Comments (6)
@ashimpd How many samples did you use in the training set?
from yolo-digit-detector.
I used all the samples present in svhn training set which is approx 33K
from yolo-digit-detector.
@ashimpd As a result of my experiments, it is difficult to learn multiple samples of svhn dataset at once. So I overfit a small number of samples (2 to 10) and then gradually add training samples. I am studying whether there is a better way of training.
from yolo-digit-detector.
@penny4860 Can you elaborate on how you trained the net and got good results? Thanks!
from yolo-digit-detector.
@cyberh49 Thank you for your interest in this project. It is difficult to train several samples with the mobilenet structure. So I am doing resnet50-based experiments and I have confirmed that training is good for 1000 samples. This will soon be reflected in the master.
from yolo-digit-detector.
@ashimpd @cyberh49 I updated to network based on resnet. I confirmed that training is converged for many samples (1000).
from yolo-digit-detector.
Related Issues (20)
- Hey pretrained weights are overfitted. HOT 3
- pre-train model HOT 6
- SVHN labeling dataset HOT 4
- Digit Detection fails after training from scratch (or fine tuning) HOT 5
- Extraneous detection boxes on sample input using pre-trained weight file HOT 9
- Did you train your model from scrath without load any pretrained weight? HOT 3
- Yolo weights file HOT 3
- input size HOT 4
- train model by other labels HOT 1
- Is your notebook directly use weight.h5 from google? HOT 1
- How to train with non-square images without resizing HOT 1
- The Layer has never been called and thus has no defined output shape. HOT 2
- Detecting Handwritten Digits HOT 1
- Training model from scratch on custom dataset performing poorly
- Detecting more than 2 digits HOT 7
- RuntimeError: The layer has never been called and thus has no defined output shape HOT 3
- I'm not able to download weights.h5
- 'str' object has no attribute 'decode' HOT 3
- incorrect detection outputs by pre-trained model HOT 1
- Pre-trained model doesn't detect anything on the SVHN sample images
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 yolo-digit-detector.