search

scwangdyd / zero_shot_hoi

Discovering human interaction with novel objects via zero-shot learning, CVPR, 2020
MIT License
40 stars 6 forks source link

boxes AssertionError #9

Open xxxzhi opened 3 years ago

xxxzhi commented 3 years ago

python train_net.py --num-gpus 1 --config-file configs/HICO-DET/interaction_R_50_FPN.yaml OUTPUT_DIR ./output/HICO_interaction

ERROR [09/08 16:54:57 d2.engine.train_loop]: Exception during training: Traceback (most recent call last):
File "/opt/data/private/Code/detectron2/detectron2/engine/train_loop.py", line 141, in train self.run_step()
File "/opt/data/private/Code/detectron2/detectron2/engine/train_loop.py", line 227, in run_step loss_dict = self.model(data)
File "/usr/local/lib/python3.6/dist-packages/torch/nn/modules/module.py", line 532, in call result = self.forward(*input, *kwargs)
File "/opt/data/private/Code/zero_shot_hoi/lib/arch.py", line 127, in forward
proposals, proposal_losses = self.proposal_generator(images, features, gt_instances) File "/usr/local/lib/python3.6/dist-packages/torch/nn/modules/module.py", line 532, in call result = self.forward(input, *kwargs)
File "/opt/data/private/Code/zero_shot_hoi/lib/modeling/horpn.py", line 369, in forward
losses = {k: v self.loss_weight for k, v in outputs.losses().items()} File "/opt/data/private/Code/zero_shot_hoi/lib/modeling/horpn_outputs.py", line 509, in losses gts = self._get_ground_truth()
File "/opt/data/private/Code/zero_shot_hoi/lib/modeling/horpn_outputs.py", line 389, in _get_ground_truth anchors = [Boxes.cat(anchors_i) for anchors_i in self.anchors]
File "/opt/data/private/Code/zero_shot_hoi/lib/modeling/horpn_outputs.py", line 389, in anchors = [Boxes.cat(anchors_i) for anchors_i in self.anchors]
File "/opt/data/private/Code/detectron2/detectron2/structures/boxes.py", line 291, in cat
assert isinstance(boxes_list, (list, tuple)) AssertionError

byrsongyuxin commented 2 years ago

Have you solved this problem?