \"cpu\"\n", "print(\"Using {} device\".format(device))\n", "\n", "# Define model\n", "class NeuralNetwork(nn.Module):\n", " def __init__(self):\n", " super(NeuralNetwork, self).__init__()\n", " self.flatten = nn.Flatten()\n", " self.linear_relu_stack = nn.Sequential(\n", " nn.Linear(28*28, 512),\n", " nn.ReLU(),\n", " nn.Linear(512, 512),\n", " nn.ReLU(),\n", " nn.Linear(512, 10),\n", " nn.ReLU()\n", " )\n", "\n", " def forward(self, x):\n", " x = self.flatten(x)\n", " logits = self.linear_relu_stack(x)\n", " return logits\n", "\n", "model = NeuralNetwork().to(device)\n", "print(model)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Read more about `building neural networks in PyTorch <buildmodel_tutorial.html>`_.\n", "\n", "\n" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "--------------\n", "\n", "\n" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Optimizing the Model Parameters\n", "----------------------------------------\n", "To train a model, we need a `loss function <https://pytorch.org/docs/stable/nn.html#loss-functions>`_\n", "and an `optimizer <https://pytorch.org/docs/stable/optim.html>`_.\n", "\n" ] }, { "cell_type": "code", "execution_count": 7, "metadata": { "collapsed": false, "jupyter": { "outputs_hidden": false } }, "outputs": [], "source": [ "loss_fn = nn.CrossEntropyLoss()\n", "optimizer = torch.optim.SGD(model.parameters(), lr=1e-3)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "In a single training loop, the model makes predictions on the training dataset (fed to it in batches), and\n", "backpropagates the prediction error to adjust the model's parameters.\n", "\n" ] }, { "cell_type": "code", "execution_count": 8, "metadata": { "collapsed": false, "jupyter": { "outputs_hidden": false } }, "outputs": [], "source": [ "def train(dataloader, model, loss_fn, optimizer):\n", " size = len(dataloader.dataset)\n", " for batch, (X, y) in enumerate(dataloader):\n", " X, y = X.to(device), y.to(device)\n", "\n", " # Compute prediction error\n", " pred = model(X)\n", " loss = loss_fn(pred, y)\n", "\n", " # Backpropagation\n", " optimizer.zero_grad()\n", " loss.backward()\n", " optimizer.step()\n", "\n", " if batch % 100 == 0:\n", " loss, current = loss.item(), batch * len(X)\n", " print(f\"loss: {loss:>7f} [{current:>5d}/{size:>5d}]\")" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "We also check the model's performance against the test dataset to ensure it is learning.\n", "\n" ] }, { "cell_type": "code", "execution_count": 9, "metadata": { "collapsed": false, "jupyter": { "outputs_hidden": false } }, "outputs": [], "source": [ "def test(dataloader, model, loss_fn):\n", " size = len(dataloader.dataset)\n", " num_batches = len(dataloader)\n", " model.eval()\n", " test_loss, correct = 0, 0\n", " with torch.no_grad():\n", " for X, y in dataloader:\n", " X, y = X.to(device), y.to(device)\n", " pred = model(X)\n", " test_loss += loss_fn(pred, y).item()\n", " correct += (pred.argmax(1) == y).type(torch.float).sum().item()\n", " test_loss /= num_batches\n", " correct /= size\n", " print(f\"Test Error: \\n Accuracy: {(100*correct):>0.1f}%, Avg loss: {test_loss:>8f} \\n\")" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "The training process is conducted over several iterations (*epochs*). During each epoch, the model learns\n", "parameters to make better predictions. We print the model's accuracy and loss at each epoch; we'd like to see the\n", "accuracy increase and the loss decrease with every epoch.\n", "\n" ] }, { "cell_type": "code", "execution_count": 11, "metadata": { "collapsed": false, "jupyter": { "outputs_hidden": false } }, "outputs": [ { "cell_type": "markdown", "metadata": {}, "source": [ "This model can now be used to make predictions.\n\n" ] }, "name": "stdout", "output_type": "stream", "text": [ "Epoch 1\n", "-------------------------------\n", "loss: 1.758146 [ 0/60000]\n", "loss: 1.820034 [ 6400/60000]\n", "loss: 1.846449 [12800/60000]\n", "loss: 1.975245 [19200/60000]\n", "loss: 1.612495 [25600/60000]\n", "loss: 1.748993 [32000/60000]\n", "loss: 1.628008 [38400/60000]\n", "loss: 1.655061 [44800/60000]\n", "loss: 1.770255 [51200/60000]\n", "loss: 1.654287 [57600/60000]\n", "Test Error: \n", " Accuracy: 37.7%, Avg loss: 1.749445 \n", "\n", "Epoch 2\n", "-------------------------------\n", "loss: 1.670408 [ 0/60000]\n", "loss: 1.743051 [ 6400/60000]\n", "loss: 1.773547 [12800/60000]\n", "loss: 1.924395 [19200/60000]\n", "loss: 1.529726 [25600/60000]\n", "loss: 1.692361 [32000/60000]\n", "loss: 1.559834 [38400/60000]\n", "loss: 1.593531 [44800/60000]\n", "loss: 1.712157 [51200/60000]\n", "loss: 1.605115 [57600/60000]\n", "Test Error: \n", " Accuracy: 38.1%, Avg loss: 1.694516 \n", "\n", "Epoch 3\n", "-------------------------------\n", "loss: 1.607648 [ 0/60000]\n", "loss: 1.684907 [ 6400/60000]\n", "loss: 1.716139 [12800/60000]\n", "loss: 1.888849 [19200/60000]\n", "loss: 1.474264 [25600/60000]\n", "loss: 1.652733 [32000/60000]\n", "loss: 1.514825 [38400/60000]\n", "loss: 1.549373 [44800/60000]\n", "loss: 1.670293 [51200/60000]\n", "loss: 1.571395 [57600/60000]\n", "Test Error: \n", " Accuracy: 39.0%, Avg loss: 1.653676 \n", "\n", "Epoch 4\n", "-------------------------------\n", "loss: 1.561757 [ 0/60000]\n", "loss: 1.640771 [ 6400/60000]\n", "loss: 1.669458 [12800/60000]\n", "loss: 1.862879 [19200/60000]\n", "loss: 1.435348 [25600/60000]\n", "loss: 1.623189 [32000/60000]\n", "loss: 1.482370 [38400/60000]\n", "loss: 1.515045 [44800/60000]\n", "loss: 1.638349 [51200/60000]\n", "loss: 1.545919 [57600/60000]\n", "Test Error: \n", " Accuracy: 39.9%, Avg loss: 1.621615 \n", "\n", "Epoch 5\n", "-------------------------------\n", "loss: 1.525517 [ 0/60000]\n", "loss: 1.604991 [ 6400/60000]\n", "loss: 1.630397 [12800/60000]\n", "loss: 1.841878 [19200/60000]\n", "loss: 1.406707 [25600/60000]\n", "loss: 1.599460 [32000/60000]\n", "loss: 1.456716 [38400/60000]\n", "loss: 1.485950 [44800/60000]\n", "loss: 1.612476 [51200/60000]\n", "loss: 1.525381 [57600/60000]\n", "Test Error: \n", " Accuracy: 40.7%, Avg loss: 1.595456 \n", "\n", "Done!\n" ] } ], "source": [ "epochs = 5\n", "for t in range(epochs):\n", " print(f\"Epoch {t+1}\\n-------------------------------\")\n", " train(train_dataloader, model, loss_fn, optimizer)\n", " test(test_dataloader, model, loss_fn)\n", "print(\"Done!\")" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Read more about `Training your model <optimization_tutorial.html>`_.\n", "\n", "\n" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "--------------\n", "\n", "\n" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Saving Models\n", "-------------\n", "A common way to save a model is to serialize the internal state dictionary (containing the model parameters).\n", "\n" ] }, { "cell_type": "code", "execution_count": 12, "metadata": { "collapsed": false, "jupyter": { "outputs_hidden": false } }, "outputs": [ { "cell_type": "code", "execution_count": null, "metadata": { "collapsed": false }, "outputs": [], "source": [ "classes = [\n \"T-shirt/top\",\n \"Trouser\",\n \"Pullover\",\n \"Dress\",\n \"Coat\",\n \"Sandal\",\n \"Shirt\",\n \"Sneaker\",\n \"Bag\",\n \"Ankle boot\",\n]\n\nmodel.eval()\nx, y = test_data[0][0], test_data[0][1]\nwith torch.no_grad():\n pred = model(x)\n predicted, actual = classes[pred[0].argmax(0)], classes[y]\n print(f'Predicted: \"{predicted}\", Actual: \"{actual}\"')" ] }, "name": "stdout", "output_type": "stream", "text": [ "Saved PyTorch Model State to model.pth\n" ] } ], "source": [ "torch.save(model.state_dict(), \"model.pth\")\n", "print(\"Saved PyTorch Model State to model.pth\")" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Loading Models\n", "----------------------------\n", "\n", "The process for loading a model includes re-creating the model structure and loading\n", "the state dictionary into it.