Dear Developers,
I have tried to convert resnet50 model trained with code: https://github.com/mrharicot/monodepth
When converting checkpoint or frozed model to dlc model, the convert tool is just hang in session run:
snpe-1.17.0/lib/python/converters/tensorflow/util.py: 234
232 if len(requiring_evaluation) > 0:
233 try:
234 outputs = self._session.run(fetches=requiring_evaluation, feed_dict=input_tensors)
235 outputs = dict(zip(requiring_evaluation, outputs))
236 for t, o in outputs.iteritems():
237 self._tensor_value_cache[t.name] = o
238 outputs_map.update(outputs)
239 requiring_evaluation = []
240 except InvalidArgumentError:
241 pass
So why would it hang in session run?
My convert command line is :
./snpe-tensorflow-to-dlc --graph /home/damon/work/monodepth/my_model_resnet/frozen_model.pb -i split 1,256,512,3 --out_node model/decoder/mul_21 --dlc ~/work/monodepth/my_model_resnet/frozen_model.dlc
Any comments would be appreciated! Thanks.
Hi Everyone,
Has anybody converted resnet50 successfully?