MMdnn

MMdnn copied to clipboard

caffe to tensorflow: convert one depthwise op with group=36 from caffe to tensorflow's 36 depthwise ops

2

convert one depthwise op with group=36 from caffe to tensorflow's 36 depthwise ops ## caffe model  ## converted tensorflow 

ysh329

Tensorflow has not supported operator [Less] with name [image_padding/pad_to_bounding_box/assert_positive/assert_less/Less].

1

Platform (like ubuntu 16.04/win10): ubuntu Python version: 3.6 Source framework with version (like Tensorflow 1.4.1 with GPU): Tensorflow 1.10 with GPU Destination framework with version (like CNTK 2.3 with GPU):...

merria28

when will caffe_emitter support output of layer with more than 1 blob?

1

Platform (like ubuntu 16.04/win10): ubuntu 16.04 Python version: python 3.5.2 Source framework with version (like Tensorflow 1.4.1 with GPU): pytorch or tensorflow Destination framework with version (like CNTK 2.3 with...

hnuhchen

Error when using the converted pytorch model(mxnet->IR->pytorch)

3

Platform (ubuntu 1４.04): Python version:　3.5 Source framework with version (like mxnet 1.0.0 with GPU): Destination framework with version (like pytorch 0.4.0 with GPU): Pre-trained model path (LResNet34E , https://github.com/Microsoft/MMdnn/blob/72529a9f6b17f7298eacb7b2a0dae6dc5b9ce408/mmdnn/conversion/pytorch/README.md):...

MengDebin18

Error when using the converted pytorch model

6

I get the following error when processing data through pytorch model. Converted from mxnet to pytorch >NameError: global name '_KitModel__weights_dict' is not defined

kar1989

Convert mxnet model to IR, name not found in symbol.list_arguments()

7

Platform (like ubuntu 16.04/win10): `win10` Python version: `3.6.6` Source framework with version (like Tensorflow 1.4.1 with GPU): `mxnet 1.3.0` Destination framework with version (like CNTK 2.3 with GPU): `tensorflow 1.10.0...

ningningG

IndexError: list index (0) out of range

4

Python version: 3.7 Source framework with version (like Tensorflow 1.4.1 with GPU): Tensorflow 1.15 Destination framework with version (like CNTK 2.3 with GPU): Pytorch Pre-trained model path (webpath or webdisk...

alex96295

mxnet pareser does not support upsample op

5

Platform (like ubuntu 16.04/win10): **ubuntu16.04** Python version: **3.7** Source framework with version (like Tensorflow 1.4.1 with GPU): **mxnet** Destination framework with version (like CNTK 2.3 with GPU): **tensorflow 1.8 with...

memoiry

Tensorflow to IR rep not working - `TensorflowEmitter has not supported operator [BiasAdd] with name [dense/BiasAdd].`

1

Platform (like ubuntu 16.04/win10): kubuntu 18.10 Python version: 3.6 Source framework with version (like Tensorflow 1.4.1 with GPU): tensorflow 1.12.0 with CPU Destination framework with version (like CNTK 2.3 with...

aruna-ram

LSTM tensorflow to caffe error

1

Platform (like ubuntu 16.04/win10):ubuntu 16.04 Python version: 3.6 Source framework with version (like Tensorflow 1.4.1 with GPU): tensorflow Destination framework with version (like CNTK 2.3 with GPU): caffe Pre-trained model...

yulinhuyang