This trains a U-Net model on Carvana dataset. You can find the download instructions on Kaggle.
\nSave the training images inside _^_0_^_ folder and the masks in _^_1_^_ folder.
\nFor simplicity, we do not do a training and validation split.
\n": "\u3053\u308c\u306b\u3088\u308a\u3001Carvana\u30c7\u30fc\u30bf\u30bb\u30c3\u30c8\u3067U-Net\u30e2\u30c7\u30eb\u3092\u30c8\u30ec\u30fc\u30cb\u30f3\u30b0\u3057\u307e\u3059\u3002\u30c0\u30a6\u30f3\u30ed\u30fc\u30c9\u624b\u9806\u306f Kaggle \u3067\u78ba\u8a8d\u3067\u304d\u307e\u3059
\u3002\n_^_0_^_\u30c8\u30ec\u30fc\u30cb\u30f3\u30b0\u753b\u50cf\u3092\u30d5\u30a9\u30eb\u30c0\u30fc\u5185\u306b\u4fdd\u5b58\u3057\u3001_^_1_^_\u30de\u30b9\u30af\u3092\u30d5\u30a9\u30eb\u30c0\u30fc\u306b\u4fdd\u5b58\u3057\u307e\u3059\u3002
\n\u308f\u304b\u308a\u3084\u3059\u304f\u3059\u308b\u305f\u3081\u306b\u3001\u30c8\u30ec\u30fc\u30cb\u30f3\u30b0\u3068\u691c\u8a3c\u306e\u5206\u5272\u306f\u884c\u3063\u3066\u3044\u307e\u305b\u3093\u3002
\n", "\n": "\n", "
U-Net model
\n": "U-\u30cd\u30c3\u30c8\u30e2\u30c7\u30eb
\n", "Adam optimizer
\n": "\u30a2\u30c0\u30e0\u30fb\u30aa\u30d7\u30c6\u30a3\u30de\u30a4\u30b6\u30fc
\n", "Batch size
\n": "\u30d0\u30c3\u30c1\u30b5\u30a4\u30ba
\n", "Calculate loss
\n": "\u640d\u5931\u306e\u8a08\u7b97
\n", "Compute gradients
\n": "\u52fe\u914d\u306e\u8a08\u7b97
\n", "Create configurations
\n": "\u69cb\u6210\u306e\u4f5c\u6210
\n", "Create dataloader
\n": "\u30c7\u30fc\u30bf\u30ed\u30fc\u30c0\u30fc\u306e\u4f5c\u6210
\n", "Create experiment
\n": "\u5b9f\u9a13\u3092\u4f5c\u6210
\n", "Create optimizer
\n": "\u30aa\u30d7\u30c6\u30a3\u30de\u30a4\u30b6\u30fc\u3092\u4f5c\u6210
\n", "Crop the image to the size of the mask
\n": "\u753b\u50cf\u3092\u30de\u30b9\u30af\u306e\u30b5\u30a4\u30ba\u306b\u30c8\u30ea\u30df\u30f3\u30b0\u3057\u307e\u3059
\n", "Crop the target mask to the size of the logits. Size of the logits will be smaller if we don't use padding in convolutional layers in the U-Net.
\n": "\u30bf\u30fc\u30b2\u30c3\u30c8\u30de\u30b9\u30af\u3092\u30ed\u30b8\u30c3\u30c8\u306e\u30b5\u30a4\u30ba\u306b\u30c8\u30ea\u30df\u30f3\u30b0\u3057\u307e\u3059\u3002U-Net\u306e\u7573\u307f\u8fbc\u307f\u5c64\u306b\u30d1\u30c7\u30a3\u30f3\u30b0\u3092\u4f7f\u308f\u306a\u3044\u3068\u3001\u30ed\u30b8\u30c3\u30c8\u306e\u30b5\u30a4\u30ba\u306f\u5c0f\u3055\u304f\u306a\u308a\u307e\u3059
\u3002\n", "Dataloader
\n": "\u30c7\u30fc\u30bf\u30ed\u30fc\u30c0\u30fc
\n", "Dataset
\n": "\u30c7\u30fc\u30bf\u30bb\u30c3\u30c8
\n", "Device to train the model on. _^_0_^_ picks up an available CUDA device or defaults to CPU.
\n": "\u30e2\u30c7\u30eb\u3092\u30c8\u30ec\u30fc\u30cb\u30f3\u30b0\u3059\u308b\u30c7\u30d0\u30a4\u30b9\u3002_^_0_^_\u4f7f\u7528\u53ef\u80fd\u306a CUDA \u30c7\u30d0\u30a4\u30b9\u3092\u9078\u629e\u3059\u308b\u304b\u3001\u30c7\u30d5\u30a9\u30eb\u30c8\u3067 CPU \u306b\u8a2d\u5b9a\u3057\u307e\u3059
\u3002\n", "Get a random sample
\n": "\u30e9\u30f3\u30c0\u30e0\u30b5\u30f3\u30d7\u30eb\u3092\u5165\u624b
\n", "Get predicted mask
\n": "\u4e88\u6e2c\u30de\u30b9\u30af\u3092\u53d6\u5f97
\n", "Get predicted mask logits
\n": "\u4e88\u6e2c\u3055\u308c\u305f\u30de\u30b9\u30af\u30ed\u30b8\u30c3\u30c8\u306e\u53d6\u5f97
\n", "Image logging
\n": "\u753b\u50cf\u30ed\u30ae\u30f3\u30b0
\n", "Increment global step
\n": "\u30b0\u30ed\u30fc\u30d0\u30eb\u30b9\u30c6\u30c3\u30d7\u3092\u30a4\u30f3\u30af\u30ea\u30e1\u30f3\u30c8
\n", "Initialize
\n": "[\u521d\u671f\u5316]
\n", "Initialize the Carvana dataset
\n": "Carvana \u30c7\u30fc\u30bf\u30bb\u30c3\u30c8\u3092\u521d\u671f\u5316\u3057\u307e\u3059
\n", "Initialize the model
\n": "\u30e2\u30c7\u30eb\u3092\u521d\u671f\u5316
\n", "Iterate through the dataset. Use _^_0_^_ to sample _^_1_^_ times per epoch.
