Comments (7)
I think maybe resnet101 is difficult to train.
This maybe helpful.
For Resnets, we fix the first block (total 4) when fine-tuning the network, and only use crop_and_resize to resize the RoIs (7x7) without max-pool (which Xinlei finds useless especially for COCO). The final feature maps are average-pooled for classification and regression. All batch normalization parameters are fixed. Learning rate for biases is not doubled.
from simple-faster-rcnn-pytorch.
@chenyuntc Thanks, I also fixed the weights for top layers, but the result didn't improve. As you mentioned, it might be the reason of BN and biases. I'll have another try.
from simple-faster-rcnn-pytorch.
Hi @chenyuntc, I've trained the model with:
- Fix the first block.
- Learning rate for biases is not doubled.
- All batch normalization parameters are fixed.
- Use 1e-4 as weight decay.
And I restrictedly followed the way of training as I did in caffe, while it seems the performance cannot be improved.
Have you tried to train the model on networks other than VGG16?
from simple-faster-rcnn-pytorch.
Actually, I only tried VGG16.
from simple-faster-rcnn-pytorch.
I recently also want to implement resnet structure based on this project. And I found your @twtygqyy codes are very helpful to me. But I have a question about batch normalization. Why we need to fix batch normalization parameters here?
from simple-faster-rcnn-pytorch.
@blateyang BN only work when batch_size>1 and only work well when batch_size>=16.You can see this paper https://arxiv.org/abs/2002.05712.However,@chenyuntc code only surport batch_size==1
from simple-faster-rcnn-pytorch.
from simple-faster-rcnn-pytorch.
Related Issues (20)
- Time consumption mainly comes from the i/o of cpu and gpu(such as numpy to tensor(cuda)) is that correct?
- Why do I need to copy a formal parameter in your codes? Is there some trick?(data/util.py bbox = bbox.copy())It's common in C++, but in python, i'm very curious.
- How to train Faster R-CNN on my own custom dataset and changing the RPN loss functions? HOT 2
- ValueError: need at least one array to stack HOT 3
- 关于RPN网络softmax HOT 2
- connection error HOT 1
- Can I test this model for real-time object detection? Is there a demo for it? HOT 1
- Without the incoming socket you cannot receive events from the server or register event handlers to your Visdom client. HOT 4
- In train.py line: 76
- 训练过程的loss HOT 2
- train mine dataset had an error!!! HOT 2
- Visdom and aws Sagemaker - output ?
- 训练好的模型在哪里保存啊? HOT 1
- out of memory 训练的时候显存一直在增长 HOT 4
- 怎么打印fps HOT 1
- step by step understanding approximate joint training method #192 HOT 5
- approximate joint training method problem
- How can I cite your work in my thesis?
- Convert to onnx
- Dependencies versions
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 simple-faster-rcnn-pytorch.