Grigory Malivenko

Conv2DTranspose problem

1

I have 2 problems with Conv2DTranspose layer: 1. When I try to create model with `gpu: false` an error with shapes occurs: ``` Error: Mismatched array shapes for matrix product...

Implement: - [ ] LSTM - [ ] GRU

Implement recurrent layers

1

Add support of recurrent layers to the converter: - [ ] GRU - [ ] LSTM

Hello! There is a one more issue with converter: ``` Traceback (most recent call last): File "convert_keras.py", line 114, in main() File "convert_keras.py", line 64, in main graph = converter.convert(model)...

Hello! I've a problem with convertation my model to the webdnn format: ``` Traceback (most recent call last): File "convert_to_dnn.py", line 31, in graph = PyTorchConverter().convert(model, dummy_input) File "/usr/lib/python3.6/site-packages/webdnn/frontend/pytorch/converter.py", line...

Hello. I added links to these model converters: * [pytorch2keras](https://github.com/nerox8664/pytorch2keras) - Convert PyTorch models to Keras (with TensorFlow backend) format * [gluon2keras](https://github.com/nerox8664/gluon2keras) - Convert Gluon models to Keras (with TensorFlow...

Hello. I added links to these model converters: * [pytorch2keras](https://github.com/nerox8664/pytorch2keras) - Convert PyTorch models to Keras (with TensorFlow backend) format * [gluon2keras](https://github.com/nerox8664/gluon2keras) - Convert Gluon models to Keras (with TensorFlow...