denise-k opened a new issue #8611:
URL: https://github.com/apache/tvm/issues/8611


   # Context
   
   CI is taking a while (see #8552 and 
[build#1384](https://ci.tlcpack.ai/job/tvm/job/main/1384/testReport/)), and I 
am tracking short-term fixes to alleviate this
   
   # Summary of the issue
   
   `test_roi_align` is pretty well tested at the relay and topi level as well 
as the frontends. However, the ONNX roi align tests take [7 
minutes](https://ci.tlcpack.ai/job/tvm/job/main/1384/testReport/cython.tests.python.frontend.onnx/test_forward/Integration_Test___frontend__GPU___test_roi_align)
 vs [just 7 seconds on 
pytorch](https://ci.tlcpack.ai/job/tvm/job/main/1384/testReport/cython.tests.python.frontend.pytorch/test_forward/Integration_Test___frontend__GPU___test_forward_roi_align).
   
   Part of this is because there are more tests on onnx with larger shapes.
   
   ```
   # onnx (7min runtime)
       verify_roi_align((1, 4, 16, 16), 32, 7, 7, sampling_ratio=0, 
spatial_scale=1.0)
       verify_roi_align((4, 4, 16, 32), 32, 7, 7, sampling_ratio=0, 
spatial_scale=1.0)
       verify_roi_align((1, 8, 16, 16), 32, 7, 7, sampling_ratio=0, 
spatial_scale=1.0)
       verify_roi_align((1, 4, 8, 8), 32, 7, 7, sampling_ratio=0, 
spatial_scale=1.0)
       verify_roi_align((1, 4, 16, 16), 16, 5, 7, sampling_ratio=0, 
spatial_scale=1.0)
       verify_roi_align((1, 4, 16, 12), 8, 7, 3, sampling_ratio=0, 
spatial_scale=1.0)
       verify_roi_align((1, 4, 16, 16), 32, 7, 7, sampling_ratio=0, 
spatial_scale=0.5)
       verify_roi_align((3, 4, 12, 16), 32, 7, 7, sampling_ratio=0, 
spatial_scale=1.5)
       verify_roi_align((5, 4, 16, 14), 32, 7, 7, sampling_ratio=1, 
spatial_scale=1.0)
       verify_roi_align((1, 4, 16, 16), 32, 7, 7, sampling_ratio=2, 
spatial_scale=1.0)
   ```
   
   ```
   # pytorch (7sec runtime)
       verify_model(ROIAlign(7), [in_data, in_boxes])
       verify_model(ROIAlign((10, 10), 0.7, 5), [in_data, in_boxes])
       verify_model(ROIAlign(15, 0.9, 3), [in_data, in_boxes])
   ```
   
   Perhaps secondarily, the ONNX frontend is just slower at lowering ROI align.
   
   # Suggested actions
   * Reduce the number of ROI align tests on the ONNX frontend. It's already 
pretty well covered at each level of the stack
   * Minimize the input/output shapes of each ROI align test case 


-- 
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.

To unsubscribe, e-mail: [email protected]

For queries about this service, please contact Infrastructure at:
[email protected]


Reply via email to