ciaochao

@farmingyard Thanks a lot. But i found some differences between prototxt and caffemodel, in 'resx5_conv1', num_output : 60 in your prototxt, and 240 in your model. i think it should...

@farmingyard I have found the real difference, missing the param "group" in resx5_conv1 and resx13_conv1 in your prototxt, and missing the shuffle_layer, i think you forget to update the prototxt.

@ananddb90 not good, only 63% on VOC, still in finetune. how about you?

@CrazySssst i have pre-trained on coco, 63% is the result after pre-train on coco.