Comments (5)
Hi,
we use slow updating of parameters. The parameters are updated after waiting for 'iter_size' iterations. We set the batch size as 16 and iter_size as 2. Thus, the effective batch size is 32. You can change the batch_size as 32 and iter_size as 1 to have the same effect.
from gsm.
Hi,
we use slow updating of parameters. The parameters are updated after waiting for 'iter_size' iterations. We set the batch size as 16 and iter_size as 2. Thus, the effective batch size is 32. You can change the batch_size as 32 and iter_size as 1 to have the same effect.
hello! Thanks for your reply.
I test your something-v1_RGB_InceptionV3_avg_segment8_checkpoint.pth.tar and got the same result as in your paper.(49.01% top1.However when i using follow shell to train model by myself:
#!/usr/bin/env bash
python main.py something-v1 RGB --arch InceptionV3 \
--num_segments 8 --consensus_type avg \
--batch-size 32 --iter_size 1 --dropout 0.5 \
--lr 0.01 --warmup 10 --epochs 60 --eval-freq 5 \
--gd 20 --run_iter 1 -j 16 --npb --gsm
I got the 48% acc. If using --batch_size 16 --iter_size=2 I get the result about 48% not the 49% acc reported in your paper too. For BNInception I got the 46% acc(it is 47% in paper!).Maybe there are some details i have ignored. Such as BN? I using 2 2080Ti GPUS.
1.Is there anything I should be aware of when using your GSM code?
2.How many GPUS used duing your training time?
3.The acc 49.01% is a normal vaule or just a maximum of many experiments?
Thanks! Looking forward to your reply!
from gsm.
Due to the stochastic nature of training, there will be some minor differences in the result. All the models are trained using 2 1080TI gpus. We report the accuracy obtained from a single run.
from gsm.
Due to the stochastic nature of training, there will be some minor differences in the result. All the models are trained using 2 1080TI gpus. We report the accuracy obtained from a single run.
Hello! Thanks for your help! I have get the 49% result of sthv1 through my many experiments! I think 49% is not easy to get out. Anyway, it is a good job. Thanks for your share!
And have you ever train GSM with sthv2? Why not writer it into paper?
from gsm.
Thank you for the nice words.
I recently noticed that the BN statistics are update in a different way when slow updating of parameters are used (batch_size=16, iter_size=2). However, I am not sure if this causes a significant impact in the final result.
Regarding sthv2, we did not train the model on this dataset since it a superset of sthv1 with less label noise and more samples. We will do an evaluation on sthv2.
from gsm.
Related Issues (20)
- about the input HOT 6
- how many gpu used when training HOT 1
- These lines of code seem to be redundant, can I delete the code from line 47 to line 50? HOT 4
- Performance difference in Diving48 dataset HOT 11
- Too long training time on Something-V1
- t-sne HOT 5
- Can you share the Diving48 dataset HOT 1
- Training issue on num_segment=12 HOT 3
- How to reproduce the result on EPIC-Kitchens dataset HOT 2
- Different dimension in figure 2 and figure 3 in your paper HOT 2
- How to get the result in Tab 3 HOT 8
- How does the batch_size parameter influence the accuracy HOT 3
- Confused with the codes using grads clipping and accumulation simultaneously HOT 1
- Can you share me the link to the supplementary document of this paper ? I can not understand the model ensembles well. Thank you very much! HOT 1
- How many GPUs are used when you train the models here? I have 4 gpus. How can I set the learning rate here ? HOT 1
- How to set the number of frames in the code when we train the models? What is the meaning of "num_segments" in the code ? Thank you very much ! HOT 1
- test_rgb.sh cannot work. And get an error:RuntimeError: shape '[0, 8, 64, 28, 28]' is invalid for input of size 50176 HOT 1
- about the gate shift module HOT 4
- about how to set frames to train the model
- how apply grad-cam on GSM
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 gsm.