MMdnn
MMdnn copied to clipboard
microsoft
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, PyT...
Hello, @kitstar & @rainLiuplus I followed the steps to convert yolov3 to keras using mmdnn. All the steps worked , however it failed in the inference at detecting the dog...
There are several errors when the TF parser working on NLP network pb. Does the NLP network supported for parsing？
Platform (like ubuntu 16.04/win10): Python version: 3.6 Source framework with version: Pytorch 1.5.0 Destination framework with version: Tensorflow 1.15.2 Pre-trained model path: https://drive.google.com/drive/folders/13UW3Qw_kYxxKrICOu7dQykmq_aBJHecT?usp=sharing Running scripts: https://gist.github.com/kyhoolee/1a9ae7b6f7d654e2c41d16959c200eb3 Tflite models work well...
I found that there are some `shape_not_implemented` in `LAYER_DESCRIPTORS` of [MMdnn/mmdnn/conversion/caffe/graph.py](https://github.com/Microsoft/MMdnn/blob/master/mmdnn/conversion/caffe/graph.py) , and this will cause exceptions as title. How to solve these? Platform: Red Hat 4.8.5-11 with 4 Nvidia...
Traceback (most recent call last): File "e:\anaconda3\envs\tensorflow\lib\runpy.py", line 193, in _run_module_as_main "__main__", mod_spec) File "e:\anaconda3\envs\tensorflow\lib\runpy.py", line 85, in _run_code exec(code, run_globals) File "E:\Anaconda3\envs\tensorflow\Scripts\mmconvert.exe\__main__.py", line 7, in File "e:\anaconda3\envs\tensorflow\lib\site-packages\mmdnn\conversion\_script\convert.py", line 102,...
tensorflow convert caffe: from ._conv import register_converters as _register_converters Parse file [model.ckpt-61236.meta] with binary format successfully. Tensorflow model file [model.ckpt-61236.meta] loaded successfully. Tensorflow checkpoint file [model.ckpt-61236] loaded successfully. [435] variables...
Platform (like ubuntu 16.04/win10): Ubuntu 18.04 Python version: 3.6/3.7 Source framework with version (like Tensorflow 1.4.1 with GPU): TF1.15/TF2.2.0 Destination framework with version (like CNTK 2.3 with GPU): Caffe Pre-trained...
When I use mmdnn to convert TF to caffe, I met these problems: TensorflowEmitter has not supported operator [Switch] with name [conv0_1/BatchNorm/cond/Switch]. TensorflowEmitter has not supported operator [Switch] with name...
Platform (like ubuntu 16.04/win10): ` ubuntu 16.04 ` Python version: ` python 2.7 ` Source framework with version (like Tensorflow 1.4.1 with GPU): ` Tensorflow 1.12 ` Destination framework with...
Platform: archlinux Python version: 3.7.2 Source framework with version: Tensorflow 1.13 with GPU Destination framework with version: onnx Pre-trained model path (webpath or webdisk path): [test.pb.zip](https://github.com/Microsoft/MMdnn/files/3051903/test.pb.zip) Running scripts: ```mmconvert -sf...
