[GitHub] [incubator-tvm] CoinCheung opened a new issue #4261: DepthWise Transposed Conv error

[GitBox <gi...@apache.org>]

CoinCheung opened a new issue #4261: DepthWise Transposed Conv error
URL: https://github.com/apache/incubator-tvm/issues/4261
 
 
   A short version of my code is: 
   ```python
   import onnx
   import torch
   import torch.nn as nn
   import tvm
   import tvm.relay as relay
   
   
   
   class UpSample16(nn.Module):
       def __init__(self, in_chan):
           super(UpSample16, self).__init__()
           self.conv1 = nn.ConvTranspose2d(in_chan,
                              in_chan,
                              kernel_size=(32, 1),
                              stride=(16, 1),
                              padding=(8, 0),
                              groups=in_chan,
                              bias=False)
           self.conv2 = nn.ConvTranspose2d(in_chan,
                              in_chan,
                              kernel_size=(1, 32),
                              stride=(1, 16),
                              padding=(0, 8),
                              groups=in_chan,
                              bias=False)
   
       def forward(self, x):
           x = self.conv1(x)
           x = self.conv2(x)
           return x
   
   
   input_shape = (1, 3, 768, 768)
   shape_dict = {'0': input_shape}
   mdpth = './tmp/play.onnx'
   opt_level = 3
   target = 'cuda'
   
   print('export')
   dummy_in = torch.randn(*input_shape)
   model = UpSample16(3)
   torch.onnx.export(model, dummy_in, mdpth, opset_version=11)
   
   print('load')
   model = onnx.load(mdpth)
   print('compile')
   mod, params = relay.frontend.from_onnx(model, shape_dict, dtype='float32', opset=11)
   with relay.build_config(opt_level=opt_level):
       intrp = relay.build_module.create_executor('graph', mod, tvm.gpu(), target)
   
   
   print('inference')
   import cv2
   import numpy as np
   impth = '000000000139.jpg'
   im = cv2.imread(impth)
   im = cv2.resize(im, (input_shape[2:][::-1]))
   im = (im - np.array([123, 117, 104])) / np.array([58.4, 57.1, 57.4])
   im = im.transpose((2, 0, 1))[np.newaxis, :]
   
   out = intrp.evaluate()(tvm.nd.array(im.astype('float32')), **params).asnumpy()
   ```
   
   There seems to be two problems: 
   1) when the target is `cuda`, there will be core dump error. When the target is `llvm`, there will not be problems until "inference".
   2) If I set the `groups` of the `nn.ConvTranspose2d` to be 1, there will be no problem(llvm target). However, when I set `groups=in_chan`, which means "depthwise-conv-transpose2d", there will be problem with compiling.
   
   Please take a look at this, if it is brought by my bad usage of tvm, please correct me. Thanks a lot :)

----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
 
For queries about this service, please contact Infrastructure at:
users@infra.apache.org


With regards,
Apache Git Services