Mobilenet_v2_quantized predict_net.pb file possible error

[TerryTsao]

TL;DR

Can't run the net using caffe2 following the 'Load Pretrained Net' tutorial. Keep showing error saying that 325 is not CPU Tensor. Fixed by changing the deserialized ascii prototxt and re-serialization.

---

I had posted this issue here before.

https://discuss.pytorch.org/t/caffe2-mobilenetv2-quantized-using-caffe2-blobistensortype-blob-cpu-blob-is-not-a-cpu-tensor-325/29065

After some experiments, I've discovered the problem and come up w/ a fix.

After I deserialized predict_net.pb file to ascii prototxt, I found out at the end, the network is supposed to output blob softmax instead of a Int8CPUTensor called 325. The problem, although I'm not entirely sure of on a source code basis, is probably because an Int8CPUTensor somehow fail the CAFFE_ENFORCE test.

When I change the very last line of the dumped ascii prototxt from exported_output: 325 to exported_output: softmax, everything worked just fine. So I'm thinking the file given in the official repo is not correct, at least for me.

I'm not sure if this happens to anyone else. Thought I put it here in case anyone encounters the same situation.

[dzung-hoang]

You can find the fixed predict_net.pb here.

[TerryTsao]

@dzung-hoang Great. I've fixed MobileNet myself as well. But it's good to know there is a bug in resnet_quant, too..... I can't believe this....