alexstaravoitau / kaggle-facial-keypoints-detection Goto Github PK
View Code? Open in Web Editor NEWKaggle "Facial Keypoints Detection" competition.
Home Page: http://navoshta.com/facial-with-tensorflow/
Kaggle "Facial Keypoints Detection" competition.
Home Page: http://navoshta.com/facial-with-tensorflow/
Dear Alex,
I'm trying use this kaggle tutorial to find keypoints on a image: I've followed the tutorial '3con_2fc_b36_e1000_aug_lrdec_mominc_dr'
But i'm trying to use this trained model on a different image.
This first thing that i've tried is to get the first image of the training data is a 'numpy.ndarray' with a image, but this shows a black canvas. This shows a 96x96 black image
print(type(X[0]))
img = X[0].reshape(96, 96)
imgPIL = Image.fromarray(img)
imgPIL.show()
After that i've tried to pass a image to the model
from PIL import Image
..
graph = tf.Graph()
with graph.as_default():
# Training computation.
with tf.variable_scope(model_variable_scope):
img = Image.open("image.jpg")
image_np = np.array(img.getdata(),np.uint8).reshape(img.size[1], img.size[0],3) # rgb
model_pass(image_np, False)
This results in this error:
ValueError: cannot reshape array of size 16900 into shape (96,96)
Would you please help me?
With kind regards,
Dion from The Netherlands
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.