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": "\u8fd9\u4f1a\u5728 Carvana \u6570\u636e\u96c6\u4e0a\u8bad\u7ec3\u4e00\u4e2a U-Net \u6a21\u578b\u3002\u4f60\u53ef\u4ee5\u5728 Kaggle \u4e0a\u627e\u5230\u4e0b\u8f7d\u8bf4\u660e\u3002
\n\u5c06\u8bad\u7ec3\u56fe\u50cf\u4fdd\u5b58\u5728_^_0_^_\u6587\u4ef6\u5939\u4e2d\uff0c\u5c06\u8499\u7248\u4fdd\u5b58\u5728_^_1_^_\u6587\u4ef6\u5939\u4e2d\u3002
\n\u4e3a\u7b80\u5355\u8d77\u89c1\uff0c\u6211\u4eec\u4e0d\u8fdb\u884c\u8bad\u7ec3\u548c\u9a8c\u8bc1\u62c6\u5206\u3002
\n", "\n": "\n", "
U-Net model
\n": "U-Net \u6a21\u578b
\n", "Adam optimizer
\n": "Adam \u4f18\u5316\u5668
\n", "Batch size
\n": "\u6279\u91cf\u5927\u5c0f
\n", "Calculate loss
\n": "\u8ba1\u7b97\u635f\u5931
\n", "Compute gradients
\n": "\u8ba1\u7b97\u68af\u5ea6
\n", "Create configurations
\n": "\u521b\u5efa\u914d\u7f6e
\n", "Create dataloader
\n": "\u521b\u5efa\u6570\u636e\u52a0\u8f7d\u5668
\n", "Create experiment
\n": "\u521b\u5efa\u5b9e\u9a8c
\n", "Create optimizer
\n": "\u521b\u5efa\u4f18\u5316\u5668
\n", "Crop the image to the size of the mask
\n": "\u5c06\u56fe\u50cf\u88c1\u526a\u4e3a\u8499\u7248\u7684\u5927\u5c0f
\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": "\u5c06\u76ee\u6807\u8499\u7248\u88c1\u526a\u4e3a logits \u7684\u5927\u5c0f\u3002\u5982\u679c\u6211\u4eec\u4e0d\u5728 U-Net \u7684\u5377\u79ef\u5c42\u4e2d\u4f7f\u7528\u586b\u5145\uff0clogits \u7684\u5927\u5c0f\u4f1a\u53d8\u5c0f\u3002
\n", "Dataloader
\n": "\u6570\u636e\u52a0\u8f7d\u5668
\n", "Dataset
\n": "\u6570\u636e\u96c6
\n", "Device to train the model on. _^_0_^_ picks up an available CUDA device or defaults to CPU.
\n": "\u7528\u4e8e\u8bad\u7ec3\u6a21\u578b\u7684\u8bbe\u5907\u3002_^_0_^_\u9009\u62e9\u53ef\u7528\u7684 CUDA \u8bbe\u5907\u6216\u9ed8\u8ba4\u4e3a CPU\u3002
\n", "Get a random sample
\n": "\u968f\u673a\u83b7\u53d6\u6837\u672c
\n", "Get predicted mask
\n": "\u83b7\u53d6\u9884\u6d4b\u7684\u53e3\u7f69
\n", "Get predicted mask logits
\n": "\u83b7\u53d6\u9884\u6d4b\u7684\u63a9\u7801\u65e5\u5fd7
\n", "Image logging
\n": "\u56fe\u50cf\u65e5\u5fd7\u8bb0\u5f55
\n", "Increment global step
\n": "\u9012\u589e\u5168\u5c40\u6b65\u957f
\n", "Initialize
\n": "\u521d\u59cb\u5316
\n", "Initialize the Carvana dataset
\n": "\u521d\u59cb\u5316 C arvana \u6570\u636e\u96c6
\n", "Initialize the model
\n": "\u521d\u59cb\u5316\u6a21\u578b
\n", "Iterate through the dataset. Use _^_0_^_ to sample _^_1_^_ times per epoch.
\n": "\u904d\u5386\u6570\u636e\u96c6\u3002\u7528\u4e8e_^_0_^_\u5bf9\u6bcf\u4e2a\u7eaa\u5143\u7684\u91c7\u6837_^_1_^_\u6b21\u6570\u3002
\n", "Learning rate
\n": "\u5b66\u4e60\u7387
\n", "Log samples
\n": "\u65e5\u5fd7\u6837\u672c
\n", "Loss function
\n": "\u4e8f\u635f\u51fd\u6570
\n", "Make the gradients zero
\n": "\u5c06\u6e10\u53d8\u8bbe\u4e3a\u96f6
\n", "Move data to device
\n": "\u5c06\u6570\u636e\u79fb\u52a8\u5230\u8bbe\u5907
\n", "New line in the console
\n": "\u63a7\u5236\u53f0\u4e2d\u7684\u65b0\u884c
\n", "Number of channels in the image. _^_0_^_ for RGB.
\n": "\u56fe\u50cf\u4e2d\u7684\u901a\u9053\u6570\u3002_^_0_^_\u5bf9\u4e8e RGB\u3002
\n", "Number of channels in the output mask. _^_0_^_ for binary mask.
\n": "\u8f93\u51fa\u63a9\u7801\u4e2d\u7684\u58f0\u9053\u6570\u3002_^_0_^_\u7528\u4e8e\u4e8c\u8fdb\u5236\u63a9\u7801\u3002
\n", "Number of training epochs
\n": "\u8bad\u7ec3\u5468\u671f\u7684\u6570\u91cf
\n", "Save the model
\n": "\u4fdd\u5b58\u6a21\u578b
\n", "Set configurations. You can override the defaults by passing the values in the dictionary.
\n": "\u8bbe\u7f6e\u914d\u7f6e\u3002\u60a8\u53ef\u4ee5\u901a\u8fc7\u5728\u5b57\u5178\u4e2d\u4f20\u9012\u503c\u6765\u8986\u76d6\u9ed8\u8ba4\u503c\u3002
\n", "Set models for saving and loading
\n": "\u8bbe\u7f6e\u7528\u4e8e\u4fdd\u5b58\u548c\u52a0\u8f7d\u7684\u6a21\u578b
\n", "Sigmoid function for binary classification
\n": "\u4e8c\u8fdb\u5236\u5206\u7c7b\u7684 Sigmoid \u51fd\u6570
\n", "Start and run the training loop
\n": "\u542f\u52a8\u5e76\u8fd0\u884c\u8bad\u7ec3\u5faa\u73af
\n", "Take an optimization step
\n": "\u91c7\u53d6\u4f18\u5316\u6b65\u9aa4
\n", "Track the loss
\n": "\u8ffd\u8e2a\u635f\u5931
\n", "Train the model
\n": "\u8bad\u7ec3\u6a21\u578b
\n", "Code for training a U-Net model on Carvana dataset.": "\u7528\u4e8e\u5728 Carvana \u6570\u636e\u96c6\u4e0a\u8bad\u7ec3 U-Net \u6a21\u578b\u7684\u4ee3\u7801\u3002", "Training a U-Net on Carvana dataset": "\u5728 Carvana \u6570\u636e\u96c6\u4e0a\u8bad\u7ec3 U-Net" }