{
  "fetched_at": "2026-10-19T10:39:51Z",
  "source_url": "https://www.kaggle.com/competitions/cifar-10-image-classification-exercise/data",
  "pages": [
    {
      "name": "rules",
      "content": "This is a page where you can include rules that participants must accept before joining. You may wish to include rules like:\n\n - Don't cheat!\n - Apply yourself!\n - Have fun!",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "data-description",
      "content": "# Data Description\n<p>This is the CIFAR-10 Dataset consists of a collection of 60,000 images of 32x32 pixels with three 8-bit RGB channels. Note that in some machine learning frameworks this data set can be downloaded directly into data structures useful for processing in the CNN.</p>\n![](https://appliedmachinelearning.files.wordpress.com/2018/03/cifar2.jpg)\n\nThe data is REQUIRED to be read using the following code:\n> `import torchvision`\n> \n> `from torchvision.datasets import CIFAR10`\n> \n> \n> `TRAIN_TRANSFORMS = torchvision.transforms.ToTensor()`\n> \n> `TEST_TRANSFORMS = TRAIN_TRANSFORMS`\n> \n> `BATCH_SIZE = 16`\n> \n> `### DO NOT MODIFY ANY CODE STARTING HERE ###`\n> \n> `cifar_train = CIFAR10('./data', download=True, train=True, transform=TRAIN_TRANSFORMS)`\n> \n> `cifar_test = CIFAR10('./data', download=True, train=False, transform=TEST_TRANSFORMS)`\n> \n> `temp_dataloader = torch.utils.data.DataLoader(cifar_data_test, batch_size=10000, shuffle=False)`\n> \n> `temp_data = next(iter(temp_dataloader))[0]`\n> \n> `train_dataloader = torch.utils.data.DataLoader(cifar_train, batch_size=BATCH_SIZE, shuffle=False)`\n> \n> `test_dataloader = torch.utils.data.DataLoader(temp_data, batch_size=BATCH_SIZE, shuffle=False)`\n> \n> `del cifar_train, cifar_test, temp_dataloader, temp_data`\n> \n> `### END OF CODE NOT TO MODIFY ###`",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "<p>The Convolutional Neural Network (CNN) is a class of deep learning neural networks. CNNs represents a huge breakthrough in image recognition. They’re most commonly used to analyze visual imagery and are frequently working behind the scenes in image classification. They can be found at the core of everything from Facebook’s photo tagging to self-driving cars. They’re working hard behind the scenes in everything from healthcare to security.</p>\n<p>In this exercise, your task is to create a Convolutional Neural Network(CNN) based image classifer for the CIFAR-10 dataset of images [3]. Feel free to experiment with different architectures, hyper-parameters, and training procedures to make yourself familiar with training and tuning CNN models. Please refer to the papers  listed below for inspiration.</p>\n<h2>References</h2>\n<p>[1] Sandler, M.; Howard, A.; Zhu, M.; Zhmoginov, A.; Chen, L.C. Mobilenetv2: Inverted residuals and linear bottlenecks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Salt Lake City, UT, USA, 18–22 June 2018; pp. 4510–4520.</p>\n<p>[2] Handwritten digit recognition with a back-propagation network, Y. LeCun, In Proc. Advances in Neural Information Processing Systems, (1990).</p>\n<p>[3] ImageNet Classification with Deep Convolutional Neural Networks, Krizhevsky, A., Sutskever, I. and Hinton, G. E., NIPS: Neural Information Processing Systems, (2012).</p>\n<p>[4] CIFAR10 Dataset: Learning Multiple Layers of Features from Tiny Images, Alex Krizhevsky, 2009. Images collected by Alex Krizhevsky, Vinod Nair, and Geoffrey Hinton of the Canadian Institute For Advanced Research, available at: https://www.cs.toronto.edu/~kriz/cifar.html.</p>\n<p>[5] Receptive fields of single neurons in the cat's striate cortex, Hubel, D.H.; Wiesel, T.N., J Physiol. 148 (3), (1959).</p>\n<p>[6] Deep learning, LeCun, Y., Bengio, Y., and Hinton, G., Nature, 521, May, (2015).</p>\n<p>[7] Neocognitron: A self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position, K. Fukushima, Biological Cybernetics, 36, 4, April (1980).</p>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "<p>You will be evaluated based on the percentage of labels that you predicted correctly i.e. classification accuracy.</p>\n<h2>Submission Format</h2>\nFor each image in the test set, predict a label(which is a number between 0 and 9) for the given id. Have a look at the sample submission csv file from the data section.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}