STEP icon indicating copy to clipboard operation
STEP copied to clipboard

STEP: Spatio-Temporal Progressive Learning for Video Action Detection. CVPR'19 (Oral)

Results 17 STEP issues
Sort by recently updated
recently updated
newest added

hi, thanks for you great works. I train my dataset, which has ten classes, fps =1, and I don't add --fp16 flag. max_iter=2 batch_size=2 But when I start training, there...

when I train my datasets,it always reports errors like: ValueError: Image path /STEP/datasets/ava/frames/D01/00922/ not Found because my datasets' each video only has 20 clips,which from 00902 to 00921,and fps equals...

Building I3D model... Building I3D head for global branch... Building I3D head for global branch... Building I3D head for global branch... Building I3D head for context branch... Datalist len: 0

Hello,i want to konw how to generate pre-defined proposals? I don't find some codes in generating the pre-defined proposals through the whole project.So,the pre-trained proposals are trained independently,and then feed...

RuntimeError: A tensor was not on the same device as the first tensor When i run the train.py ,i face up with this problem

when running python test.py it expects val.pkl and frames of data I have downloaded test videos (from ava_test.txt) But How can I generate pkl file? Generate_label.py code generates it it...

Hi there, First of all I would like to congratulate you for this great work and thank you for saharing the this awsome content publicly. I am trying to run...

Can you tell me the code which is used in UCF

I run demo 1st time in google colab and it's working, but when i try 2th time the demo is not working. This is what I got: ` Warning: If...