joslefaure/HIT
Official Implementation of our WACV2023 paper: “Holistic Interaction Transformer Network for Action Detection”
Python
Issues
- 0
About Key Frames
#55 opened by grannycola - 3
CUDA error
#54 opened by hhh804 - 1
error with test_net.py
#53 opened by hhh804 - 1
“No such file or directory: 'data/jhmdb/annotations/jhmdb_train_gt_min.json'”
#52 opened by LIUHENGSHUAI - 1
No such file or directory: 'data/jhmdb/annotations/jhmdb_train_gt_min.json'
#51 opened by LIUHENGSHUAI - 2
Retrieve result_ava.csv for inference
#48 opened by 12sakura - 2
- 2
Optimal versions for libs
#49 opened by grannycola - 8
ucf-24 code
#15 opened by hongminglin08 - 2
PreTrained model on Multi Sports Dataset
#29 opened by girmaji08 - 1
size mismatch for my video
#47 opened by fengjingchehu - 1
- 1
ImportError
#46 opened by fengjingchehu - 3
- 8
Some questions regarding the results
#35 opened by ZWXCV - 3
the data of UCF101-24
#11 opened by yan-ctrl - 2
Loss function
#43 opened by ddddqt - 2
- 1
TypeError: conv3d() received an invalid combination of arguments error on training and inference
#44 opened by Chris009527 - 4
Could MultiSports Dataset be tranformed to like ucf101-24 dataset or JHMDB dataset?
#27 opened by Eurususu - 5
Error while training the model
#7 opened by piyushandilya - 3
Problems encountered during training
#32 opened by ZWXCV - 4
No hit._custom_cuda_ext was found
#37 opened by ddddqt - 3
ImportError
#38 opened by fengjingchehu - 1
demo
#42 opened by fengjingchehu - 1
Misror error in window on pip install-e
#41 opened by ddddqt - 3
model is missing!!
#26 opened by Eurususu - 2
J-HMDB Model link is not working
#40 opened by HaithemH - 1
Distributed training problem
#39 opened by ddddqt - 2
As model is missing so how should we run it
#28 opened by johnsmith228 - 3
Broken model links
#23 opened by tsunehiko - 1
Some questions about the results
#36 opened by ZWXCV - 3
get frame mAP error
#34 opened by ZWXCV - 1
- 2
Calculate frame mAP
#33 opened by ZWXCV - 2
- 2
Backward Error
#24 opened by tsunehiko - 1
How to generate video visualization results?
#12 opened by SileiZhao - 1
parameter setting
#19 opened by hongminglin08 - 1
- 1
- 3
- 1
Data Preparation of ava dataset
#22 opened by hongminglin08 - 13
Some problem about UCF101-24 annotations
#8 opened by CKK-coder - 2
AssertionError: The shape of tensor class logits doesn't match total number of action classes.
#18 opened by hongminglin08 - 0
UCF101-24 dataset
#17 opened by yan-ctrl - 12
The code about video map
#13 opened by CKK-coder - 28
how to train AVA datasets
#6 opened by yan-ctrl - 4
get_ Keypoints?
#14 opened by yan-ctrl - 9
error when install hit
#5 opened by ccx2022