About error of aim

[chenqs1995]

I encountered the following error during operation, how to solve it?

Epoch[1] Complete. Time taken: 00:01:00
Engine run complete. Time taken 00:01:00
Engine run is terminating due to exception: 'Engine' object has no attribute 'aim'
Traceback (most recent call last):
File "/home/T3090U2/project/CQS/code/infrared/SAAI/train.py", line 219, in
train(cfg)
File "/home/T3090U2/project/CQS/code/infrared/SAAI/train.py", line 153, in train
engine.run(train_loader, max_epochs=cfg.num_epoch)
File "/home/T3090U2/anaconda3/envs/saai/lib/python3.10/site-packages/ignite/engine/engine.py", line 326, in run
self._handle_exception(e)
File "/home/T3090U2/anaconda3/envs/saai/lib/python3.10/site-packages/ignite/engine/engine.py", line 291, in _handle_exception
raise e
File "/home/T3090U2/anaconda3/envs/saai/lib/python3.10/site-packages/ignite/engine/engine.py", line 317, in run
self._fire_event(Events.EPOCH_COMPLETED)
File "/home/T3090U2/anaconda3/envs/saai/lib/python3.10/site-packages/ignite/engine/engine.py", line 226, in _fire_event
func(self, *(event_args + args), **kwargs)
File "/home/T3090U2/project/CQS/code/infrared/SAAI/engine/init.py", line 150, in epoch_completed_callback
mAP, r1, r5, _, _ = eval_sysu(q_feats, q_ids, q_cams, g_feats, g_ids, g_cams, g_img_paths, perm, mode='all', num_shots=1, aim=engine.aim)
AttributeError: 'Engine' object has no attribute 'aim'

[xiaoye-hhh]

Are you training or testing?

[xiaoye-hhh]

I run test.sh:

[chenqs1995]

when I am traing the epoch of 120

[xiaoye-hhh]

You can change as:
mAP, r1, r5, _, _ = eval_sysu(q_feats, q_ids, q_cams, g_feats, g_ids, g_cams, g_img_paths, perm, mode='all', num_shots=1, aim=False)

[chenqs1995]

Thank you, but that's not proof that the inference phase didn't use AIM

[xiaoye-hhh]

If you want to track the inference phase, you can run test.sh with your model weight. It will execute both simple inference and AIM.

[chenqs1995]

Thank you very much!

[yuting-coder]

You can change as: mAP, r1, r5, _, _ = eval_sysu(q_feats, q_ids, q_cams, g_feats, g_ids, g_cams, g_img_paths, perm, mode='all', num_shots=1, aim=False)

I encountered the following error during change this operation, how to solve it?

Epoch[1] Complete. Time taken: 00:01:00
Engine run complete. Time taken 00:01:11
Engine run is terminating due to exception: cannot reshape tensor of 0 elements into shape [0, -1] because the unspecified dimension size -1 can be any value and is ambiguous
Traceback (most recent call last):
File "D:\anaconda\envs\cumtlh\lib\site-packages\ignite\engine\engine.py", line 326, in run
self._handle_exception(e)
File "D:\anaconda\envs\cumtlh\lib\site-packages\ignite\engine\engine.py", line 291, in _handle_exception
raise e
File "D:\anaconda\envs\cumtlh\lib\site-packages\ignite\engine\engine.py", line 317, in run
self._fire_event(Events.EPOCH_COMPLETED)
File "D:\anaconda\envs\cumtlh\lib\site-packages\ignite\engine\engine.py", line 226, in fire_event
func(self, *(event_args + args), **kwargs)
File "F:\paper_code_YT\2024\01\SFE\engine_init.py", line 150, in epoch_completed_callback
mAP, r1, r5, _, _ = eval_sysu(q_feats, q_ids, q_cams, g_feats, g_ids, g_cams, g_img_paths, perm, mode='all', num_shots=1, aim=False)
File "F:\paper_code_YT\2024\01\SFE\utils\eval_sysu.py", line 133, in eval_sysu
dist_mat = pairwise_distance(query_feats, g_feat)
File "F:\paper_code_YT\2024\01\SFE\utils\eval_sysu.py", line 15, in pairwise_distance
y = y.view(n, -1)
RuntimeError: cannot reshape tensor of 0 elements into shape [0, -1] because the unspecified dimension size -1 can be any value and is ambiguous
python-BaseException

Process finished with exit code 1