diff options
Diffstat (limited to 'quickstart_tutorial.ipynb')
-rw-r--r-- | quickstart_tutorial.ipynb | 747 |
1 files changed, 747 insertions, 0 deletions
diff --git a/quickstart_tutorial.ipynb b/quickstart_tutorial.ipynb new file mode 100644 index 0000000..3ea080e --- /dev/null +++ b/quickstart_tutorial.ipynb @@ -0,0 +1,747 @@ +{ + "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": [ + { + "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" + ] + }, + { + "data": { + "application/vnd.jupyter.widget-view+json": { + "model_id": "47918efb82854fc7a269ce73230391b0", + "version_major": 2, + "version_minor": 0 + }, + "text/plain": [ + " 0%| | 0/26421880 [00:00<?, ?it/s]" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "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" + ] + }, + { + "data": { + "application/vnd.jupyter.widget-view+json": { + "model_id": "9abecd52d9144d53bd028f14a2cfd60b", + "version_major": 2, + "version_minor": 0 + }, + "text/plain": [ + " 0%| | 0/29515 [00:00<?, ?it/s]" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "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" + ] + }, + { + "data": { + "application/vnd.jupyter.widget-view+json": { + "model_id": "df61f428b0c44a818d2ab0f64420d9b3", + "version_major": 2, + "version_minor": 0 + }, + "text/plain": [ + " 0%| | 0/4422102 [00:00<?, ?it/s]" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "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" + ] + }, + { + "data": { + "application/vnd.jupyter.widget-view+json": { + "model_id": "418ca86b3df24c84979a54ca66cebe56", + "version_major": 2, + "version_minor": 0 + }, + "text/plain": [ + " 0%| | 0/5148 [00:00<?, ?it/s]" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Extracting data/FashionMNIST/raw/t10k-labels-idx1-ubyte.gz to data/FashionMNIST/raw\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": [ + { + "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": [ + { + "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": [ + { + "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": [ + { + "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": [ + { + "data": { + "text/plain": [ + "<All keys matched successfully>" + ] + }, + "execution_count": 13, + "metadata": {}, + "output_type": "execute_result" + } + ], + "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}\"')" + ] + }, + { + "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 +} |