search

microsoft / MMdnn

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

Caffe to Tensorflow model ,error! #133

Open FakerYFX opened 6 years ago

FakerYFX commented 6 years ago

caffemodel for ctpn deploy.prototxt deploy.txt

error information: I0331 08:47:32.099702 7859 net.cpp:228] relu1_1 does not need backward computation. I0331 08:47:32.099707 7859 net.cpp:228] conv1_1 does not need backward computation. I0331 08:47:32.099712 7859 net.cpp:228] input does not need backward computation. I0331 08:47:32.099717 7859 net.cpp:270] This network produces output rois I0331 08:47:32.099723 7859 net.cpp:270] This network produces output scores I0331 08:47:32.099759 7859 net.cpp:283] Network initialization done. Traceback (most recent call last): File "/usr/lib/python2.7/runpy.py", line 162, in _run_module_as_main "main", fname, loader, pkg_name) File "/usr/lib/python2.7/runpy.py", line 72, in _run_code exec code in run_globals File "/usr/local/lib/python2.7/dist-packages/mmdnn/conversion/_script/convertToIR.py", line 164, in _main() File "/usr/local/lib/python2.7/dist-packages/mmdnn/conversion/_script/convertToIR.py", line 159, in _main ret = _convert(args) File "/usr/local/lib/python2.7/dist-packages/mmdnn/conversion/_script/convertToIR.py", line 9, in _convert transformer = CaffeTransformer(args.network, args.weights, "tensorflow", args.inputShape, phase = args.caffePhase) File "/usr/local/lib/python2.7/dist-packages/mmdnn/conversion/caffe/transformer.py", line 316, in init graph = GraphBuilder(def_path, self.input_shape, self.is_train_proto, phase).build() File "/usr/local/lib/python2.7/dist-packages/mmdnn/conversion/caffe/graph.py", line 447, in build graph.compute_output_shapes(self.model) File "/usr/local/lib/python2.7/dist-packages/mmdnn/conversion/caffe/graph.py", line 266, in compute_output_shapes node.output_shape = TensorShape(*NodeKind.compute_output_shape(node)) File "/usr/local/lib/python2.7/dist-packages/mmdnn/conversion/caffe/graph.py", line 126, in compute_output_shape return LAYER_DESCRIPTORSnode.kind KeyError: None

TobeyQin commented 6 years ago

Hi, which caffe model you used? could you provide the caffe model files (both .caffemodel and .prototxt files)?

FakerYFX commented 6 years ago

@TobeyQin ok you can download from this site: https://pan.baidu.com/s/1kEt8bhDOY-rsceISEsKmDg thank you very much , look forward to your review.

FakerYFX commented 6 years ago

@kitstar @TobeyQin @namizzz Can this model change from caffe to tensorflow?