nilboy / colorization-tf Goto Github PK
View Code? Open in Web Editor NEWA Tensorflow implementation of ECCV2016 paper([Colorful Image Colorization](https://arxiv.org/pdf/1603.08511.pdf))
A Tensorflow implementation of ECCV2016 paper([Colorful Image Colorization](https://arxiv.org/pdf/1603.08511.pdf))
tf.mul no longer exists (and has been renamed to tf.multiply: https://www.tensorflow.org/api_docs/python/tf/multiply)
I would like to test your model without having to train it first. I see that there is a color_model.ckpt
file provided, but there is meta file with the graph. Is is possible to provide color_model.ckpt.meta
as well?
Traceback (most recent call last):
File "tools/train.py", line 23, in <module>
solver.train_model()
File "./solver.py", line 57, in train_model
new_loss, self.total_loss = self.construct_graph(scope)
File "./solver.py", line 45, in construct_graph
new_loss, g_loss = self.net.loss(scope, self.conv8_313, self.prior_boost_nongray, self.gt_ab_313)
File "./net.py", line 132, in loss
dl2c = tf.stop_gradient(dl2c)
File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/ops/gen_array_ops.py", line 5220, in stop_gradient
"StopGradient", input=input, name=name)
.
.
.
TypeError: Failed to convert object of type <class 'list'> to Tensor. Contents: [None]. Consider casting elements to a supported type.
PS: It seems to me that this script was made using Python 2.7, which tensforflow version do you use?
Could I ask for the dependencies?
Could you show me which version of tensorflow you use?
I would like to ask can the training model handle any size image?
i got an error
ValueError: Only call softmax_cross_entropy_with_logits
with named arguments (labels=..., logits=..., ...)
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.