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.
When I run the third command I get the following error, could anyone help me with this error, please?
Traceback (most recent call last):
File "/Users/mahzadkhoshlessan/miniconda3/envs/DMG/lib/python3.8/runpy.py", line 194, in _run_module_as_main
return _run_code(code, main_globals, None,
File "/Users/mahzadkhoshlessan/miniconda3/envs/DMG/lib/python3.8/runpy.py", line 87, in _run_code
exec(code, run_globals)
File "/Users/mahzadkhoshlessan/miniconda3/envs/DMG/lib/python3.8/site-packages/mmdnn/conversion/examples/keras/imagenet_test.py", line 157, in <module>
tester = TestKeras()
File "/Users/mahzadkhoshlessan/miniconda3/envs/DMG/lib/python3.8/site-packages/mmdnn/conversion/examples/keras/imagenet_test.py", line 31, in __init__
self.model = self.MainModel.KitModel(self.args.w)
File "converted_ArcModel.py", line 61, in KitModel
minusscalar0 = my_sub()(data, minusscalar0_second)
NameError: name 'minusscalar0_second' is not defined
Platform (like ubuntu 16.04/win10): macOS Catalina V10.15.6
Python version: 3.8 Source framework with version (like Tensorflow 1.4.1 with GPU): mxnet1.6.0 Destination framework with version (like CNTK 2.3 with GPU): Keras '2.4.3' Pre-trained model path (webpath or webdisk path): https://www.dropbox.com/s/tj96fsm6t6rq8ye/model-r100-arcface-ms1m-refine-v2.zip?dl=0
Running scripts:
python3 -m mmdnn.conversion._script.convertToIR -f mxnet -n pretrained_model/model-r100-ii/model-symbol.json -w pretrained_model/model-r100-ii/model-0000.params -d . --inputShape 3,112,112
python3 -m mmdnn.conversion._script.IRToCode -f keras --IRModelPath ArcModel.pb --dstModelPath converted_ArcModel.py --IRWeightPath ArcModel.npy
python3 -m mmdnn.conversion.examples.keras.imagenet_test -n converted_ArcModel.py -w ArcModel.npy --dump mxnet_ArcModel.h5
When I run the third command I get the following error, could anyone help me with this error, please?