Comments (2)
For JHMDB Inference
-
here should be
from models.tuber_jhmdb import build_model
-
modify
tubelet-transformer/models/tuber_jhmdb.py
Line 20 in f610c97
as
from models.transformer.transformer import build_transformer
-
Needs 'JHMDB-GT.pkl'
Found the script to download according to the direction in dataset part.
Update:- nope, that link only has Annotations, Frames and OF, but not with the file above.
- Get the pickle file from MOC
-
Provided pretrained DETR model has different embedded query input dimensions as the model built and pretrained JHMDB model
modify the loading detr part according to the built model embed_query input dimensions to avoid this problem
tubelet-transformer/utils/model_utils.py
Line 25 in f610c97
pretrained_dict.update({k: v[:query_size]})
if query_size == model.module.query_embed.weight.shape[0]: continue
if v.shape[0] < model.module.query_embed.weight.shape[0]: # In case the pretrained model does not align
query_embed_zeros=torch.zeros(model.module.query_embed.weight.shape)
pretrained_dict.update({k: query_embed_zeros})
else:
pretrained_dict.update({k: v[:model.module.query_embed.weight.shape[0]]})
Got different mAP as the table shows
per_class [0.96529908 0.4870422 0.81740977 0.64671594 0.99981187 0.48678173
0.72522214 0.70157535 0.99132313 0.99332738 0.92539198 0.63780982
0.6607778 0.89695387 0.78694818 0.42965094 0.26324953 0.94429166
0.27346689 0.68134081 0.87238637 nan nan nan]
{'PascalBoxes_Precision/[email protected]': 0.7231798302410739, 'PascalBoxes_PerformanceByCategory/[email protected]/Basketball': 0.9652990848728149, 'PascalBoxes_PerformanceByCategory/[email protected]/BasketballDunk': 0.4870421987013735, 'PascalBoxes_PerformanceByCategory/[email protected]/Biking': 0.8174097664543525, 'PascalBoxes_PerformanceByCategory/[email protected]/CliffDiving': 0.6467159401389935, 'PascalBoxes_PerformanceByCategory/[email protected]/CricketBowling': 0.9998118686054533, 'PascalBoxes_PerformanceByCategory/[email protected]/Diving': 0.48678173366600064, 'PascalBoxes_PerformanceByCategory/[email protected]/Fencing': 0.7252221388068574, 'PascalBoxes_PerformanceByCategory/[email protected]/FloorGymnastics': 0.7015753486207187, 'PascalBoxes_PerformanceByCategory/[email protected]/GolfSwing': 0.9913231289322941, 'PascalBoxes_PerformanceByCategory/[email protected]/HorseRiding': 0.9933273801597415, 'PascalBoxes_PerformanceByCategory/[email protected]/IceDancing': 0.9253919821730238, 'PascalBoxes_PerformanceByCategory/[email protected]/LongJump': 0.637809816668955, 'PascalBoxes_PerformanceByCategory/[email protected]/PoleVault': 0.6607777957457814, 'PascalBoxes_PerformanceByCategory/[email protected]/RopeClimbing': 0.8969538737505489, 'PascalBoxes_PerformanceByCategory/[email protected]/SalsaSpin': 0.7869481765834933, 'PascalBoxes_PerformanceByCategory/[email protected]/SkateBoarding': 0.42965094009542815, 'PascalBoxes_PerformanceByCategory/[email protected]/Skiing': 0.26324952994810963, 'PascalBoxes_PerformanceByCategory/[email protected]/Skijet': 0.9442916605769802, 'PascalBoxes_PerformanceByCategory/[email protected]/SoccerJuggling': 0.27346688938240526, 'PascalBoxes_PerformanceByCategory/[email protected]/Surfing': 0.681340807090747, 'PascalBoxes_PerformanceByCategory/[email protected]/TennisSwing': 0.8723863740884812, 'PascalBoxes_PerformanceByCategory/[email protected]/TrampolineJumping': nan, 'PascalBoxes_PerformanceByCategory/[email protected]/VolleyballSpiking': nan, 'PascalBoxes_PerformanceByCategory/[email protected]/WalkingWithDog': nan}
mAP: 0.72318
from tubelet-transformer.
For JHMDB Inference
here should be
from models.tuber_jhmdb import build_model
modify
tubelet-transformer/models/tuber_jhmdb.py
Line 20 in f610c97
as
from models.transformer.transformer import build_transformer
Needs 'JHMDB-GT.pkl'
Found the script to download according to the direction in dataset part.
Update:
- nope, that link only has Annotations, Frames and OF, but not with the file above.
