{ "
Create a configurable optimizer. We can change the optimizer type and hyper-parameters using configurations.
\n": "\u521b\u5efa\u53ef\u914d\u7f6e\u7684\u4f18\u5316\u5668\u3002\u6211\u4eec\u53ef\u4ee5\u4f7f\u7528\u914d\u7f6e\u66f4\u6539\u4f18\u5316\u5668\u7c7b\u578b\u548c\u8d85\u53c2\u6570\u3002
\n", "Add global step if we are in training mode
\n": "\u5982\u679c\u6211\u4eec\u5904\u4e8e\u8bad\u7ec3\u6a21\u5f0f\uff0c\u5219\u6dfb\u52a0\u5168\u5c40\u6b65\u957f
\n", "Calculate the accuracy
\n": "\u8ba1\u7b97\u7cbe\u5ea6
\n", "Calculate the gradients
\n": "\u8ba1\u7b97\u68af\u5ea6
\n", "Calculate the loss
\n": "\u8ba1\u7b97\u635f\u5931
\n", "Clear the gradients
\n": "\u6e05\u9664\u6e10\u53d8
\n", "Get the batch
\n": "\u83b7\u53d6\u6279\u6b21
\n", "Log the loss
\n": "\u8bb0\u5f55\u635f\u5931
\n", "Log the parameter and gradient L2 norms once per epoch
\n": "\u6bcf\u4e2a\u7eaa\u5143\u8bb0\u5f55\u4e00\u6b21\u53c2\u6570\u548c\u68af\u5ea6 L2 \u89c4\u8303
\n", "Optimize if we are in training mode
\n": "\u5982\u679c\u6211\u4eec\u5904\u4e8e\u8bad\u7ec3\u6a21\u5f0f\uff0c\u8bf7\u8fdb\u884c\u4f18\u5316
\n", "Run the model and specify whether to log the activations
\n": "\u8fd0\u884c\u6a21\u578b\u5e76\u6307\u5b9a\u662f\u5426\u8bb0\u5f55\u6fc0\u6d3b
\n", "Save logs
\n": "\u4fdd\u5b58\u65e5\u5fd7
\n", "Specify the optimizer
\n": "\u6307\u5b9a\u4f18\u5316\u5668
\n", "Take optimizer step
\n": "\u91c7\u53d6\u4f18\u5316\u5668\u6b65\u9aa4
\n", "MNIST example to test the optimizers": "\u6d4b\u8bd5\u4f18\u5316\u5668\u7684 MNIST \u793a\u4f8b", "This is a simple MNIST example with a CNN model to test the optimizers.": "\u8fd9\u662f\u4e00\u4e2a\u7b80\u5355\u7684 MNIST \u793a\u4f8b\uff0c\u5176\u4e2d\u5305\u542b CNN \u6a21\u578b\u6765\u6d4b\u8bd5\u4f18\u5316\u5668\u3002" }