Comments (3)
Prec@3 means as long as one of your top 3 predictions is correct, your prediction is correct. It is a loose metric, so it should be higher than Prec@1. This makes sense.
For your problem, the most common explanation would be overfitting. How large is your own dataset? For example, how many classes, how many videos for each class, etc. As you should know, resnet152 can overfit UCF101 (UCF101 has 101 classes, each class has more than 100 videos). So if your dataset is smaller than UCF101, overfitting should be the reason. You can try different things, like choosing a smaller network, early stopping, turn off BN, add more data augmentations etc.
There is also another possibility, which is the domain similarity. Maybe your training data and validation data look very different, so that your model can't generalize.
In general, validation accuracy will be lower than training accuracy, this is expected. Take UCF101 as an example, the training accuracy could be 90+, the validation accuracy is 80+. There is a 10% gap there as well. But again, since datasets are different, there is no direct comparison can be made. Hope this helps.
from two-stream-pytorch.
Thank you for your answer. My dataset is similar to the UCF101 dataset. There are 100 classes, each with 250 videos. I think it should be the reason for overfitting, I will adopt your suggestion and try it. Thank you very much!
from two-stream-pytorch.
No problem at all, good luck with your experiments. Close the issue for now.
from two-stream-pytorch.
Related Issues (20)
- About pre-trained Model HOT 2
- test video HOT 5
- Question about training the models together HOT 2
- Different running env? HOT 5
- Can you provide your results for loss and accuracy values of spatial and temporal training?
- The number of GPUs? HOT 1
- I use your restnet152 model parameters for testing, but in split_1 the accuracy is only 67.59%.
- Use the video input from the camera for action recognition HOT 7
- Problems about VideoSpatialPrediction.py HOT 2
- How is the two streams fused ? HOT 1
- What is the accuracy of UCF101?
- what's version of pytorch and cuda
- dense_flow 可不可以在windows安装 HOT 1
- 如果没有安装dense_flow,运行build_of.py文件,是不是不会运行出结果 HOT 1
- fusion two stream feature?
- a PROBLEM when using VGG as motion model
- 老师我想问下怎么late fusion呀 HOT 1
- 关于抽帧的图片存放路径 HOT 2
- video sampling rate in training two-stream network
- About parameter --new_length in training RGB videos
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-pytorch.