pytorch2keras
pytorch2keras copied to clipboard
gmalivenko
PyTorch to Keras model convertor
Layer (type) Output Shape Param # ================================================================= input_0 (InputLayer) [(None, 28, 28, 1)] 0 _________________________________________________________________ 27_pad (ZeroPadding2D) (None, 30, 30, 1) 0 _________________________________________________________________ the format is [()] , is it...
**Describe the bug** Trying to convert a siamese Resnet18 model from Pytorch to Tensorflow but I get the following error in tf.loadModel > tfjs@latest:2 Uncaught (in promise) Error: Provided weight...
**Describe the bug** `TypeError: pytorch_to_keras() got an unexpected keyword argument 'names'` **To Reproduce** I've tried to add in requirements.txt either `pytorch2keras` or `git+https://github.com/nerox8664/pytorch2keras`, but I've got the same error. __Snippet...
I've added batchnorm layer to your dummy example and it crushed **the code:** ``` from keras import backend as K K.set_image_data_format('channels_first') from pytorch2keras.converter import pytorch_to_keras import torch import torch.nn as...
**Describe the bug** DEBUG:onnx2keras:Converting ONNX operation DEBUG:onnx2keras:type: Cast DEBUG:onnx2keras:node_name: 353 DEBUG:onnx2keras:node_params: {'to': 1, 'change_ordering': True, 'name_policy': 'short'} DEBUG:onnx2keras:... DEBUG:onnx2keras:Check if all inputs are available: DEBUG:onnx2keras:Check input 0 (name 351). DEBUG:onnx2keras:......
**Describe the bug** thanks for your code I tried to convert official PyTorch centernet, the backbone is hourglass, got this error. **Logs** ``` DEBUG:onnx2keras:Check input 1 (name 1194). DEBUG:onnx2keras:... found...
**Describe the bug** Linear followed by a view leads to incorrect result, tensorflowjs complains shape mismatch [NULL, output_size]. changing ` reshape = keras.layers.Reshape([-1], name=tf_name)` to match the input shape seems...
**Describe the bug** Guide under Tensorflow.js heading needs an update, 'names' flag changed to 'name_policy ' according to latest commit? Under supported layers heading, ConvTrsnpose2d==ConvTranspose2d?
**Describe the bug** When i try to convert the pytorch model to keras model, I get an error saying "Key error: 'Slice' **To Reproduce** with_gpu = False net = vgg.VGG('VGG19')...
