Comments (3)
Also, I should point out that when I try to try a decay
value of 0.0
, the network is kinda close in accuracy, but not really (it doesn't come that close to what would be expected given that the loss is so good during training; this probably isn't a case of overfitting as I'm testing, for now, on the same images that I've trained on).
Also, off topic, but I love this framework. It's a shame that PFN gave up on it. I find PyTorch to be spaghetti code.
from chainer.
Using the recommended 1.17 (well, 1.17.3) version of NumPy doesn't seem to help.
from chainer.
I wrote my own variant of Batch Normalization, and it appears to be having similar issues both evaluating on the network that is left in memory right after training as well as one loaded from disk (aka deserialized). I think this means that there isn't an issue with Chainer's BatchNormalization, but rather an issue with my network (or dataset).
from chainer.
Related Issues (20)
- Replace URLs to cupy.dev HOT 1
- How about matching weight indices of LSTM in the docstring to implementation? HOT 2
- ZeroDivisionError: division by zero HOT 3
- Can't use chainer in W10 with CUDA 11.1 HOT 5
- cupy_9.0.0a1 support HOT 1
- Broken release version 1.5.0 HOT 3
- cuslover causes memory overrun while calling syevjBatched HOT 1
- ValueError: Inexistent group is specified HOT 2
- module 'cupy.cuda' has no attribute 'cudnn' HOT 1
- Experimental support for CuPy v8 in Chainer v7 HOT 2
- No module named 'cupy.util' HOT 1
- cupy.cuda.cudnn.CuDNNError: cuDNN Error: CUDNN_STATUS_BAD_PARAM HOT 1
- Incorrect reading of MNIST Images HOT 1
- There is no mish activation function in chainer.functions. Also I noticed that all the activations have not been added to chainer.links.activations. Can I work on the mish function and also add the activations to links.activations ?
- import chainer error: 'raise TypeError(f"{cls} is not a generic class")' HOT 2
- cupy version constraints HOT 1
- can't use chainer with new cupy, can't install old cupy HOT 1
- How to fix some network parameters in training to achieve fine tuning?
- Porting To SYCL
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 chainer.