FrozenGene commented on a change in pull request #6381:
URL: https://github.com/apache/incubator-tvm/pull/6381#discussion_r482795512
##########
File path: python/tvm/relay/frontend/tflite.py
##########
@@ -2696,11 +2696,11 @@ def convert_transpose_conv(self, op):
# Input (data) Tensor. NHWC layout
input_tensor = input_tensors[2]
- _, _, _, input_c = input_tensor.tensor.ShapeAsNumpy()
+ input_shape = input_tensor.tensor.ShapeAsNumpy()
Review comment:
Don't you think we create `_, input_h, input_w, input_c` is more make
sense if you want to use `input_shape[1] / input_shape[2] / input_shape[3]`?
##########
File path: python/tvm/relay/frontend/tflite.py
##########
@@ -2742,13 +2742,16 @@ def convert_transpose_conv(self, op):
assert out_channels == output_shape_value[3], \
"Output channel in the filter should match to channel in the
output_shape"
- # TF frontend supports 'SAME' padding for kernel 1x1 only. Lets do the
same here
if padding == Padding.SAME:
- assert (kernel_h, kernel_w) == (1, 1), \
- "SAME padding is supported for kernel (1,1) only"
+ pad_top, pad_bottom = get_pad_value(input_shape[1], kernel_h,
stride_h)
+ pad_left, pad_right = get_pad_value(input_shape[2], kernel_w,
stride_w)
+ pads = (pad_top, pad_left, pad_bottom, pad_right)
Review comment:
better name `pads` to `padding`
----------------------------------------------------------------
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:
[email protected]