\n": "\u30c7\u30fc\u30bf\u30bb\u30c3\u30c8\u3092\u7e70\u308a\u8fd4\u3057\u51e6\u7406\u3057\u307e\u3059\u3002_^_0_^__^_1_^_\u30a8\u30dd\u30c3\u30af\u3042\u305f\u308a\u306e\u30b5\u30f3\u30d7\u30ea\u30f3\u30b0\u6642\u9593\u306b\u4f7f\u7528\u3057\u307e\u3059
\u3002\n", "Learning rate
\n": "\u5b66\u7fd2\u7387
\n", "Log samples
\n": "\u30ed\u30b0\u30b5\u30f3\u30d7\u30eb
\n", "Loss function
\n": "\u640d\u5931\u95a2\u6570
\n", "Make the gradients zero
\n": "\u30b0\u30e9\u30c7\u30fc\u30b7\u30e7\u30f3\u3092\u30bc\u30ed\u306b\u3059\u308b
\n", "Move data to device
\n": "\u30c7\u30fc\u30bf\u3092\u30c7\u30d0\u30a4\u30b9\u306b\u79fb\u52d5
\n", "New line in the console
\n": "\u30b3\u30f3\u30bd\u30fc\u30eb\u306e\u65b0\u3057\u3044\u884c
\n", "Number of channels in the image. _^_0_^_ for RGB.
\n": "\u753b\u50cf\u5185\u306e\u30c1\u30e3\u30f3\u30cd\u30eb\u6570\u3002_^_0_^_RGB \u7528\u3067\u3059\u3002
\n", "Number of channels in the output mask. _^_0_^_ for binary mask.
\n": "\u51fa\u529b\u30de\u30b9\u30af\u306e\u30c1\u30e3\u30f3\u30cd\u30eb\u6570\u3002_^_0_^_\u30d0\u30a4\u30ca\u30ea\u30de\u30b9\u30af\u7528\u3002
\n", "Number of training epochs
\n": "\u30c8\u30ec\u30fc\u30cb\u30f3\u30b0\u30a8\u30dd\u30c3\u30af\u306e\u6570
\n", "Save the model
\n": "\u30e2\u30c7\u30eb\u3092\u4fdd\u5b58\u3059\u308b
\n", "Set configurations. You can override the defaults by passing the values in the dictionary.
\n": "\u69cb\u6210\u3092\u8a2d\u5b9a\u3057\u307e\u3059\u3002\u30c7\u30a3\u30af\u30b7\u30e7\u30ca\u30ea\u306b\u5024\u3092\u6e21\u3059\u3053\u3068\u3067\u30c7\u30d5\u30a9\u30eb\u30c8\u3092\u30aa\u30fc\u30d0\u30fc\u30e9\u30a4\u30c9\u3067\u304d\u307e\u3059\u3002
\n", "Set models for saving and loading
\n": "\u4fdd\u5b58\u304a\u3088\u3073\u8aad\u307f\u8fbc\u307f\u7528\u306e\u30e2\u30c7\u30eb\u3092\u8a2d\u5b9a\u3059\u308b
\n", "Sigmoid function for binary classification
\n": "\u30d0\u30a4\u30ca\u30ea\u5206\u985e\u7528\u306e\u30b7\u30b0\u30e2\u30a4\u30c9\u95a2\u6570
\n", "Start and run the training loop
\n": "\u30c8\u30ec\u30fc\u30cb\u30f3\u30b0\u30eb\u30fc\u30d7\u3092\u958b\u59cb\u3057\u3066\u5b9f\u884c\u3059\u308b
\n", "Take an optimization step
\n": "\u6700\u9069\u5316\u306e\u4e00\u6b69\u3092\u8e0f\u307f\u51fa\u3059
\n", "Track the loss
\n": "\u640d\u5931\u3092\u30c8\u30e9\u30c3\u30ad\u30f3\u30b0
\n", "Train the model
\n": "\u30e2\u30c7\u30eb\u306e\u30c8\u30ec\u30fc\u30cb\u30f3\u30b0
\n", "Code for training a U-Net model on Carvana dataset.": "Carvana\u30c7\u30fc\u30bf\u30bb\u30c3\u30c8\u3067U-Net\u30e2\u30c7\u30eb\u3092\u30c8\u30ec\u30fc\u30cb\u30f3\u30b0\u3059\u308b\u305f\u3081\u306e\u30b3\u30fc\u30c9\u3002", "Training a U-Net on Carvana dataset": "Carvana\u30c7\u30fc\u30bf\u30bb\u30c3\u30c8\u3067\u306eU-Net\u306e\u30c8\u30ec\u30fc\u30cb\u30f3\u30b0" }