Closed tianylijun closed 6 years ago
@tianylijun Make sure use ReLU6 to replace ReLU
@tianylijun Make sure use ReLU6 to replace ReLU
@chuanqi305
offset problem is the pad diff between TensorFlow and caffe, I fix it add tf_pad =SAME in caffe prototxt(hope you update the gen_model.py with tf_pad =SAME support, thanks), and I replace relu with relu6. But the result still has some diff with TensorFlow, and the dog recog as bird。
I have fix it
@tianylijun how to fix it ?i meet the same error as you.
i convert ssdlite_mobilenet_v2_coco_2018_05_09 model from tensorflow to caffe, the result boxs get from caffe (I use your ssd caffe with relu6 version) all have some offset, any suggest about the issuse?
I get there is has_tf_pad in base_conv_layer.cpp, how to add this param into prototxt?????