Comments (7)
my env:
python: 3.6
tf: 1.8
keras: 2.2
I also faced same problem. and sovled it.
model.save('./model/nn4.small2.lrn.h5')
using python 2.7- load nn4.small2.lrn.h5 and save
model.save_weights('weight.h5')
- create model structure file: https://gist.github.com/tkwoo/a9da631b3f7d437b8961a7d5276a6087
model = facenet_keras.facenet()
model.load_weights('weight.h5')
from keras-openface.
@dgolano You should use python 2.7 .
I also got the same error related to bad marshal.
Now I am able to load these model without any error.
My current version are
python - 2.7.12
keras - 2.1.1
tensorflow- 1.0.0
from keras-openface.
i have same error
from keras-openface.
my environment:
python: 3.5.2
tensorflow: 1.3
cuda: 8.0
from keras-openface.
are you (@beimingmaster ) find a solution for bad marshal problem?
from keras-openface.
!git clone https://github.com/TessFerrandez/research-papers.git
%cd research-papers/facenet
from model import create_model
%cd ../..
#check if '%pwd' prints '/content' if using google colab
#download facenet_keras.py and upload to your colab's 'content/' direcory #https://gist.github.com/tkwoo/a9da631b3f7d437b8961a7d5276a6087
import facenet_keras
model = facenet_keras.facenet()
from keras-openface.
Actually, now that tensoflow absorbed keras, we should make the respective modifications:
keras -> tensorflow.keras
and replace all things like keras.layers.* by keras.layers
from keras-openface.
Related Issues (20)
- Try Triplet Semihard loss and online triplet mining
- dataset and model HOT 2
- Loss funtion of nn4.small2.lrn.h5 ?
- How to save the keras model with model architecture and weights? HOT 2
- Does it predict face pose? HOT 2
- Can I use this for Commercial Applications ? HOT 4
- Generator
- Can I use it for one shot face authentication ? HOT 2
- I can't find network structure of nn4_small2_v1.I am a beginner. where,thank you.
- Can this model detect the line of sight?
- accuracy of pre-trained weights
- i got nan value on loss after training
- The squared l2 distance values are different from that of official OpenFace demos. HOT 2
- How train model from scratch? HOT 4
- How to apply this to custom classification?
- Very slow embeddings generation
- How was you generate the reps2.csv
- image transform before processing
- Generating the embedding for feature extraction
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-openface.