Comments (9)
Can you provide more information? Maybe a log of the training.
It's probably due to the fact that it converges from the first epoch
from movinet-pytorch.
The notebook functions correctly, also I use the networks daily. It's unlikely these are problem related to part of the code of this repository. If you provide a colab short script that reproduces the problem I will look at it.
from movinet-pytorch.
I had the same problem.
When I trained Movinet with my own dataset. The training loss decreased but the validation loss increased from the first epoch.
( see the below image )
If I trained Movinet not using pretrained Kinetics with HMDB51 in the notebook sample and my own dataset (i did not save a log of the training), both losses had not decreased.
Can you explain it? Thank you
from movinet-pytorch.
I will run your notebook with HMDB51 for 10 epochs and show to you a log of the training. Because I used the same function for my own dataset and got the same problem. I don't think it can converges from the first epoch with many datasets. When you train Movinet with your dataset, the validation loss decreases or not?
Thank you
from movinet-pytorch.
I trained HMDB51 dataset for 20 epochs with modelA0_stream_statedict_v3, the result is as follows:
from movinet-pytorch.
@nguyenquibk1996
Hi, did you solve the problem? I met the same problem in my own dataset. Then I tried to train hmdb51 without pretrained, the evaluation accuracy is as follows:
Did I miss any key points during finetuning or could you give any clues about this?
from movinet-pytorch.
@nguyenquibk1996 Hi, did you solve the problem? I met the same problem in my own dataset. Then I tried to train hmdb51 without pretrained, the evaluation accuracy is as follows:
Did I miss any key points during finetuning or could you give any clues about this?
I think the dataset is primary cause, and the data processing method(one clip or multiple clips sampled from one video) is second cause. I have train the X3D and SlowFast on the HMDB51 by mmaction2(default config samples one clip from one video), top1 acc is also about 30%, and validation loss can decrease.
from movinet-pytorch.
Have you tried any other datasets? BTW, I see in mmaction2 there's no training codes of X3D, could you tell me how to get the codes?
from movinet-pytorch.
Have you tried any other datasets? BTW, I see in mmaction2 there's no training codes of X3D, could you tell me how to get the codes?
I have tried UCF101, the top1 can over 45%. I write the codes of X3D by myself(of course refer to existing codes )
from movinet-pytorch.
Related Issues (20)
- Using MoViNet in a dataset with variable-length videos HOT 1
- why don't you use 'T.Normalize' when you train HMDB51? HOT 1
- Neural network arch displayed by Netron is wrong HOT 7
- Tips for Implementing a3 ,a4,a5 movinets streaming version HOT 3
- Test model based on 'evaluate_stream' is ok, but do inference frame by frame is very different? HOT 2
- Modifying for binary classification HOT 2
- Kinetics 400 models HOT 1
- Very low validation accuracy with pretrained models! HOT 1
- F.ToFloatTensorInZeroOne not exist HOT 2
- 。
- There seems no implementation of positional_encoding HOT 4
- How can we access the stream buffer? HOT 1
- need to process HMDB51 dataset?
- got wrong results during test
- weight
- The parameters that trained on Charades.
- Kinetics400/600
- Training
- Training on the custom dataset HOT 1
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 movinet-pytorch.