{ "
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", "\n": "\n", "
Bottleneck sizes
\n": "\u74f6\u9888\u5927\u5c0f
\n", "Create configurations
\n": "\u521b\u5efa\u914d\u7f6e
\n", "Create experiment
\n": "\u521b\u5efa\u5b9e\u9a8c
\n", "Kernel size of the initial convolution layer
\n": "\u521d\u59cb\u5377\u79ef\u5c42\u7684\u5185\u6838\u5927\u5c0f
\n", "Linear layer for classification
\n": "\u7528\u4e8e\u5206\u7c7b\u7684\u7ebf\u6027\u5c42
\n", "Load configurations
\n": "\u88c5\u8f7d\u914d\u7f6e
\n", "Move the model to the device
\n": "\u5c06\u6a21\u578b\u79fb\u5230\u8bbe\u5907\u4e0a
\n", "Number fo blocks for each feature map size
\n": "\u6bcf\u4e2a\u8981\u7d20\u5730\u56fe\u5927\u5c0f\u7684\u533a\u5757\u6570
\n", "Number of channels for each feature map size
\n": "\u6bcf\u4e2a\u8981\u7d20\u6620\u5c04\u5927\u5c0f\u7684\u901a\u9053\u6570
\n", "Set model for saving/loading
\n": "\u8bbe\u7f6e\u4fdd\u5b58/\u52a0\u8f7d\u7684\u6a21\u578b
\n", "Stack them
\n": "\u5806\u53e0\u5b83\u4eec
\n", "Start the experiment and run the training loop
\n": "\u5f00\u59cb\u5b9e\u9a8c\u5e76\u8fd0\u884c\u8bad\u7ec3\u5faa\u73af
\n", "Train a ResNet on CIFAR 10": "\u5728 CIFAR 10 \u4e0a\u8bad\u7ec3 ResNet" }