Comments (7)
@tzynzs thanks for your interest in my work. I am not understanding your question. Could you rephrase it better. You want to test on 1 video sample or query-class=1 video?
from strm.
@tzynzs thanks for your interest in my work. I am not understanding your question. Could you rephrase it better. You want to test on 1 video sample or query-class=1 video?
thank you for your reply.I want to test 1 video to see the accuracy of the prediction.Either hmdb's or my own data.How do i do it?
from strm.
Okay, you will need to modify the test function a bit.
-
Use a pre-trained model and load it before testing.
-
Look into the paper and sample K frames for your video.
-
Check the labels of HMDB /Your dataset and see if they properly match with the dataset used by the pre-trained model. If not, the predictions won't make sense.
from strm.
Thanks for your detailed answer!
I understand what you mean.These videos are based on datasets to predict.
If I trained a model using hmdb or something,and how do I use this model to predict an unlabeled new video?
from strm.
@tzynzs you can just feed the video to the model, and look up the data feeder to see the classes included. If it is an unlabeled video, only perform testing with the pretrained weights. It will require some understanding of the https://github.com/Anirudh257/strm/blob/main/video_reader.py
from strm.
Okay,I get it.Thank you for your help!
from strm.
Your welcome.
from strm.
Related Issues (20)
- Accuracy issues HOT 2
- ssv2
- About the number of the params HOT 3
- the Kinetics-100 dataset HOT 1
- What to do checkpoint_corr model file loading error HOT 1
- Five categories of samples are missing in the Kinetics-100 dataset; HOT 1
- Accuracy recurrence issues HOT 15
- When training ,loss is nan HOT 1
- accuracy
- ValueError: Sample larger than population or is negative HOT 1
- ucf数据集处理
- Q about few-shot action recognition
- A question about two log files called train_output.log and eval_output.log.
- Why did the target image change to 40 x 3 x 224 x 224 during training? HOT 1
- Training environment issues
- Inconsistent dataset catalog structure from official UCF101 HOT 1
- Missing key(s) in state_dict
- ValueError: not enough values to unpack (expected 3, got 0) HOT 2
- Questions about validation sets HOT 1
- Preprocessing about UCF 101
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 strm.