This extends from CIFAR 10 dataset configurations from _^_0_^_ and _^_1_^_.
\n": "\u8fd9\u662f\u4ece\u548c\u5f00\u59cb\u7684 CIFAR 10 \u6570\u636e\u96c6\u914d\u7f6e\u6269\u5c55_^_0_^_\u800c\u6765\u7684_^_1_^_\u3002
\n", "\n": "\n", "
Convolution and activation combined
\n": "\u5377\u79ef\u548c\u6fc0\u6d3b\u76f8\u7ed3\u5408
\n", "5 _^_0_^_ pooling layers will produce a output of size _^_1_^_. CIFAR 10 image size is _^_2_^_
\n": "5 \u4e2a_^_0_^_\u6c60\u5316\u56fe\u5c42\u5c06\u751f\u6210\u5927\u5c0f\u4e3a size \u7684\u8f93\u51fa_^_1_^_\u3002CIFAR 10 \u56fe\u50cf\u5927\u5c0f\u4e3a_^_2_^_
\n", "Convolution, Normalization and Activation layers
\n": "\u5377\u79ef\u3001\u5f52\u4e00\u5316\u548c\u6fc0\u6d3b\u5c42
\n", "Create a sequential model with the layers
\n": "\u4f7f\u7528\u5c42\u521b\u5efa\u987a\u5e8f\u6a21\u578b
\n", "Final linear layer
\n": "\u6700\u540e\u7684\u7ebf\u6027\u5c42
\n", "Final logits layer
\n": "\u6700\u540e\u7684 logits \u5c42
\n", "Max pooling at end of each block
\n": "\u6bcf\u4e2a\u533a\u5757\u672b\u7aef\u7684\u6700\u5927\u6c60\u6570
\n", "Number of channels in each layer in each block
\n": "\u6bcf\u4e2a\u533a\u5757\u4e2d\u6bcf\u5c42\u7684\u901a\u9053\u6570
\n", "Pad and crop
\n": "\u586b\u5145\u548c\u88c1\u526a
\n", "RGB channels
\n": "RGB \u901a\u9053
\n", "Random horizontal flip
\n": "\u968f\u673a\u6c34\u5e73\u7ffb\u8f6c
\n", "Reshape for classification layer
\n": "\u4fee\u6539\u5206\u7c7b\u56fe\u5c42\u7684\u5f62\u72b6
\n", "The VGG layers
\n": "VGG \u5c42
\n", "Use CIFAR10 dataset by default
\n": "\u9ed8\u8ba4\u4f7f\u7528 CIFAR10 \u6570\u636e\u96c6
\n", "CIFAR10 Experiment": "CIFAR10 \u5b9e\u9a8c", "This is a reusable trainer for CIFAR10 dataset": "\u8fd9\u662f CIFAR10 \u6570\u636e\u96c6\u7684\u53ef\u91cd\u590d\u4f7f\u7528\u7684\u8bad\u7ec3\u5668" }