czhu95 / ternarynet Goto Github PK
View Code? Open in Web Editor NEWImplementation for Trained Ternary Network.
License: Apache License 2.0
ternarynet's People
Contributors
Stargazers
Watchers
Forkers
liuguoyou airjimmy89 oppa3109 canbuoy whsz6 weijingshi ningyixu robert-junwang 6676401088 kaix90 skoppula antsaharinala phenixi mottotime rudychin xuyibo2013 wang-mengjiao shubhampachori12110095 huanhuanzhang hanzz2007 xtanitfy csuyz haoshuji yujunfeng afcarl arcadia-1 ewenwan minhson zyazz saums lxwithgod mengxiangming 666dzy666 shaoyandea singadk bbalimbatuhan cyber-neuron jpl24hub 10555gffternarynet's Issues
Traceback was occured at cifar10 training.
Hi Chenzhuo!
I tried to train cifar10 by
python ./tw-cifar10-resnet.py --gpu 0
But, Traceback was occured.
Traceback (most recent call last):
File "./tw-cifar10-resnet.py", line 213, in <module>
config = get_config(args.n)
File "./tw-cifar10-resnet.py", line 197, in get_config
model=Model(n=nsize),
TypeError: Can't instantiate abstract class Model with abstract methods _get_inputs
My environment were below.
by conda install.
freetype 2.5.5 2
h5py 2.7.0 np112py36_0
hdf5 1.8.17 1
jbig 2.1 0
jpeg 8d 2
libgfortran 3.0.0 1
libpng 1.6.27 0
libprotobuf 3.2.0 0
libsodium 1.0.10 0
libtiff 4.0.6 2
lmdb 0.9.18 0
mkl 2017.0.1 0
msgpack-numpy 0.3.9 <pip>
msgpack-python 0.4.8 py36_0
nltk 3.2.2 py36_0
numpy 1.12.1 py36_0
opencv 3.1.0 np112py36_1
openssl 1.0.2k 2
pillow 3.4.2 py36_0
pip 9.0.1 py36_1
protobuf 3.2.0 py36_0
protobuf 3.3.0 <pip>
python 3.6.1 2
pyzmq 16.0.2 py36_0
readline 6.2 2
scipy 0.19.0 np112py36_0
setuptools 27.2.0 py36_0
six 1.10.0 py36_0
sqlite 3.13.0 0
tabulate 0.7.7 <pip>
tensorflow 1.1.0 np112py36_0
tensorpack 0.1.9 <pip>
termcolor 1.1.0 <pip>
tk 8.5.18 0
tqdm 4.11.2 py36_0
werkzeug 0.12.2 py36_0
Werkzeug 0.12.2 <pip>
wheel 0.29.0 py36_0
xz 5.2.2 1
zeromq 4.1.5 0
zlib 1.2.8 3
by pip install
appdirs (1.4.3)
h5py (2.7.0)
msgpack-numpy (0.3.9)
msgpack-python (0.4.8)
nltk (3.2.2)
numpy (1.12.1)
packaging (16.8)
Pillow (3.4.2)
pip (9.0.1)
protobuf (3.3.0)
pyparsing (2.2.0)
pyzmq (16.0.2)
scipy (0.19.0)
setuptools (35.0.2)
six (1.10.0)
tabulate (0.7.7)
tensorflow (1.1.0)
tensorpack (0.1.9)
termcolor (1.1.0)
tqdm (4.11.2)
Werkzeug (0.12.2)
wheel (0.29.0)
Monkey patch is not useful in current version (tensorpack 0.8.5, TensorFlow 1.3.0)
Hi Chenzhuo, @czhu95
The monkey-patch way to replace tf.get_variable is not useful in current version (tensorpack 0.8.5, TensorFlow 1.3.0). Codes can not generate Wn and Wp under above-mentioned platform.
Best regards,
Shangyu
关于阈值delta的问题？
您好，论文中做ternary之前，先对weight进行归一化，即除以最大的abs(w)归一化到[-1, 1]。
根据论文中设定threshold的方法
weight已经归一化，最大的max(abs(w))是1，因此delta就是t，也就是文中的0.05。
请问是这样吗？谢谢
Alexnet+Imagenet training
Hi Chenzhuo,
I was studying your Ternarynet work and was trying to run the Alexnet+Imagenet training.
'python ./tw-imagenet-alexnet.py --gpu 0,1,2,3 --data MY_IMAGENET_PATH' {I have arranged the data in the format expected by the ILSVRC12()}
I got the following AssertionError:
Command protoc caffe.proto --python_out . failed!
Where is it actually looking for caffe.proto? Is Caffe installation required for it to run?
Thanks and regards.
build_prune not in repository (example is non-reproducible)
Hi there,
I'm trying to re-run p-cifar10-resnet.py, but I'm unable to find build_prune
Is this included in the repository?
Thanks
Reproduced ResNet18 CIFAR10 result is 10% lower than reported
Hi @czhu95 ,
Thanks for providing the codes!
Recently I use your codes to ternarize a ResNet18 using CIFAR10. Firstly I use tensorpack to train a ResNet18 to validation error as 0.083. However, when I apply this as initial status and ternarize (using the example codes), as I use the default delta t=0.05 in your code, the validation error is always around 0.1843. I tried other t but it is still around 0.18, which is about 10% lower than your paper report.
Is there any tricks or mistake I made?
Best regards,
Shangyu
resnet fine-tuned models
Hi @czhu95 ,
Thanks for your interesting work. I ran your code to reproduce your results of resnet on Cifar-10 from scratch. However I see the results are not similar as you reported because it might be not using finetune models of ResNet. How can I download finetuned models?
Thanks,
Hai
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.