.. DO NOT EDIT. .. THIS FILE WAS AUTOMATICALLY GENERATED BY SPHINX-GALLERY. .. TO MAKE CHANGES, EDIT THE SOURCE PYTHON FILE: .. "beginner/blitz/cifar10_tutorial.py" .. LINE NUMBERS ARE GIVEN BELOW. .. only:: html .. note:: :class: sphx-glr-download-link-note Click :ref:`here ` to download the full example code .. rst-class:: sphx-glr-example-title .. _sphx_glr_beginner_blitz_cifar10_tutorial.py: Training a Classifier ===================== This is it. You have seen how to define neural networks, compute loss and make updates to the weights of the network. Now you might be thinking, What about data? ---------------- Generally, when you have to deal with image, text, audio or video data, you can use standard python packages that load data into a numpy array. Then you can convert this array into a ``torch.*Tensor``. - For images, packages such as Pillow, OpenCV are useful - For audio, packages such as scipy and librosa - For text, either raw Python or Cython based loading, or NLTK and SpaCy are useful Specifically for vision, we have created a package called ``torchvision``, that has data loaders for common datasets such as ImageNet, CIFAR10, MNIST, etc. and data transformers for images, viz., ``torchvision.datasets`` and ``torch.utils.data.DataLoader``. This provides a huge convenience and avoids writing boilerplate code. For this tutorial, we will use the CIFAR10 dataset. It has the classes: ‘airplane’, ‘automobile’, ‘bird’, ‘cat’, ‘deer’, ‘dog’, ‘frog’, ‘horse’, ‘ship’, ‘truck’. The images in CIFAR-10 are of size 3x32x32, i.e. 3-channel color images of 32x32 pixels in size. .. figure:: /_static/img/cifar10.png :alt: cifar10 cifar10 Training an image classifier ---------------------------- We will do the following steps in order: 1. Load and normalize the CIFAR10 training and test datasets using ``torchvision`` 2. Define a Convolutional Neural Network 3. Define a loss function 4. Train the network on the training data 5. Test the network on the test data 1. Load and normalize CIFAR10 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ Using ``torchvision``, it’s extremely easy to load CIFAR10. .. GENERATED FROM PYTHON SOURCE LINES 58-62 .. code-block:: default import torch import torchvision import torchvision.transforms as transforms .. GENERATED FROM PYTHON SOURCE LINES 63-65 The output of torchvision datasets are PILImage images of range [0, 1]. We transform them to Tensors of normalized range [-1, 1]. .. GENERATED FROM PYTHON SOURCE LINES 67-70 .. note:: If running on Windows and you get a BrokenPipeError, try setting the num_worker of torch.utils.data.DataLoader() to 0. .. GENERATED FROM PYTHON SOURCE LINES 70-90 .. code-block:: default transform = transforms.Compose( [transforms.ToTensor(), transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))]) batch_size = 4 trainset = torchvision.datasets.CIFAR10(root='./data', train=True, download=True, transform=transform) trainloader = torch.utils.data.DataLoader(trainset, batch_size=batch_size, shuffle=True, num_workers=2) testset = torchvision.datasets.CIFAR10(root='./data', train=False, download=True, transform=transform) testloader = torch.utils.data.DataLoader(testset, batch_size=batch_size, shuffle=False, num_workers=2) classes = ('plane', 'car', 'bird', 'cat', 'deer', 'dog', 'frog', 'horse', 'ship', 'truck') .. rst-class:: sphx-glr-script-out .. code-block:: none Downloading https://www.cs.toronto.edu/~kriz/cifar-10-python.tar.gz to ./data/cifar-10-python.tar.gz 0%| | 0/170498071 [00:00`_ for more details on saving PyTorch models. 5. Test the network on the test data ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ We have trained the network for 2 passes over the training dataset. But we need to check if the network has learnt anything at all. We will check this by predicting the class label that the neural network outputs, and checking it against the ground-truth. If the prediction is correct, we add the sample to the list of correct predictions. Okay, first step. Let us display an image from the test set to get familiar. .. GENERATED FROM PYTHON SOURCE LINES 211-219 .. code-block:: default dataiter = iter(testloader) images, labels = next(dataiter) # print images imshow(torchvision.utils.make_grid(images)) print('GroundTruth: ', ' '.join(f'{classes[labels[j]]:5s}' for j in range(4))) .. image-sg:: /beginner/blitz/images/sphx_glr_cifar10_tutorial_002.png :alt: cifar10 tutorial :srcset: /beginner/blitz/images/sphx_glr_cifar10_tutorial_002.png :class: sphx-glr-single-img .. rst-class:: sphx-glr-script-out .. code-block:: none GroundTruth: cat ship ship plane .. GENERATED FROM PYTHON SOURCE LINES 220-222 Next, let's load back in our saved model (note: saving and re-loading the model wasn't necessary here, we only did it to illustrate how to do so): .. GENERATED FROM PYTHON SOURCE LINES 222-226 .. code-block:: default net = Net() net.load_state_dict(torch.load(PATH)) .. rst-class:: sphx-glr-script-out .. code-block:: none .. GENERATED FROM PYTHON SOURCE LINES 227-228 Okay, now let us see what the neural network thinks these examples above are: .. GENERATED FROM PYTHON SOURCE LINES 228-231 .. code-block:: default outputs = net(images) .. GENERATED FROM PYTHON SOURCE LINES 232-236 The outputs are energies for the 10 classes. The higher the energy for a class, the more the network thinks that the image is of the particular class. So, let's get the index of the highest energy: .. GENERATED FROM PYTHON SOURCE LINES 236-241 .. code-block:: default _, predicted = torch.max(outputs, 1) print('Predicted: ', ' '.join(f'{classes[predicted[j]]:5s}' for j in range(4))) .. rst-class:: sphx-glr-script-out .. code-block:: none Predicted: cat ship truck ship .. GENERATED FROM PYTHON SOURCE LINES 242-245 The results seem pretty good. Let us look at how the network performs on the whole dataset. .. GENERATED FROM PYTHON SOURCE LINES 245-261 .. code-block:: default correct = 0 total = 0 # since we're not training, we don't need to calculate the gradients for our outputs with torch.no_grad(): for data in testloader: images, labels = data # calculate outputs by running images through the network outputs = net(images) # the class with the highest energy is what we choose as prediction _, predicted = torch.max(outputs.data, 1) total += labels.size(0) correct += (predicted == labels).sum().item() print(f'Accuracy of the network on the 10000 test images: {100 * correct // total} %') .. rst-class:: sphx-glr-script-out .. code-block:: none Accuracy of the network on the 10000 test images: 54 % .. GENERATED FROM PYTHON SOURCE LINES 262-268 That looks way better than chance, which is 10% accuracy (randomly picking a class out of 10 classes). Seems like the network learnt something. Hmmm, what are the classes that performed well, and the classes that did not perform well: .. GENERATED FROM PYTHON SOURCE LINES 268-291 .. code-block:: default # prepare to count predictions for each class correct_pred = {classname: 0 for classname in classes} total_pred = {classname: 0 for classname in classes} # again no gradients needed with torch.no_grad(): for data in testloader: images, labels = data outputs = net(images) _, predictions = torch.max(outputs, 1) # collect the correct predictions for each class for label, prediction in zip(labels, predictions): if label == prediction: correct_pred[classes[label]] += 1 total_pred[classes[label]] += 1 # print accuracy for each class for classname, correct_count in correct_pred.items(): accuracy = 100 * float(correct_count) / total_pred[classname] print(f'Accuracy for class: {classname:5s} is {accuracy:.1f} %') .. rst-class:: sphx-glr-script-out .. code-block:: none Accuracy for class: plane is 37.9 % Accuracy for class: car is 62.2 % Accuracy for class: bird is 45.6 % Accuracy for class: cat is 29.2 % Accuracy for class: deer is 50.3 % Accuracy for class: dog is 45.9 % Accuracy for class: frog is 60.1 % Accuracy for class: horse is 70.3 % Accuracy for class: ship is 82.9 % Accuracy for class: truck is 63.1 % .. GENERATED FROM PYTHON SOURCE LINES 292-303 Okay, so what next? How do we run these neural networks on the GPU? Training on GPU ---------------- Just like how you transfer a Tensor onto the GPU, you transfer the neural net onto the GPU. Let's first define our device as the first visible cuda device if we have CUDA available: .. GENERATED FROM PYTHON SOURCE LINES 303-310 .. code-block:: default device = torch.device('cuda:0' if torch.cuda.is_available() else 'cpu') # Assuming that we are on a CUDA machine, this should print a CUDA device: print(device) .. rst-class:: sphx-glr-script-out .. code-block:: none cuda:0 .. GENERATED FROM PYTHON SOURCE LINES 311-364 The rest of this section assumes that ``device`` is a CUDA device. Then these methods will recursively go over all modules and convert their parameters and buffers to CUDA tensors: .. code:: python net.to(device) Remember that you will have to send the inputs and targets at every step to the GPU too: .. code:: python inputs, labels = data[0].to(device), data[1].to(device) Why don't I notice MASSIVE speedup compared to CPU? Because your network is really small. **Exercise:** Try increasing the width of your network (argument 2 of the first ``nn.Conv2d``, and argument 1 of the second ``nn.Conv2d`` – they need to be the same number), see what kind of speedup you get. **Goals achieved**: - Understanding PyTorch's Tensor library and neural networks at a high level. - Train a small neural network to classify images Training on multiple GPUs ------------------------- If you want to see even more MASSIVE speedup using all of your GPUs, please check out :doc:`data_parallel_tutorial`. Where do I go next? ------------------- - :doc:`Train neural nets to play video games ` - `Train a state-of-the-art ResNet network on imagenet`_ - `Train a face generator using Generative Adversarial Networks`_ - `Train a word-level language model using Recurrent LSTM networks`_ - `More examples`_ - `More tutorials`_ - `Discuss PyTorch on the Forums`_ - `Chat with other users on Slack`_ .. _Train a state-of-the-art ResNet network on imagenet: https://github.com/pytorch/examples/tree/master/imagenet .. _Train a face generator using Generative Adversarial Networks: https://github.com/pytorch/examples/tree/master/dcgan .. _Train a word-level language model using Recurrent LSTM networks: https://github.com/pytorch/examples/tree/master/word_language_model .. _More examples: https://github.com/pytorch/examples .. _More tutorials: https://github.com/pytorch/tutorials .. _Discuss PyTorch on the Forums: https://discuss.pytorch.org/ .. _Chat with other users on Slack: https://pytorch.slack.com/messages/beginner/ .. GENERATED FROM PYTHON SOURCE LINES 366-367 .. code-block:: default del dataiter .. rst-class:: sphx-glr-timing **Total running time of the script:** ( 1 minutes 58.522 seconds) .. _sphx_glr_download_beginner_blitz_cifar10_tutorial.py: .. only:: html .. container:: sphx-glr-footer sphx-glr-footer-example .. container:: sphx-glr-download sphx-glr-download-python :download:`Download Python source code: cifar10_tutorial.py ` .. container:: sphx-glr-download sphx-glr-download-jupyter :download:`Download Jupyter notebook: cifar10_tutorial.ipynb ` .. only:: html .. rst-class:: sphx-glr-signature `Gallery generated by Sphinx-Gallery `_