pytorch转caffe中maxpool一定要注意,不然成功转换了还是会出错.下面给出了pytorch与caffe中maxpool层的转换的对应关系.为了自己以后不要再被这个问题坑吧.
fast-reid中怎么转caffe成功且正确.
pytorch layer
self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, ceil_mode=True)caffe layer:
layer {name: "max_pool1"type: "Pooling"bottom: "relu_blob1"top: "max_pool_blob1"pooling_param {pool: MAXkernel_size: 3stride: 2pad: 0 # 1# ceil_mode: false}
}