\n", "\n" ] }, { "cell_type": "code", "execution_count": 13, "metadata": { "collapsed": false, "jupyter": { "outputs_hidden": false } }, "outputs": [ { "cell_type": "markdown", "metadata": {}, "source": [ "Read more about `Saving & Loading your model <saveloadrun_tutorial.html>`_.\n\n\n" "data": { "text/plain": [ "<All keys matched successfully>" ] }, "execution_count": 13, "metadata": {}, "output_type": "execute_result" } ], "metadata": { "kernelspec": { "display_name": "Python 3", "language": "python", "name": "python3" }, "language_info": { "codemirror_mode": { "name": "ipython", "version": 3 }, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", "version": "3.6.13" ], "source": [ "model = NeuralNetwork()\n", "model.load_state_dict(torch.load(\"model.pth\"))" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "This model can now be used to make predictions.\n", "\n" ] }, { "cell_type": "code", "execution_count": 17, "metadata": { "collapsed": false, "jupyter": { "outputs_hidden": false } }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Predicted: \"Ankle boot\", Actual: \"Ankle boot\"\n" ] } ], "source": [ "classes = [\n", " \"T-shirt/top\",\n", " \"Trouser\",\n", " \"Pullover\",\n", " \"Dress\",\n", " \"Coat\",\n", " \"Sandal\",\n", " \"Shirt\",\n", " \"Sneaker\",\n", " \"Bag\",\n", " \"Ankle boot\",\n", "]\n", "\n", "model.eval()\n", "x, y = test_data[0][0], test_data[0][1]\n", "with torch.no_grad():\n", " pred = model(x)\n", " predicted, actual = classes[pred[0].argmax(0)], classes[y]\n", " print(f'Predicted: \"{predicted}\", Actual: \"{actual}\"')" ] }, "nbformat": 4, "nbformat_minor": 0 } { "cell_type": "markdown", "metadata": {}, "source": [ "Read more about `Saving & Loading your model <saveloadrun_tutorial.html>`_.\n", "\n", "\n" ] } ], "metadata": { "kernelspec": { "display_name": "Python 3 (ipykernel)", "language": "python", "name": "python3" }, "language_info": { "codemirror_mode": { "name": "ipython", "version": 3 }, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", "version": "3.9.6" } }, "nbformat": 4, "nbformat_minor": 4 }
-
-
-
@@ -1,6 +1,78 @@{ "cells": [], "metadata": {}, "cells": [ { "cell_type": "code", "execution_count": 1, "id": "5a2a1e37-f4db-4963-a0ac-7b39353f826f", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "tensor([[0.2226, 0.2227, 0.1347],\n", " [0.7975, 0.3823, 0.9395],\n", " [0.1675, 0.9185, 0.4175],\n", " [0.0476, 0.1244, 0.6878],\n", " [0.5177, 0.7245, 0.2723]])\n" ] } ], "source": [ "import torch\n", "x = torch.rand(5, 3)\n", "print(x)" ] }, { "cell_type": "code", "execution_count": 2, "id": "53469c52-9438-4d62-aa2a-e93fb3fef23b", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "False" ] }, "execution_count": 2, "metadata": {}, "output_type": "execute_result" } ], "source": [ "torch.cuda.is_available()" ] }, { "cell_type": "code", "execution_count": null, "id": "f13c7010-acb0-4870-aa6f-1294701cfc7e", "metadata": {}, "outputs": [], "source": [] } ], "metadata": { "kernelspec": { "display_name": "Python 3 (ipykernel)", "language": "python", "name": "python3" }, "language_info": { "codemirror_mode": { "name": "ipython", "version": 3 }, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", "version": "3.9.6" } }, "nbformat": 4, "nbformat_minor": 5 }
-