[go: nahoru, domu]
Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Fix bug in onnx perchannel mode with ConvTranspose #3149

Merged
merged 4 commits into from
Jul 7, 2024
+84 −17
Merged

Fix bug in onnx perchannel mode with ConvTranspose #3149

Changes from 1 commit
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
b35c40c
Fix bug in onnx perchannel mode with ConvTranspose
quic-mtuttle Jul 1, 2024
11545e2
Fix unit test failure
quic-mtuttle Jul 2, 2024
370568a
Add perchannel depthwise convtranspose tests
quic-mtuttle Jul 2, 2024
a1fcfd1
Remove hardcoded path when getting model
quic-mtuttle Jul 3, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Prev Previous commit
Remove hardcoded path when getting model 
Signed-off-by: Michael Tuttle <quic_mtuttle@quicinc.com>
  • Loading branch information
@quic-mtuttle
quic-mtuttle committed Jul 5, 2024
commit a1fcfd11f12d3cf4b1dc388913f7ff4f66d9804c
55 changes: 29 additions & 26 deletions TrainingExtensions/onnx/test/python/models/models_for_tests.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -41,6 +41,7 @@
from typing import Dict, List

import os
import tempfile
import torch.nn.functional as F
from torch import nn as nn
from torchvision.ops import roi_align
Expand Down Expand Up @@ -1112,35 +1113,37 @@ def multi_output_model():
return model

def transposed_conv_model():
x = torch.randn(10, 10, 4, 4, requires_grad=True)
model = TransposedConvModel()

# Export the model
torch.onnx.export(model, # model being run
x, # model input (or a tuple for multiple inputs)
"./model_transposed_conv.onnx", # where to save the model (can be a file or file-like object)
export_params=True, # store the trained parameter weights inside the model file
opset_version=12, # the ONNX version to export the model to
do_constant_folding=True, # whether to execute constant folding for optimization
input_names=['input'], # the model's input names
output_names=['output'])
model = ONNXModel(load_model('./model_transposed_conv.onnx'))
with tempfile.TemporaryDirectory() as save_dir:
x = torch.randn(10, 10, 4, 4, requires_grad=True)
model = TransposedConvModel()
save_path = os.path.join(save_dir, "model_transposed_conv.onnx")
# Export the model
torch.onnx.export(model, # model being run
x, # model input (or a tuple for multiple inputs)
save_path, # where to save the model (can be a file or file-like object)
export_params=True, # store the trained parameter weights inside the model file
opset_version=12, # the ONNX version to export the model to
do_constant_folding=True, # whether to execute constant folding for optimization
input_names=['input'], # the model's input names
output_names=['output'])
model = ONNXModel(load_model(save_path))
return model

def depthwise_transposed_conv_model():
x = torch.randn(10, 10, 4, 4, requires_grad=True)
model = DepthwiseTransposedConvModel()

# Export the model
torch.onnx.export(model, # model being run
x, # model input (or a tuple for multiple inputs)
"./model_transposed_conv.onnx", # where to save the model (can be a file or file-like object)
export_params=True, # store the trained parameter weights inside the model file
opset_version=12, # the ONNX version to export the model to
do_constant_folding=True, # whether to execute constant folding for optimization
input_names=['input'], # the model's input names
output_names=['output'])
model = ONNXModel(load_model('./model_transposed_conv.onnx'))
with tempfile.TemporaryDirectory() as save_dir:
x = torch.randn(10, 10, 4, 4, requires_grad=True)
model = DepthwiseTransposedConvModel()
save_path = os.path.join(save_dir, "model_transposed_conv.onnx")
# Export the model
torch.onnx.export(model, # model being run
x, # model input (or a tuple for multiple inputs)
save_path, # where to save the model (can be a file or file-like object)
export_params=True, # store the trained parameter weights inside the model file
opset_version=12, # the ONNX version to export the model to
do_constant_folding=True, # whether to execute constant folding for optimization
input_names=['input'], # the model's input names
output_names=['output'])
model = ONNXModel(load_model(save_path))
return model


Expand Down
Loading