python - Caffe to Keras conversion of grouped convolution ...
stackoverflow.com › questions › 54610665Feb 10, 2019 · As you see, conv1 shape in Caffe and Keras are equal (ignoring the order). But in Caffe conv2 shape is [ (256, 48, 5, 5), (256,)]), whereas in Keras 'conv2' shape is [ (5, 5, 96, 256), (256,)], notice, that 48*2=96. Also, notice that conv2 layer is directly after the max pooling layer, so there might be something wrong with the max pooling ...