Skip to content

[DNL] executorch export faster-rcnn #8788

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
Draft
wants to merge 1 commit into
base: main
Choose a base branch
from
Draft

[DNL] executorch export faster-rcnn #8788

wants to merge 1 commit into from

Conversation

@yipjustin
Copy link

No description provided.

@pytorch-bot
Copy link

pytorch-bot bot commented Dec 6, 2024 •
edited
Loading

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/vision/8788

Note: Links to docs will display an error until the docs builds have been completed.

❌ 16 New Failures

As of commit 916ba03 with merge base 6279faa (image):

NEW FAILURES - The following jobs have failed:

This comment was automatically generated by Dr. CI and updates every 15 minutes.

@yipjustin
Copy link
Author 

    return guard_scalar(self.sym_num)

For more information, run with TORCH_LOGS="dynamic"
For extended logs when we create symbols, also add TORCHDYNAMO_EXTENDED_DEBUG_CREATE_SYMBOL="u1"
If you suspect the guard was triggered from C++, add TORCHDYNAMO_EXTENDED_DEBUG_CPP=1
For more debugging help, see https://docs.google.com/document/d/1HSuTTVvYH1pTew89Rtpeu84Ht3nQEFTYhAX3Ypa_xJs/edit?usp=sharing

User Stack (most recent call last):
  (snipped, see stack below for prefix)
  File "/home/yipjustin/et-arm/vision/torchvision/models/detection/generalized_rcnn.py", line 104, in forward
    proposals, proposal_losses = self.rpn(images, features, targets)
  File "/home/yipjustin/miniconda3/envs/vision/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1747, in _call_impl
    return forward_call(*args, **kwargs)
  File "/home/yipjustin/et-arm/vision/torchvision/models/detection/rpn.py", line 373, in forward
    boxes, scores = self.filter_proposals(proposals, objectness, images.image_sizes, num_anchors_per_level)
  File "/home/yipjustin/et-arm/vision/torchvision/models/detection/rpn.py", line 289, in filter_proposals
    keep = box_ops.batched_nms(boxes, scores, lvl, self.nms_thresh)
  File "/home/yipjustin/et-arm/vision/torchvision/ops/boxes.py", line 72, in batched_nms
    return _batched_nms_vanilla(boxes, scores, idxs, iou_threshold)
  File "/home/yipjustin/miniconda3/envs/vision/lib/python3.12/site-packages/torch/_dynamo/polyfills/__init__.py", line 133, in getattr_and_trace
    return fn(*args[2:], **kwargs)
  File "/home/yipjustin/et-arm/vision/torchvision/ops/boxes.py", line 109, in _batched_nms_vanilla
    for class_id in idxs:

For C++ stack trace, run with TORCHDYNAMO_EXTENDED_DEBUG_CPP=1
For more information about this error, see: https://pytorch.org/docs/main/generated/exportdb/index.html#constrain-as-size-example

from user code:
   File "/home/yipjustin/et-arm/vision/torchvision/models/detection/generalized_rcnn.py", line 104, in forward
    proposals, proposal_losses = self.rpn(images, features, targets)
  File "/home/yipjustin/miniconda3/envs/vision/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1747, in _call_impl
    return forward_call(*args, **kwargs)
  File "/home/yipjustin/et-arm/vision/torchvision/models/detection/rpn.py", line 373, in forward
    boxes, scores = self.filter_proposals(proposals, objectness, images.image_sizes, num_anchors_per_level)
  File "/home/yipjustin/et-arm/vision/torchvision/models/detection/rpn.py", line 289, in filter_proposals
    keep = box_ops.batched_nms(boxes, scores, lvl, self.nms_thresh)
  File "/home/yipjustin/et-arm/vision/torchvision/ops/boxes.py", line 72, in batched_nms
    return _batched_nms_vanilla(boxes, scores, idxs, iou_threshold)
  File "/home/yipjustin/miniconda3/envs/vision/lib/python3.12/site-packages/torch/_dynamo/polyfills/__init__.py", line 133, in getattr_and_trace
    return fn(*args[2:], **kwargs)
  File "/home/yipjustin/et-arm/vision/torchvision/ops/boxes.py", line 109, in _batched_nms_vanilla
    for class_id in idxs:

Set TORCH_LOGS="+dynamo" and TORCHDYNAMO_VERBOSE=1 for more information

digantdesai
digantdesai reviewed Dec 7, 2024
View reviewed changes
torchvision/ops/boxes.py
return _batched_nms_vanilla(boxes, scores, idxs, iou_threshold)
else:
return _batched_nms_coordinate_trick(boxes, scores, idxs, iou_threshold)
return _batched_nms_vanilla(boxes, scores, idxs, iou_threshold)
Copy link

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Can we do what Angela suggested here?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

@digantdesai digantdesai digantdesai left review comments

Assignees

No one assigned

Labels

cla signed

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

4 participants

@yipjustin @digantdesai @facebook-github-bot