Comments (5)
Hello, I used the original implementation in Darknet (https://pjreddie.com/darknet/yolo/). You can follow this guide: http://guanghan.info/blog/en/my-works/train-yolo/ to train YOLO with your own dataset. I also hack into the C code to get the program output predicted bounding boxes.
from cnn_finetune.
Yes, the article is slightly outdated. It is for YOLO v1. However, the config files of YOLO v2 and v1 are very similar so long as I recall, so if you can follow that of v1 I am sure you can do the same for v2.
YOLO v2 should outperform SSD-300. Resolution plays an important part in detector performance (can refer to this paper: https://arxiv.org/pdf/1611.10012.pdf). YOLO v2 takes 448x448 inputs while SSD takes 300x300. Speaking from my personal experience, YOLO v2 outperformed SSD-300 in the kaggle competition. In this regard, YOLO v2 vs SSD-512 should be a more fair comparison.
Yes, the provided weights for YOLO v2 (DarkNet19 with 448x448 input resolution pre-trained on ImageNet) is for classification. But it's still very useful as good feature extractor for the detection layers. I used that for my kaggle dataset and it worked quite well.
from cnn_finetune.
one missing feature in Yolo v2 is that they have not implemented the angle
in training, it is a useful feature when the target objects might rotate in practice, which of course does not apply for the VOC dataset, and that's the reason why they have not implemented it completely.
from cnn_finetune.
Thank you.
The article dated at 15/12/22
. seems to be for YOLO V1
from cnn_finetune.
Besides, Do you think YOLO v2 or SSD-300 (7++12+COCO) will have less detection errors? in Fine-Tuning.
Although I think we can not Fine-Tune the YOLO. The provided weights is as an initial classification weights and we train from scratch actually.
from cnn_finetune.
Related Issues (20)
- You are trying to load a weight file containing 0 layers into a model with 16 layers HOT 3
- Input_shape mis_match using the denseNet121.py
- Can I finetune the pretrained densenet with 5-channel inputs?
- load_data() module HOT 3
- Resnet101 weights using channels other than 3 results in weight loading error HOT 1
- the input size of image is fixed? HOT 1
- fine tune my own dataset? HOT 6
- Failed to use Theano as backend for vgg16.py
- what's the difference between this completation and official keras completation
- Can I use this code for regression problem?
- Resnet50 Issue loading weights
- TypeError: 'module' object is not callable HOT 2
- Issue will running densenet? HOT 1
- Scale layer after Batch Normalization
- CNN MODEL / FINE TUNING / VGG16
- How to finetune for Grayscale images?
- In resnet152 i am getting that error
- AttributeError: module 'keras.backend' has no attribute 'image_dim_ordering' HOT 2
- TypeError: 'module' object is not callable HOT 2
- NotImplementedError: Cannot convert a symbolic Tensor (pool1/3x3_s2_1/MaxPool:0) to a numpy array.
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 cnn_finetune.