huidingumd / exprgan Goto Github PK
View Code? Open in Web Editor NEWFacial Expression Editing with Controllable Expression Intensity
Facial Expression Editing with Controllable Expression Intensity
Thank you for sharing your codes. But I happen to have an error: No such file or directory: '../data/OULU/P008/Surprise/028.jpeg'
Would you please tell me where can I get the test dataset ? Thank you!
Do you have another way to get it? Thanks.
Hello, I have read your paper and run the model that you released.But it is only generating face with new identity.How to generate the input identity face image? Where do I need to change the code?
Hi,
Thanks for sharing your exciting research. What is the license for usage? Is it MIT?
the trained model's not compatible with the exisitng code (it's got a lower producer version of 17 for the existing graph of version 26)- it's creating shape inference issues.
I thought of training the model with the oulu dataset, but the person I should contact for getting the access to the dataset is missing or unreachable. Does anyone have the downloaded dataset that they could share so that people can work with this model? Or a way to contact someone to get the dataset?
Or at least, if they can pass the version of the trained model that can be used with the code itself, it would be very helpful.
Also the code itself has problems with tensorflow 1.6 and above (tf.nn.sigmoid_cross_entropy_with_logits and tf.concat_label )
I have been trying to reproduce your result but couldn't manage to do so. In addition, I wanted to see if I could create some photos but doesn't seem gto work neither ( I don't see which part is able to do so).
Thanks in advance
Hi, may I know which version of the tensorflow you use for the implementation?
Thank you.
Hi,
I wanted to try out your expr gan and I downloaded the models. Your test_oulu.sh has a main_simple_vgg_mul.py and I am unable to find this file in your repo?
I am using Tensor Flow version 1.12 and Python 3.6.
I don't know how to fix this error.
Traceback (most recent call last):
File "/home/math01/exprgan/joint-train/main.py", line 58, in
tf.app.run()
File "/home/math01/anaconda3/envs/py363/lib/python3.6/site-packages/tensorflow/python/platform/app.py", line 125, in run
_sys.exit(main(argv))
File "/home/math01/exprgan/joint-train/main.py", line 46, in main
num_epochs=FLAGS.epoch, # number of epochs
File "/home/math01/exprgan/joint-train/exprgan.py", line 267, in train
var_list=self.E_variables + self.G_variables
File "/home/math01/anaconda3/envs/py363/lib/python3.6/site-packages/tensorflow/python/training/optimizer.py", line 410, in minimize
name=name)
File "/home/math01/anaconda3/envs/py363/lib/python3.6/site-packages/tensorflow/python/training/optimizer.py", line 593, in apply_gradients
self._create_slots(var_list)
File "/home/math01/anaconda3/envs/py363/lib/python3.6/site-packages/tensorflow/python/training/adam.py", line 135, in _create_slots
self._zeros_slot(v, "m", self._name)
File "/home/math01/anaconda3/envs/py363/lib/python3.6/site-packages/tensorflow/python/training/optimizer.py", line 1139, in _zeros_slot
new_slot_variable = slot_creator.create_zeros_slot(var, op_name)
File "/home/math01/anaconda3/envs/py363/lib/python3.6/site-packages/tensorflow/python/training/slot_creator.py", line 183, in create_zeros_slot
colocate_with_primary=colocate_with_primary)
File "/home/math01/anaconda3/envs/py363/lib/python3.6/site-packages/tensorflow/python/training/slot_creator.py", line 157, in create_slot_with_initializer
dtype)
File "/home/math01/anaconda3/envs/py363/lib/python3.6/site-packages/tensorflow/python/training/slot_creator.py", line 65, in _create_slot_var
validate_shape=validate_shape)
File "/home/math01/anaconda3/envs/py363/lib/python3.6/site-packages/tensorflow/python/ops/variable_scope.py", line 1487, in get_variable
aggregation=aggregation)
File "/home/math01/anaconda3/envs/py363/lib/python3.6/site-packages/tensorflow/python/ops/variable_scope.py", line 1237, in get_variable
aggregation=aggregation)
File "/home/math01/anaconda3/envs/py363/lib/python3.6/site-packages/tensorflow/python/ops/variable_scope.py", line 540, in get_variable
aggregation=aggregation)
File "/home/math01/anaconda3/envs/py363/lib/python3.6/site-packages/tensorflow/python/ops/variable_scope.py", line 492, in _true_getter
aggregation=aggregation)
File "/home/math01/anaconda3/envs/py363/lib/python3.6/site-packages/tensorflow/python/ops/variable_scope.py", line 879, in _get_single_variable
"reuse=tf.AUTO_REUSE in VarScope?" % name)
ValueError: Variable E_conv0/w/Adam/ does not exist, or was not created with tf.get_variable(). Did you mean to set reuse=tf.AUTO_REUSE in VarScope?
Process finished with exit code 1
can you share the oulu dataset?
i emailed the one on the dataset website but got no reply..
so can you share this dataset?
hi,can you tell me,when public the model (FaceNet2ExpNet: Regularizing a Deep Face Recognition Net for
Expression Recognition)
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 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. 📊📈🎉
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 ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.