Comments (5)
This is finetuning from imagenet initialisation, to finetune from the pretrained model download it
https://www.robots.ox.ac.uk/~maxbain/frozen-in-time/models/cc-webvid2m-4f_stformer_b_16_224.pth.tar
Then add
"load_checkpoint": PATH_TO_DOWNLOADED_MODEL
to configs/msrvtt_4f_i21k.json
from frozen-in-time.
Thanks! I will try to implement the pretaining with this checkpoint.
BTW, I have finetuned the checkpoint WebVid2M+CC3M+COCO, 4-frames, base_patch_16_224. I achieve:
epoch : 27
loss_0 : 0.5593496548643809
val_loss_0 : 1.0900163816081152
val_0_t2v_metrics_R1: 28.4
val_0_t2v_metrics_R5: 55.8
val_0_t2v_metrics_R10: 67.5
val_0_t2v_metrics_R50: 88.6
val_0_t2v_metrics_MedR: 4.0
val_0_t2v_metrics_MeanR: 29.498
val_0_t2v_metrics_geometric_mean_R1-R5-R10: 47.46994959864713
val_0_v2t_metrics_R1: 28.6
val_0_v2t_metrics_R5: 56.2
val_0_v2t_metrics_R10: 68.4
val_0_v2t_metrics_R50: 88.9
val_0_v2t_metrics_MedR: 4.0
val_0_v2t_metrics_MeanR: 26.8585
val_0_v2t_metrics_geometric_mean_R1-R5-R10: 47.90558524371724
Validation performance didn't improve for 10 epochs. Training stops.
Are these results correct? The R1 is slightly lower than reported values (31.0). Is this regular fluctuation?
from frozen-in-time.
I got the similar results as in paper with batch_size = 64.
from frozen-in-time.
run the test script
test.py --resume PATH_TO_FINETUNED_CHECKPOINT --sliding_window_stride 12
the sliding window stride argument adds temporal averaging over multiple frame samples :)
from frozen-in-time.
Exactly! I got further improvements with this testing script. R1 comes to 33.7.
from frozen-in-time.
Related Issues (20)
- CC3M data error HOT 3
- About Curriculum Learning HOT 3
- What does zero-pad means? HOT 1
- License ? HOT 2
- Curriculum Learning and Video-Image Joint Training HOT 4
- How about initializing parameters with CLIP model HOT 1
- Creating 256 emb vector from text during inferenece HOT 2
- evaluation for MSVD . HOT 1
- How to select checkpoint when fine-tuning on MSRVTT HOT 1
- config about Paper Result HOT 2
- Code/template for the demo? HOT 4
- CC3M dataset broken HOT 1
- Result about MSVD HOT 2
- About the effects of sliding_window_stride
- pre-process mp4 HOT 1
- Question about pretrained models? HOT 1
- Could you please also share the demo UI codes? HOT 2
- RuntimeError: There were no tensor arguments to this function (e.g., you passed an empty list of Tensors), but no fallback function is registered for schema aten::_cat. HOT 1
- Cannot reproduce results
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 frozen-in-time.