kuc2477 / pytorch-deep-generative-replay Goto Github PK
View Code? Open in Web Editor NEWPyTorch implementation of "Continual Learning with Deep Generative Replay", NIPS 2017
License: MIT License
PyTorch implementation of "Continual Learning with Deep Generative Replay", NIPS 2017
License: MIT License
Can incremental learning be achieved, that is to say, if a model can recognize a picture as a cat or a dog, it is necessary to add new categories on this basis and only train new categories without retraining all data?
I had problems running the code initially. The first problem that I encountered was "ImportError: cannot import name 'ImageOps' ". I solved it by changing it to "from PIL import ImageOps". The second problem I had has something to do with visdom which I solved it by removing all related codes.
Hopefully the above information help someone who would like to run this code.
If anyone can provide codes that are compatible with newer PyTorch (either 0.4.1 or 1.0), Please share it !
not in real life,
in minecraft
Kindly help as to how to extract more than two variables (x,y) using default_collate in label_squeezing_collate_fn in utils.py.
During the periodic evaluation, the solver model is utilized but the model is still in .train() mode. It might affect the training process.
I found that training loss for generator and critic will quickly explode and the accuracy can't achieve the one represented in the paper. Is it because unfit training hyperparameter? Btw, I modified the code to make it trainable with newer version pytorch.
Hi,
I am facing the foll. issue using the pytorch, torchvision, and PIL versions (because of compatibility requirement with cuda 10.1) as:
torch: 1.4.0
torchvision: 0.5.0
PIL: 5.2.0
Traceback (most recent call last):
File "./main.py", line 186, in
cuda=cuda
File "/home/js/DGR_pytorch/train.py", line 102, in train
collate_fn=collate_fn,
File "/home/js/DGR_pytorch/dgr.py", line 130, in train_with_replay
collate_fn=collate_fn,
File "/home/js/DGR_pytorch/dgr.py", line 205, in _train_batch_trainable_with_replay
callback(trainable, progress, batch_index, result)
File "/home/js/DGR_pytorch/train.py", line 157, in cb
result['g_loss'], 'generator g loss', iteration, env=env
File "/home/js/DGR_pytorch/visual.py", line 87, in visualize_scalar
[name], name, iteration, env=env
File "/home/js/DGR_pytorch/visual.py", line 92, in visualize_scalars
assert len(scalars) == len(names)
File "/home/js/anaconda3/envs/env_con/lib/python3.5/site-packages/torch/tensor.py", line 445, in len
raise TypeError("len() of a 0-d tensor")
TypeError: len() of a 0-d tensor
Kindly suggest an alternative. Thank you.
A declarative, efficient, and flexible JavaScript library for building user interfaces.
๐ Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. ๐๐๐
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google โค๏ธ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.