You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@tvm.apache.org by GitBox <gi...@apache.org> on 2019/12/23 04:30:44 UTC
[GitHub] [incubator-tvm] jwfromm commented on a change in pull request
#4566: [Relay/Topi][Op] Added native DepthToSpace and SpaceToDepth Operators
jwfromm commented on a change in pull request #4566: [Relay/Topi][Op] Added native DepthToSpace and SpaceToDepth Operators
URL: https://github.com/apache/incubator-tvm/pull/4566#discussion_r360763434
##########
File path: python/tvm/relay/frontend/onnx.py
##########
@@ -539,35 +539,7 @@ class DepthToSpace(OnnxOpConverter):
def _impl_v11(cls, inputs, attr, params):
block_size = int(attr['blocksize'])
- mode = attr.get("mode", "DCR")
-
- # handle NCHW layout
- indata = infer_value_simulated(inputs[0], params)
- in_n, in_c, in_h, in_w = indata.shape
-
- # reshape to proper output
- new_c = int(in_c / (block_size * block_size))
- new_h = in_h * block_size
- new_w = in_w * block_size
- newshape = (in_n, new_c, new_h, new_w)
-
- if mode == "DCR":
- # expand input to larger dimension.
- expanded = _op.reshape(inputs[0],
- newshape=(in_n, block_size, block_size, new_c, in_h, in_w))
- # reorder to expand spatial blocks.
- transposed = _op.transpose(expanded, axes=(0, 3, 4, 1, 5, 2))
-
- else: # CRD mode
- # expand input to larger dimension.
- expanded = _op.reshape(inputs[0],
- newshape=(in_n, new_c, block_size, block_size, in_h, in_w))
- # reorder to expand spatial blocks.
- transposed = _op.transpose(expanded, axes=(0, 1, 4, 2, 5, 3))
-
- return AttrCvt(op_name="reshape",
- extras={'newshape': newshape},
- ignores=['mode', 'blocksize'])([transposed], attr)
+ return _op.nn.depth_to_space(inputs[0], block_size)
Review comment:
Thank you for the correction. I never quite understood the use of CDR mode, but now that I know its how PyTorch handles depthtospace it makes much more sense. I added a mode argument to the depth_to_space operator that allows switching the channel indexing. Also added the proper mode parsing in the ones frontend.
----------------------------------------------------------------
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