Comments (7)
My learning rate was initially 0.0001, and I used a step lr scheduler to reduce the learning rate to 0.1 after every 3 epochs. The batch size was 64. The number of epochs trained for the teacher model was 8, and the number of epochs trained for the student model was 3.
from multitask-emotion-recognition-with-incomplete-labels.
- Which dataset did I use to train the teacher model
Firstly, the multitask CNN model was trained on the mixed dataset, well balanced. After training, the weights of the resnet50 convolutional filters were imported in multitask CNN-RNN model, and fixed. Secondly, the multitask CNN-RNN model was trained on Aff-wild2 dataset only, because one of the external dataset is not a video dataset. - What parameter setting did I use to train the teacher model?
About parameter settings, please refer to the default settings in /options, andpython train.py --force_balance --name image_size_112_n_students_5 --image_size 112
BTW, I will recommend you to ask for the cropped and aligned faces of aff-wild2 dataset by emailing to [email protected] . Because that is the data I used.
from multitask-emotion-recognition-with-incomplete-labels.
Thanks a lot for the clarification! Yes, we are using the cropped aligned images provided the challenge organisers.
Regarding the initialisation of Multitask-CNN, I have found three options, i.e., 'ferplus', 'sfew' and 'imagenet'. May I know which one do you use? the default is 'ferplus'. Does the inistialisation makes huge difference in your training?
Thanks again!
from multitask-emotion-recognition-with-incomplete-labels.
The 'ferplus' choice means that the backbone model (resnet50) was pretrained on ferplus dataset. If you choose other options, the weight initialization will be different. Especially, if you choose 'imagenet' dataset, which is an object recognition dataset, the pretrained task is very different from what we are trying to learn here.
But there might be other reasons. May I ask you provide 1) the options, it looks like
------------ Options -------------
C_adam_b1: 0.5
C_adam_b2: 0.999
F_adam_b1: 0.5
F_adam_b2: 0.999
batch_size: 64
checkpoints_dir: ./checkpoints
criterion: CE
dataset_mode: Mixed_EXPR
force_balance: True
gpu_ids: [0]
... ...
-------------- End ----------------
2 ) Your evaluation results on the validation set of Aff-wild2 dataset
from multitask-emotion-recognition-with-incomplete-labels.
I see, thanks!
I used the default options in the base_options.py, with the force_balance option enabled and image size to be 112.
May I ask what is the learning rate and batch_size you used? The default is batch_size 20, and lr 0.0001?
from multitask-emotion-recognition-with-incomplete-labels.
Thanks a lot, that's very useful!
We also found that you have two merging methods when reporting validation performance. May we know which ones did you use in your paper? Or you simply report whatever it is the best for each task?
Sorry for these many questions! We really appreciate your help, and we will certainly cite your work if there is any follow-up publication from our side.
from multitask-emotion-recognition-with-incomplete-labels.
We just tried the two methods for ensembling student models: one is to average the raw outputs, the other one is to do major voting on the estimations. We found the first one had better performance than the second one for all the three tasks. So we reported the results for the first method in our paper.
from multitask-emotion-recognition-with-incomplete-labels.
Related Issues (20)
- using model as prediction HOT 2
- Replicate your result
- Validation loss increases after the first epoch
- Could I get pkl of database?
- Creating aligned images of ExpW dataset problem HOT 2
- About Datasets HOT 1
- AssertionError: The OpenFace output directory should not be empty: examples/utterance_1_opface HOT 1
- AssertionError HOT 6
- AU prediction
- 关于注释文件 HOT 2
- pretrained imagenet does not work HOT 2
- Getting same csv generated by api for different video files HOT 9
- Cannot find txt files (AU.txt, EXPR.txt, and VA.txt) HOT 1
- Cannot find train.py HOT 1
- Demo
- Dead Link: Unable to download the recommended "pytorch-benchmark" models in the ReadMe file of api folder
- crop and align face images HOT 4
- 怎样获取到"resnet50_ferplus_dag.pth"和"resnet50_face_sfew_dag.pth"这两个预训练模型? HOT 1
- Is there any skipped frames within a sequence of video frames? 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 multitask-emotion-recognition-with-incomplete-labels.