Comments (12)
Doesn't that require pre-trained weights? I can work on porting over resnet50 weights. Not sure about others. Do you know if Kaiming He has pretrained weights for all resnet configurations? If yes, we could try and port those over.
from keras-resnet.
there are a bunch of pretrained weights floating around. I'm sure just one set of weights would be enough for them to accept the request for the first version. I mean, your functions let you generate arbitrary sized resnets so one certainly wouldn't be expected to make them all. :-)
from keras-resnet.
Ok. I'll give it a shot. Do you know of any projects for converting caffe models? I see a bunch of them floating around. Not sure which one to use.
from keras-resnet.
What may be the easiest option is to simply convert the ones from the tensorflow slim models repository.
They have a resnet implementation and links to their pre-trained models which they already converted into tensorflow.... nvm that is resnet v1, they don't have resnet v2 up...
pretrained resnet v2 (w/pre activations) weights in torch t7 format
Well here are the resnet v2 models torch weights that are trained by a grad student under the supervision of the original author (as you may know he moved from microsoft research to facebook):
https://github.com/facebook/fb.resnet.torch/tree/master/pretrained
Actually, it looks pretty simple to move the weights from tensorflow to h5f, and it seems
https://github.com/Moodstocks/inception-v3.torch/blob/master/dump_filters.py
Those are in torch format, and I'd bet the deepmind implementation of conversion is very likely to work:
https://github.com/deepmind/torch-hdf5
From there I believe keras can load hdf5 by name.
from keras-resnet.
Cool. I will try to get to this in after december. In the mean time, if any of you guys have time, feel free to take a stab at this. It would be cool to convert all the torch models.
from keras-resnet.
looks like based on the description some of the weights were already transferred in here: https://github.com/fchollet/deep-learning-models so it might be worth asking if there is code that was used to do the conversion that could be reused
from keras-resnet.
I have an old script which can convert t7 file to keras model, maybe I can try to get it work again. The problem is there's no easy way to map between the layers created from touchfile and an existing keras model, so some adhoc logic is needed so that we can know which weight is for which layer in the existing model.
Also if I remember correctly I had a hard time reproducing the image preprocessing logic from touch.
from keras-resnet.
I believe the most appropriate place for this now might be keras-contrib:
https://github.com/farizrahman4u/keras-contrib
from keras-resnet.
I've taken first steps towards this at keras-team/keras-contrib#148
from keras-resnet.
Thanks, @ahundt. I have been super busy at work lately.
from keras-resnet.
@ahundt Did you ever find the pretrained weights for some of the architectures you have for keras-contrib?
from keras-resnet.
no, I haven't been using ResNets directly recently
from keras-resnet.
Related Issues (20)
- Should we watch val_loss or val_acc in callbacks? HOT 2
- Spec requirement for running resnet152 HOT 1
- Model cannot add original to filtered data.
- Error CNTK
- Training loss reduces sooo slow
- image prediction HOT 2
- possible bug between residual unit and shortcut HOT 1
- Last layer activation HOT 1
- TimeDistributed wrapping causing issues
- about data provider HOT 1
- Stuck in first epoch
- Where is the model saved? HOT 2
- inference image preprocessing HOT 1
- Merging before BM and Pool__resnet50
- TypeError: __init__() takes at least 4 arguments (1 given)
- Problem of funtion _shortcut HOT 1
- Why Conv2_1 has stride of (1,1)?
- Some questions about feature map size matching.
- AttributeError: module 'resnet' has no attribute 'ResnetBuilder' HOT 2
- Why does epochs stop at 56 times?
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 keras-resnet.