princeton-vl / pose-ae-train

Training code for "Associative Embedding: End-to-End Learning for Joint Detection and Grouping"
BSD 3-Clause "New" or "Revised" License
373 stars 76 forks source link

Any way to convert the model to tensorflow? #17

Open jsolves opened 6 years ago

jsolves commented 6 years ago

Hello:

I have changed the pose-ae-train to detect keypoints no-human related. This results in different number of outputs (not 17) and different weights in layers. Anybody knows how to convert the pytorch model to tensorflow (so I can infere with pose-ae-demo)?

I tried pytorch2keras, onnx and mmdnn but none of them works.

Thanks in advance.

DLluopf commented 6 years ago

have you solve this problem?