MMdnn is a set of tools to help users inter-operate among different deep learning frameworks. E.g. model conversion and visualization. Convert models between Caffe, Keras, MXNet, Tensorflow, CNTK, PyTorch Onnx and CoreML.
MIT License
5.8k
stars
965
forks
source link
MXNet Parser has not supported operator Crop with name crop0 #907
Source framework with version (like Tensorflow 1.4.1 with GPU):
MXNET
Destination framework with version (like CNTK 2.3 with GPU):
Tensorflow
Pre-trained model path (webpath or webdisk path): mnet.25
https://drive.google.com/drive/folders/1OTXuAUdkLVaf78iz63D1uqGLZi4LbPeL
Running scripts:
mmconvert -sf mxnet -in ~/.insightface/models/retinaface_mnet025_v1/mnet10-symbol.json -iw ~/.insightface/models/retinaface_mnet025_v1/mnet10-0000.params -df tensorflow -om tf_retinaface_mnet_v1 --inputShape 3,480,640 --dump_tag SERVING
The error with MMDNN lastest release
Warning: convert the null operator with name [data] into input layer.
Warning: MXNet Parser has not supported operator Crop with name crop0.
Traceback (most recent call last):
File "/home/dmp/Silent-Face-Anti-Spoofing/luandd/bin/mmconvert", line 8, in <module>
sys.exit(_main())
File "/home/dmp/Silent-Face-Anti-Spoofing/luandd/lib/python3.6/site-packages/mmdnn/conversion/_script/convert.py", line 102, in _main
ret = convertToIR._convert(ir_args)
File "/home/dmp/Silent-Face-Anti-Spoofing/luandd/lib/python3.6/site-packages/mmdnn/conversion/_script/convertToIR.py", line 120, in _convert
parser.run(args.dstPath)
File "/home/dmp/Silent-Face-Anti-Spoofing/luandd/lib/python3.6/site-packages/mmdnn/conversion/common/DataStructure/parser.py", line 22, in run
self.gen_IR()
File "/home/dmp/Silent-Face-Anti-Spoofing/luandd/lib/python3.6/site-packages/mmdnn/conversion/mxnet/mxnet_parser.py", line 263, in gen_IR
self.rename_UNKNOWN(current_node)
File "/home/dmp/Silent-Face-Anti-Spoofing/luandd/lib/python3.6/site-packages/mmdnn/conversion/mxnet/mxnet_parser.py", line 374, in rename_UNKNOWN
raise NotImplementedError()
NotImplementedError
Platform (like ubuntu 16.04/win10): 18.04
Python version: 3.6
Source framework with version (like Tensorflow 1.4.1 with GPU): MXNET Destination framework with version (like CNTK 2.3 with GPU): Tensorflow Pre-trained model path (webpath or webdisk path): mnet.25 https://drive.google.com/drive/folders/1OTXuAUdkLVaf78iz63D1uqGLZi4LbPeL Running scripts:
mmconvert -sf mxnet -in ~/.insightface/models/retinaface_mnet025_v1/mnet10-symbol.json -iw ~/.insightface/models/retinaface_mnet025_v1/mnet10-0000.params -df tensorflow -om tf_retinaface_mnet_v1 --inputShape 3,480,640 --dump_tag SERVING
The error with MMDNN lastest release