Comments (2)
I just found the repo of one of the authors (Sachin Goyal), in which the following snippet could be found in cifar/code/train_cifar_pgd.py:
#LR SCHEDULER
def adjust_learning_rate(optimizer, epoch, args):
"""decrease the learning rate"""
lr = args.lr
if epoch <= args.epochs:
lr = args.lr * 0.01
if epoch <= 0.80*args.epochs:
lr = args.lr * 0.1
if epoch <= 0.40*args.epochs:
lr = args.lr
for param_group in optimizer.param_groups:
param_group['lr'] = lr
which hints at the used learning rate scheduler for the CIFAR-10 experiment. The can easily be replaced by a torch.lr_scheduler.StepLR
scheduler with step_size=0.4*n_epochs
and gamma=0.1
, where n_epochs
is the total number of epochs.
However, the arguments for lr_scheduler
in drocc_trainer.py suggests that the learning rate may be different for the "pretraining" (without adversarial loss) phase.
I suppose I can experiment a bit with it, but I definitely think that the lr_scheduler utilized in drocc_trainer.py should be either removed or properly explained, and I would much appreciate some clarification on the parameters used during the experiments.
Cheers!
from edgeml.
Hi @mpierrau ,
Thanks for your interest in our work.
1)The LR scheduler used has been specified in the examples file.
For example : for CIFAR : here
2)We havent used the standard torch StepLR just for the simple reason that we didnt want to consider the initial "pretraining" warm up steps (without adversarial phase) as you correctly pointed out. The learning rate for pretraining is not different, but constant and equal to the specified initial LR.
I believe reading the code snippet linked above (linking here again) should clarify all your doubts.
Feel free to reach out for further queries.
Thanks
-Sachin
from edgeml.
Related Issues (20)
- Exception: FastGRNNCUDA is supported only on GPU devices. HOT 6
- Inference Code to deploy KWS on bluecoin HOT 2
- Question about F1 score for Cifar-10 HOT 5
- Error while converting .onnx model to .pb format HOT 2
- Question about Bonsai training HOT 2
- KWS-demo throwing errors on running FastGRNNCUDA inference on google speech commands dataset HOT 1
- Seedot HOT 7
- How to predict a Test Sample? HOT 5
- SeeDot-dev.py only working for fastgrnn HOT 22
- The model of DROCC seems missing HOT 3
- How to get predictions from trained model for FastCells in Tensorflow HOT 3
- Why Bonsai and ProtoNN does not return logits but only the argmax of predictions? HOT 1
- For Image Anomaly, custom dataset HOT 6
- Select protoypes without projecting
- This repo is missing important files HOT 1
- Why is the GRNN much slower than a GRU HOT 1
- ImageNet-10 dataset RNN-Pooling HOT 1
- This repo is missing important files “process_g30.py”
- Missing important codes in the file https://github.com/microsoft/EdgeML/tree/master/tools/SeeDot/SeeDot-dev.py
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 edgeml.