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
Tensorflow to Mxnet:ValueError: Need to provide the output node of Tensorflow model. #462
Traceback (most recent call last):
File "/home/datawow/miniconda2/envs/deep_learning3/bin/mmconvert", line 11, in
sys.exit(_main())
File "/home/datawow/miniconda2/envs/deep_learning3/lib/python3.6/site-packages/mmdnn/conversion/_script/convert.py", line 102, in _main
ret = convertToIR._convert(ir_args)
File "/home/datawow/miniconda2/envs/deep_learning3/lib/python3.6/site-packages/mmdnn/conversion/_script/convertToIR.py", line 51, in _convert
raise ValueError("Need to provide the output node of Tensorflow model.")
ValueError: Need to provide the output node of Tensorflow model.
Platform (like ubuntu 16.04/win10): ubuntu 16.04
Python version: 3.6.6
Source framework with version (like Tensorflow 1.4.1 with GPU):Tensorflow 1.8.0 with GPU
Destination framework with version (like CNTK 2.3 with GPU): Mxnet (anyversion) with GPU
Pre-trained model path (webpath or webdisk path): https://github.com/mdietrichstein/tensorflow-open_nsfw
Running scripts: mmconvert --srcFramework tensorflow --IRModelPath open_nsfw.pb --dstModelPath ../../classify_nsfw.py -df mxnet --IRWeightPath ../../data/open_nsfw-weights.npy -om mxnet_nxfw_v3-0000.params
basically, i have save the graph from tensorflow-nsfw, there've existed these following file
checkpoint
open_nsfw.ckpt.data-00000-of-00001
open_nsfw.ckpt.meta
optimized_open_nsfw.pb frozen_open_nsfw.pb
open_nsfw.ckpt.index
open_nsfw.pb
error found
Traceback (most recent call last): File "/home/datawow/miniconda2/envs/deep_learning3/bin/mmconvert", line 11, in
sys.exit(_main())
File "/home/datawow/miniconda2/envs/deep_learning3/lib/python3.6/site-packages/mmdnn/conversion/_script/convert.py", line 102, in _main
ret = convertToIR._convert(ir_args)
File "/home/datawow/miniconda2/envs/deep_learning3/lib/python3.6/site-packages/mmdnn/conversion/_script/convertToIR.py", line 51, in _convert
raise ValueError("Need to provide the output node of Tensorflow model.")
ValueError: Need to provide the output node of Tensorflow model.