xiaoheizi123 commented on issue #7162: Cant convert caffe model to mxnet URL: https://github.com/apache/incubator-mxnet/issues/7162#issuecomment-367900241 I also cannot convert resnet-50 using **python convert_caffe_modelzoo.py resnet-50** `converting scale layer, beta shape = (2048,), gamma shape = (2048,) skipping layer res5c of type Eltwise skipping layer res5c_relu of type ReLU skipping layer pool5 of type Pooling converting layer fc1000, wmat shape = (1000, 2048), bias shape = (1000,) skipping layer prob of type Softmax /home/users/rui.zheng/anaconda2/lib/python2.7/site-packages/mxnet/module/base_module.py:65: UserWarning: Data provided by label_shapes don't match names specified by label_names ([] vs. ['prob_label']) warnings.warn(msg) Traceback (most recent call last): File "convert_caffe_modelzoo.py", line 144, in <module> fname, _ = convert_caffe_model(args.model_name, model_meta_info[args.model_name]) File "convert_caffe_modelzoo.py", line 133, in convert_caffe_model convert_mean(mean, [mx_mean]) File "/home/users/rui.zheng/works/incubator-mxnet/tools/caffe_converter/convert_mean.py", line 44, in convert_mean mean_blob.ParseFromString(f.read()) google.protobuf.message.DecodeError: Error parsing message ` f.read() is ok, but mean_blob is None when print it? I also read [https://github.com/apache/incubator-mxnet/blob/430ea7bfbbda67d993996d81c7fd44d3a20ef846/docs/how_to/caffe.md](url), and do what **Converting Caffe trained models to MXNet** part shows, but it is still wrong, what should I do?
---------------------------------------------------------------- This is an automated message from the Apache Git Service. To respond to the message, please log on GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: us...@infra.apache.org With regards, Apache Git Services