- Get the pickle file from MOC
Provided pretrained DETR model has different embedded query input dimensions as the model built and pretrained JHMDB model
modify the loading detr part according to the built model embed_query input dimensions to avoid this problem
tubelet-transformer/utils/model_utils.py
Line 25 in f610c97
pretrained_dict.update({k: v[:query_size]}) if query_size == model.module.query_embed.weight.shape[0]: continue if v.shape[0] < model.module.query_embed.weight.shape[0]: # In case the pretrained model does not align query_embed_zeros=torch.zeros(model.module.query_embed.weight.shape) pretrained_dict.update({k: query_embed_zeros}) else: pretrained_dict.update({k: v[:model.module.query_embed.weight.shape[0]]})Got different mAP as the table shows
per_class [0.96529908 0.4870422 0.81740977 0.64671594 0.99981187 0.48678173 0.72522214 0.70157535 0.99132313 0.99332738 0.92539198 0.63780982 0.6607778 0.89695387 0.78694818 0.42965094 0.26324953 0.94429166 0.27346689 0.68134081 0.87238637 nan nan nan] {'PascalBoxes_Precision/[email protected]': 0.7231798302410739, 'PascalBoxes_PerformanceByCategory/[email protected]/Basketball': 0.9652990848728149, 'PascalBoxes_PerformanceByCategory/[email protected]/BasketballDunk': 0.4870421987013735, 'PascalBoxes_PerformanceByCategory/[email protected]/Biking': 0.8174097664543525, 'PascalBoxes_PerformanceByCategory/[email protected]/CliffDiving': 0.6467159401389935, 'PascalBoxes_PerformanceByCategory/[email protected]/CricketBowling': 0.9998118686054533, 'PascalBoxes_PerformanceByCategory/[email protected]/Diving': 0.48678173366600064, 'PascalBoxes_PerformanceByCategory/[email protected]/Fencing': 0.7252221388068574, 'PascalBoxes_PerformanceByCategory/[email protected]/FloorGymnastics': 0.7015753486207187, 'PascalBoxes_PerformanceByCategory/[email protected]/GolfSwing': 0.9913231289322941, 'PascalBoxes_PerformanceByCategory/[email protected]/HorseRiding': 0.9933273801597415, 'PascalBoxes_PerformanceByCategory/[email protected]/IceDancing': 0.9253919821730238, 'PascalBoxes_PerformanceByCategory/[email protected]/LongJump': 0.637809816668955, 'PascalBoxes_PerformanceByCategory/[email protected]/PoleVault': 0.6607777957457814, 'PascalBoxes_PerformanceByCategory/[email protected]/RopeClimbing': 0.8969538737505489, 'PascalBoxes_PerformanceByCategory/[email protected]/SalsaSpin': 0.7869481765834933, 'PascalBoxes_PerformanceByCategory/[email protected]/SkateBoarding': 0.42965094009542815, 'PascalBoxes_PerformanceByCategory/[email protected]/Skiing': 0.26324952994810963, 'PascalBoxes_PerformanceByCategory/[email protected]/Skijet': 0.9442916605769802, 'PascalBoxes_PerformanceByCategory/[email protected]/SoccerJuggling': 0.27346688938240526, 'PascalBoxes_PerformanceByCategory/[email protected]/Surfing': 0.681340807090747, 'PascalBoxes_PerformanceByCategory/[email protected]/TennisSwing': 0.8723863740884812, 'PascalBoxes_PerformanceByCategory/[email protected]/TrampolineJumping': nan, 'PascalBoxes_PerformanceByCategory/[email protected]/VolleyballSpiking': nan, 'PascalBoxes_PerformanceByCategory/[email protected]/WalkingWithDog': nan} mAP: 0.72318
Thank you for your correction.Do you find any code about video map inference. I want to reproduce the video map of UCF101-24.
from tubelet-transformer.
Related Issues (20)
- Question about temporal localization using action switch HOT 2
- the complete version of the TubeR-UCF code
- Question about 'out_logits_b'.
- Question of Loading the trained model.
- Tuber CSN-152 model with memory
- The eval results from Tuber CSN-152 IG65+K400 model HOT 8
- Inference JHMDB mAP: 0.00000,Inference ava2.2 mAP: 0.00001
- Question about the DETR pretraining process
- Training problems for JHMDB datasets HOT 1
- some question for JHMDB
- path doesnt exist /mnt/sda/ava/frames/{}/ HOT 1
- Details about DETR pretraining
- Are tubelets actually predicted for AVA?
- Cannot reproduce training results HOT 3
- Code here don't match the paper
- DETR checkpoint mismatch for JHMDB HOT 4
- What is the schedule for uCF24 HOT 1
- Questions about the code for JHMDB HOT 4
- Missing annotation file 'ava_train_v21.json' HOT 2
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from tubelet-transformer.