You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Hello, I used your trained yolo model and found a missing chinese.names file,then I download ctw-trainval-01-of-26.tar,used prepare_train_data.py to generate chinese.names.
I ran prepare_test_data.py with all provided test data,got these
It seems like out of GPU memory, died threads output nothing.
per GPU memory ≈ 3.8 GB * num_thread (Line 74, eval.py) / TEST_NUM_GPU (line 30, settings.py)
Please modify these two variables.
You don't have to rerun all tests, just replace range(settings.TEST_SPLIT_NUM) (Line 74, eval.py) with you missing outputs [0, 1, 2, 5].
Hello, I used your trained yolo model and found a missing chinese.names file,then I download ctw-trainval-01-of-26.tar,used prepare_train_data.py to generate chinese.names.
I ran prepare_test_data.py with all provided test data,got these
Then about more than a dozen hours after I ran eval.py,I got these txt in /detection/products/result/
,it didn't generate complete chinese.x.txt,I wanna know why
The text was updated successfully, but these errors were encountered: