{ "
We use _^_0_^_ which defines all the dataset related configurations, optimizer, and a training loop.
\n": "\u6211\u4eec\u4f7f\u7528_^_0_^_\u5b83\u6765\u5b9a\u4e49\u6240\u6709\u4e0e\u6570\u636e\u96c6\u76f8\u5173\u7684\u914d\u7f6e\u3001\u4f18\u5316\u5668\u548c\u8bad\u7ec3\u5faa\u73af\u3002
\n", "\n": "\n", "
Create transformer configs
\n": "\u521b\u5efa\u53d8\u538b\u5668\u914d\u7f6e
\n", "Transformer configurations to get transformer layer
\n": "\u83b7\u5f97\u53d8\u538b\u5668\u5c42\u7684\u53d8\u538b\u5668\u914d\u7f6e
\n", "Augment CIFAR 10 images for training
\n": "\u589e\u5f3a CIFAR 10 \u56fe\u50cf\u7528\u4e8e\u8bad\u7ec3
\n", "Create a vision transformer
\n": "\u521b\u5efa\u89c6\u89c9\u53d8\u538b\u5668
\n", "Create configurations
\n": "\u521b\u5efa\u914d\u7f6e
\n", "Create experiment
\n": "\u521b\u5efa\u5b9e\u9a8c
\n", "Do not augment CIFAR 10 images for validation
\n": "\u4e0d\u8981\u6269\u5927 CIFAR 10 \u56fe\u50cf\u8fdb\u884c\u9a8c\u8bc1
\n", "Load configurations
\n": "\u88c5\u8f7d\u914d\u7f6e
\n", "Number of classes in the task
\n": "\u4efb\u52a1\u4e2d\u7684\u7c7b\u6570
\n", "Optimizer
\n": "\u4f18\u5316\u5668
\n", "Set model for saving/loading
\n": "\u8bbe\u7f6e\u4fdd\u5b58/\u52a0\u8f7d\u7684\u6a21\u578b
\n", "Size of a patch
\n": "\u8865\u4e01\u7684\u5927\u5c0f
\n", "Size of the hidden layer in classification head
\n": "\u5206\u7c7b\u5934\u4e2d\u9690\u85cf\u5c42\u7684\u5927\u5c0f
\n", "Start the experiment and run the training loop
\n": "\u5f00\u59cb\u5b9e\u9a8c\u5e76\u8fd0\u884c\u8bad\u7ec3\u5faa\u73af
\n", "Training epochs and batch size
\n": "\u8bad\u7ec3\u5468\u671f\u548c\u6279\u6b21\u5927\u5c0f
\n", "Transformer embedding size
\n": "\u53d8\u538b\u5668\u5d4c\u5165\u5c3a\u5bf8
\n", "Transformer size from Transformer configurations
\n": "\u53d8\u538b\u5668\u914d\u7f6e\u4e2d\u7684\u53d8\u538b\u5668\u5c3a\u5bf8
\n", "Train a Vision Transformer (ViT) on CIFAR 10": "\u5728 CIFAR 10 \u4e0a\u8bad\u7ec3\u89c6\u89c9\u53d8\u538b\u5668 (ViT)" }