Comments (3)
It converges for me when I set the learning rate to 0.01 for the first epoch. You''ll need to modify Trainer:learningRate to get that behavior:
https://github.com/facebook/fb.resnet.torch/blob/master/train.lua#L169
from fb.resnet.torch.
Right, so this is what actually happens with this schedule if training goes on... Have you tried beyond 30 epochs?
from fb.resnet.torch.
Error = 7.3% at epoch 85. Here's a test error curve for ResNets 20,32,44,56,110,1202.
ResNet 1202 is in yellow.
The jump in your error rate around epoch 28 is really strange. Can you post your code?
from fb.resnet.torch.
Related Issues (20)
- dataset.lua,dataset-gen.lua HOT 1
- Random luajit errors
- How Can I Plot the Train Curve ? HOT 2
- running time of ResNets HOT 5
- DataSampler.lua:230: bad argument #3 to 'narrow'
- Missing batch norm in ResNet-18 weights HOT 1
- Retrain with different input size
- Can I use video or webcam to classify ? (I have a fine-tuned model with my own data.) HOT 1
- it's my code but i don't why it's show me this error...
- What are the settings of pretrained ResNet-101 and ResNet-152 model files? HOT 2
- How to extract the lower level feature with pretrained model?
- INIT.LUA not found
- How to control the CPU kernels that are used during training.
- Can not reach the validation error rate for Resnet-50 (single-crop 224*224) HOT 1
- TestOnly on different machines give different results HOT 1
- Using cifar-100 with 15 classes HOT 7
- nn
- CMake error while running install.sh HOT 7
- running lua in Pytorch HOT 1
- I want to retrain a resnext_101_32*4d.Is it possible?
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 fb.resnet.torch.