masahi commented on a change in pull request #7137:
URL: https://github.com/apache/tvm/pull/7137#discussion_r548408319
##########
File path: tests/python/frontend/pytorch/test_object_detection.py
##########
@@ -70,7 +71,7 @@ def generate_jit_model(index):
]
model_func = model_funcs[index]
- model = TraceWrapper(model_func(pretrained=True))
+ model = TraceWrapper(model_func(pretrained=True,
rpn_pre_nms_top_n_test=200))
Review comment:
I think the default parameter 1000 they picked is fairly conservative.
This means for each level in the feature pyramid, of which there is 5 if we use
resnet 50 backbone, we get maximum of 1000 x 5 boxes as input to RPN. They have
another parameter `rpn_post_nms_top_n_test`, which is like topk applied after
NMS. This value is also by default 1000 and it is not per class unlike
`rpn_pre_nms_top_n_test`. This means we always have 1000 boxes after NMS
regardless of `rpn_pre_nms_top_n_test`.
----------------------------------------------------------------
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]
