Comments (4)
In fact, we cannot know the exact 'best' iteration, just use the experience and the loss curve to choose an experiential iteration.
According to our experience, when using cosine lr decay, a good iteration can be found at about 3~5 complete annealing decay. Usually, we set the first decay as 2 epochs of the training set. More details can be found in the paper: SGDR: Stochastic Gradient Descent with Warm Restarts.
from transferable-interactiveness-network.
Thanks!
What about training v-coco, I see that your just train 20000 iteration and the result of 6000 iteration preforms a good result. However, when I training the vcoco dataset, I found the loss continued to go down when the iteration reached 20000 and the testing result was not good.
from transferable-interactiveness-network.
A more detailed analysis of the classes may provide you more clues about the fitting state of the model, some classes' performances begin to degrade after xx iterations, meanwhile, some other classes are still increasing. V-COCO is quite smaller, it exactly needs much fewer iterations to achieve a good point and has a very early stopping in our experiment.
from transferable-interactiveness-network.
Thanks a lot!
from transferable-interactiveness-network.
Related Issues (20)
- about test the model,mAP value is too low HOT 1
- The eigenvector shape problem of early fusion and late fusion
- The shape of pool5_O in early and late fusion HOT 1
- self.spatial = tf.placeholder(tf.float32, shape=[None, 64, 64, 3], name = 'sp') HOT 9
- What is the reason for using negative examples? HOT 4
- problem in installing HOT 4
- Questions about the ablation studies HOT 2
- About self.HO_weight HOT 1
- V-COCO training results is bad HOT 2
- The empty detections
- the pre-trained weight
- augment and pos_augment? HOT 1
- the code for ten part boxes HOT 1
- What is the approximate speed of video real-time motion detection?
- where to find or download the file res50_faster_rcnn HOT 2
- Bad evaluation results HOT 1
- How to use code to infer in my own data set? My own data set is not labeled, just want to see the actual application effect of HOI algorithm HOT 1
- Question about final HOI classification scores HOT 4
- Issue Downloading Pretrained Weight Files HOT 3
- raceback (most recent call last): │ File "tools/Vcoco_lis_nis.py", line 304, in <module> │ generate_result = generate_pkl(mode, test_D, test_result, prior_mask, Action_dic_inv, (6, 6, 7, 0), args.prior_flag) │ File "tools/Vcoco_lis_nis.py", line 145, in generate_pkl │ score_binary_d = np.array(dic_d['binary_score']) │KeyError: 'binary_score'
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 transferable-interactiveness-network.