Issues
- 0
How the flo is normalized
#86 opened by Sunhailin1 - 2
extract feature
#79 opened by coaast123 - 0
How to use my own video to extract feature?
#83 opened by nick8592 - 2
Why there are no reduce_mean(logits) and 'Predictions' after 'Logits' like Deepmind's version?
#73 opened by whystopped - 0
How to input different size?
#85 opened by tingfengwanxiao - 2
How to get per frame embeddings given 1 video
#47 opened by yuanzhedong - 1
about json
#82 opened by Yuuuumie - 0
Confusion about image normalization
#84 opened by KhanhNgoDuy - 3
- 0
What's the in_channels's role?
#81 opened by Dev-ori - 3
number of frames in the input
#71 opened by ekosman - 0
replace_logits function??
#80 opened by coaast123 - 2
replace_logits function??
#70 opened by destousok - 1
- 0
- 2
How to get the prediction value or accuracy?We get only loss from here but we also need to know accuracy
#53 opened by aia39 - 1
What is the "vid" mean in the code?
#52 opened by DuoPeng-CVer - 1
- 0
Predict
#77 opened by 1774467982 - 4
Extract Features
#62 opened by River-mao - 0
Extracted Charades features
#76 opened by ByZ0e - 7
Evaluation problem
#34 opened by yuanmu97 - 0
- 2
extract features
#59 opened by Serendipity-LC - 0
any colab version?
#72 opened by ezzatmostafa96 - 3
Testing results of I3D model
#46 opened by TianyuLee - 0
About extract features
#69 opened by IVparagigm - 2
About Kinetics Pretrained
#56 opened by artest08 - 0
Pretraining on Sports-1m
#68 opened by NemioLipi - 1
About the overlapping part.
#67 opened by tanghaoyu258 - 0
mAP calculation
#64 opened by RT1991mj - 2
- 0
- 2
Why is the number of flow frames halved ?
#61 opened by MounirB - 0
Wrong assigning of dropout probability
#58 opened by sparsh-b - 2
- 2
Why do you reset the loss every tenth scheduler step, and step the scheduler and zero the gradients every 4th iteration while training on the Charades Dataset?
#44 opened by tym0027 - 2
I am using the pre-trained model for feature extraction. I am getting a 4D tensor output. What is mean by each dimensoion
#45 opened by dkrathi457 - 0
extract features of my own videos.
#50 opened by GayatriPurandharT - 0
How can I use pre-trained model to inference?
#51 opened by li829 - 0
- 2
Performance of your ported weights on Kinetics400 validation set (data preprocessing)
#41 opened by bryanyzhu - 2
Overlapping values of end and start
#39 opened by digbose92 - 0
- 1
Final end point
#36 opened by MahsaEhsanpour - 0
File "extract_features_trails.py", line 80, in run b,c,t,h,w = inputs.shape ValueError: not enough values to unpack (expected 5, got 1)
#42 opened by sparsh-b - 1
F.upsample(per_frame_logits)
#37 opened by ilkarman - 0
- 2
Loss function
#35 opened by XingyuJinTI - 0
Parameter spatial_squeeze bug
#33 opened by yuanmu97