Comments (21)
Sure, but currently I am busy on some projects. I will probabaly update this repo at about Dec 20.
Jeffrey
from two-stream-action-recognition.
from two-stream-action-recognition.
from two-stream-action-recognition.
Hi,
This method is called cross-modality pretraining, which is proposed in "Temporal Segment Networks: Towards Good Practices for Deep Action Recognition".
The procedure is to average the weight value across the RGB channels and replicate this average by the channel number of motion stream input( which is 20 is this case).
Jeffrey
from two-stream-action-recognition.
Thank you, I got it. Now, I am trying this method with keras and I get some troubles, are you familiar with it?If so, I think I can get your help.
from two-stream-action-recognition.
Hi, I have tried the two stream network on Keras before but not quite familiar. Could you post your issue? There might be something I can do for help.
from two-stream-action-recognition.
I use model.get_config()
to complete cross-modality pretraining, and i use Inception-resnet-v2 model, optimizer is Adam(default parameters) / SGD(lr=1e-2, 0.9), optical frames are stacked with 10-x and 10-y, but the acc is very low(65%), I want to know more details about your model, or could you give me some advise!
from two-stream-action-recognition.
If you have keras pretrained optical flow, could you publish it? Thank you !
from two-stream-action-recognition.
Sorry, I don't have keras pretrained optical flow model.
I think the reason caused low acc might be the sampling method in your training stage since I do have some related experiences on pytorch framework.
Could you provide some details about how you sample your training data in each batch?
Jeffrey
from two-stream-action-recognition.
Can you please share your pretrained models. This would be helpful to run your code in the testing phase.
from two-stream-action-recognition.
@jeffreyhuang1 There are 8631 video-samples in train set. Each batch, I randomly choose 32 video-samples from it. And each video i random choose 10 x-frames and 10 y-frames. Then i stack it, the result is (32, 229 , 229, 20). On the third axis, the first ten numbers are 10 x-frames, the last ten numbers are 10 y-frames. All the frames is continuous.
from two-stream-action-recognition.
@roystonrodrigues
Hi, I just share my new version of pretrained model and code today. You can test it and feel free to correct my mistakes.
Jeffrey
from two-stream-action-recognition.
@cwzat
According to the two-stream paper, I remember that the input of motion stream is a stack of 10 consecutive optical flow. In my opinion, maybe your problem is in the sampling stage that you randomly choose 10 x-frames and 10 y-frames rather than choose the consecutive x,y optical flow.
Jeffrey
from two-stream-action-recognition.
@jeffreyhuang1 I already choose them consecutivly and the acc is low yet. Could you give me some another advices?
from two-stream-action-recognition.
oops, sorry my bad. I lose some information in your message. I check the implementation method in the two-stream paper and find that
Therefore, on your third axis, the order of your data should be [x0, y0, x1, y1, x2, y2, ...]
Maybe be you can try this one!!
Sorry again for misread your message.
Jeffrey
from two-stream-action-recognition.
@jeffreyhuang1 It is okay! Thank you very for your help! I am very glad to solve the problem through your help! I try it right now!
from two-stream-action-recognition.
@cwzat, I look forward to hearing your good news soon XD
Jeffrey
from two-stream-action-recognition.
@jeffreyhuang1 I have another quention, how do you choose the optimizer and the parameters?
from two-stream-action-recognition.
@cwzat, basically, I just follow the setting in the paper, which uses SGD as the optimizer.
For the batch size and learning rate, I increase learning rate according to the difference between my batch size and the batch size provided in the paper.
More precisely, you can just tune some parameters to boost the model performance.
Jeffrey
from two-stream-action-recognition.
@jeffreyhuang1 Your methods choosing test set is same as train set? And are you training only the top layers or all the layers?
from two-stream-action-recognition.
@cwzat yeah, the stacked optical flow method is the same and I am training all of the layers in resnet101.
Jeffrey
from two-stream-action-recognition.
Related Issues (20)
- HandStandPushups 在代码中多次单独处理,为什么?谢谢
- Error while testing.
- Excuse me, what is the operating environment of this experiment?Thanks HOT 1
- Missing License HOT 1
- If I take 64 x-channel and 64 y-channel optical flow images as input to motion cnn, should I make the out channel num of conv1_custom bigger?
- The environment? HOT 1
- what is the purpose of val_sample19 ?
- Please tell me how the frame_count.pickle file is generated. Thank you. I want to use hmdb51
- Excuse me, is there a tensorflow version?
- How did you get the performance you reported?
- About optic-flow?
- How can I use flownet2.0 method to generate 2-channel optical flow image ?
- pretrained model
- 写的太混乱了
- A problem I meet in spatial_cnn and spatial_dataloader
- 请问,此代码是不是先运行spatial_cnn.py在运行motion_cnn.py,最后在运行average_fusion.py,感谢
- Does this code have no data preprocessing (generating RGB image and optical flow diagram)
- pickle文件怎么生成的,具体都要包括什么内容啊,谢谢 HOT 1
- How to generate pickle files? What should be included? Thank you
- TypeError: new(): invalid data type 'str'
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 two-stream-action-recognition.