Comments (12)
@ardasnck if you want to get the same acc with the paper you must do fine tuning from sports-1M, the paper has said it. Actually you can reference this issue #2, and I have tried that if I don't do the fine tuning I just get the 33% acc.
Cheers
from c3d-tensorflow.
Hi @ardasnck
There are 13318 videos in UCF101 dataset, I used 11318 videos for traning and 2000 videos for test, and I can get a 50% top 1 accuracy after 8000 iterations with batch_size is 64.
This is my traning from scratch top-1 accuracy curve, cross entropy curve, total loss(cross entropy + regularized loss) curve:
from c3d-tensorflow.
Hi @ardasnck
I am a little busy in recent days, I think I can do the evaluation in next week.
from c3d-tensorflow.
@hx173149 sure! i can't reproduce the same results with the paper on my own tensorflow implementation. So if you can get similar results after your evaluation, it would be great to add your train-from-scratch implementation in this repository.
from c3d-tensorflow.
@hx173149 yeah i know issue #2 and also read the C3D official documentation and paper about fine-tuning. But my question is exactly on training from scratch(not fine-tuning). Actually i got 40% accuracy when I train from the scratch and you mentioned that you only reached to 33%. This https://docs.google.com/document/d/1-QqZ3JHd76JfimY4QKqOojcEaf5g3JS0lNh-FHTxLag states that they reached 45% so I was wondering what could be the potential reason for the difference? Also another observation that loss value in tensorflow is clearly higher than caffe implementation during training...
from c3d-tensorflow.
Hi @ardasnck I think I have some free time in next days,I will reproduce my result once more... and have you ever try the caffe version code? Did it can get the 45% accuracy with training from scratch? I am curious about this problem too...
PS: I can't open the URL page you mentioned upside.
Cheers
from c3d-tensorflow.
Hi @hx173149. I updated the link once again but I'm not sure what's happening with that...
For the training from scratch: Yes I run the caffe version of the code on my machine and I got 42.88% accuracy (note that I used batch size 16 because of my gpu capacity). I also edited my own tensorflow implementation (some minor changes) and I got 42.64%. I believe this shows that it works as it should be.
PS: In case of the link doesn't work again , I was referring to C3D-User Guide document which author provides it on his project page.
from c3d-tensorflow.
Dear @hx173149 ,
Thank you very much for the very detailed feedback. This is great that you reach to 50% top 1 accuracy. Did you use the same train and test split that original caffe implementation used? Because paper claims that they got 45% accuracy and when I run their code on my own machine (batch size 16) i got 42.9% accuracy.
from c3d-tensorflow.
Hello,
I also want to train from scratch but I am kind of new to Deep Learning, especially using 3d convNet. Could you briefly explain the training mechanism? Based on my understanding, you feed in 16 frames as input and a label to perform supervised learning. But do you use all the frames for training? I would really appreciate your help if you can briefly explain the whole data preparation and training process.
(I am trying to rewrite everything in Keras. So far I have defined the nets but I do not know how to prepare the video data)
from c3d-tensorflow.
Hello @gyang1011
My training mechanism is like this:
First I will choose 64 samples randomly for each iteration
Then I will slice a 3.2 seconds(about 16 frames) randomly from each sample for training.
from c3d-tensorflow.
@ardasnck @hx173149 @gyang1011
I trained this network and got 33% in split 1 of UCF101. However, I think the accuracy of this 8-layer convolution network should be 33%. In paper C3D, the author use a 5-layer convolution network (not 8-layer convolution), so they can get 45% in UCF101. This means that the structure of the network training from scratch and pre-trained in Sport 1M is different!
from c3d-tensorflow.
@LongLong-Jing I think you are right, maybe there have some duplication samples among my train list and test list, I am not very sure.
from c3d-tensorflow.
Related Issues (20)
- Before about the reshape of dimension transform issues HOT 1
- ValueError: Cannot feed value of shape (11, 16, 160, 160, 3) for Tensor 'Placeholder:0', which has shape '(12, 16, 160, 160, 3)' HOT 1
- train_c3d_ucf101.py
- predict_c3d_ucf101.py
- very very big loss values
- Could you give me a list as example? HOT 1
- ValueError: setting an array element with a sequence. HOT 1
- What is the difference between clip accuracy and video accuracy?
- Train with last checkpoint
- ERROR when using conv3d
- about how to use .meta or index
- about preprocessing HOT 7
- ResourceExhaustedError in train_c3d_ucf101.py HOT 2
- UnboundLocalError: local variable 'img_datas' referenced before assignment HOT 2
- the accuracy is always 0 HOT 2
- overfitting HOT 1
- prototxt file for conv3d_deepnetA_sport1m_iter_1900000.caffemodel
- missunderstanding about .model file type HOT 1
- hou ge niubility HOT 1
- pi zhu is watching you
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 c3d-tensorflow.