Intel® Distribution of OpenVINO™ Toolkit
Community assistance about the Intel® Distribution of OpenVINO™ toolkit, OpenCV, and all aspects of computer vision-related on Intel® platforms.

Bug in CaffeParser.py with Scale layer

idata
Employee
682 Views

Scale layer in Caffe can be used along with batch normalization to implement scale and shift operation, or it can be used to multiply 2 bottom blobs together. For example, in this paper it is used simply to multiple bottom blobs together and this layer doesn't have any weights and bias. I assume this possible utilization of Scale layer was missed during writing CaffeParser.py.

 

Overall the bug is the following. If you take a squeeze-and-excitation caffe model (or any other model with Scale layer as multiplier of bottom layers) and run mvNCProfile deploy.prototxt -is 224 224 the code will fail at line 237 return blobs[layer.name][0].data.astype(dtype=data_type), None in CaffeParser.py since this layer neither has weights nor biases.

0 Kudos
1 Reply
idata
Employee
448 Views

@ukrdailo Thanks for bringing this to our attention.

0 Kudos
Reply