We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
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
stage
python tools/train_net_mcd.py --config ./configs/sf/dut_hcmus.yaml OUTPUT_DIR outputs/dut_hcmus
issue
valid_map = scores_pre >= max(scores_pre) ValueError: max() arg is an empty sequence
cause
TEACHER MODEL output is None
From function threshold_bbox
1)scores_pre:tensor([], device='cuda:0', grad_fn=<IndexBackward>) 2)list_of_boxes[BoxList(num_boxes=0, image_width=599, image_height=512, mode=xyxy), BoxList(num_boxes=0, image_width=640, image_height=512, mode=xyxy)]
print(checkpoint["model"].get("generator_t")) is None from fcos_core/utils/checkpoint.py
how to fix this bug
# elif checkpoint["model"].get("model_backbone"): elif checkpoint["model"].get("generator_s") and not checkpoint["model"].get("generator_t"): self.logger.info("Loading the source only model v2 ==> ") load_state_dict(self.model["generator_t"], checkpoint["model"]["generator_s"]) load_state_dict(self.model["generator_s"], checkpoint["model"]["generator_s"]) load_state_dict(self.model["predictor_t"], checkpoint["model"]["predictor_s"]) load_state_dict(self.model["predictor_s"], checkpoint["model"]["predictor_s"])
The text was updated successfully, but these errors were encountered:
No branches or pull requests
stage
issue
valid_map = scores_pre >= max(scores_pre) ValueError: max() arg is an empty sequence
cause
TEACHER MODEL output is None
From function threshold_bbox
Code modification solution
how to fix this bug
The text was updated successfully, but these errors were encountered: