phamphituan / frc2019vision Goto Github PK
View Code? Open in Web Editor NEWThis project forked from justinb4003/frc2019vision
This project forked from justinb4003/frc2019vision
Step 1 is to convert to an infrence model like this: retinanet-convert-model resnet50_csv_02.h5 resnet02_inf.h5 # OPTIONAL -- NOT BEING USED RIGHT NOW # We don't need the pb/protobuf file format if we stick with keras the whole way through. Seems to be working # with the h5 model. Then we convert from inference to pb apparently.. found this one: python keras_to_tensorflow.py --input_model=./snapshots-old/resnet02_inf.h5 --output_model=output.pb --quantize=True ... didn't work. PUll new code from git to make sure we're running the right stuff. Ran that, exit_ok error in mkdir command... that only happens in python2 though, switch to python3 Now we have invalid keywoard freeze argument which has to do with loading the resnet model I think... ... Follow instructions here: amir-abdi/keras_to_tensorflow#57 .... basically change code in keras_to_tensorflow: -------------------------------- I figured in out, this is how its done in keras_to_tensorflow.py Add from keras_retinanet import models Then comment line 62 # model = keras.models.load_model(input_model_path) and add the following like this model = models.load_model(input_model_path, backbone_name="resnet50") ------------------------------ THEN it all works. Excellent! # BACK TO USEFUL STUFF # running keras_proto.py: Make sure you've got the keras-retinanet stuff installed for the active user pip3 install . -- user inside the keras-retinet git repo.. The testing_data/images/*.jpg files hould be in the diretory that keras_proto.py is run from.
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.