dali92002 / de-gan Goto Github PK
View Code? Open in Web Editor NEWDocument Image Enhancement with GANs - TPAMI journal
License: GNU General Public License v3.0
Document Image Enhancement with GANs - TPAMI journal
License: GNU General Public License v3.0
C:\ProgramData\anaconda3\python.exe "C:\Users\irfan\OneDrive\Desktop\image enhancement\DE-GAN-master\enhance.py"
Traceback (most recent call last):
File "C:\Users\irfan\OneDrive\Desktop\image enhancement\DE-GAN-master\enhance.py", line 15, in
task = sys.argv[1]
~~~~~~~~^^^
IndexError: list index out of range
Process finished with exit code 1
can anyone tell me how to solve this?
The model is not converging for the stated datasets till 300 epochs with the training setup mentioned in the repo. Can you point us to the right settings for training the model?
Hi,
Thanks for sharing your work! I wonder if you're planning to add the codes for the degraded documents clean up?
Thanks,
Hi,
I trained the model on DIBCO data without changing the code. But the model generated nearly all black/grey images after the first one or two epochs. Do you have any idea about it?
Bests
Hello, DE-GAN author.I used watermark text dataset provided by you to train the model without changing any parameters in the model.But it seems doesn't work beacause the PSNR has always been below 1 and predict images are all black or white until I stop running in epoch 36.Can you please tell me where the problem is? Thank you!!!
Is there a way to run the inference on GPU?
could you provide an idea of how can I train with my custom data?
Traceback (most recent call last):
File "train.py", line 303, in
generator.load_weights("weights_org/watermark_rem_weights.h5")
File "/home/ubuntu/.local/lib/python3.6/site-packages/tensorflow/python/keras/engine/training.py", line 250, in load_weights
return super(Model, self).load_weights(filepath, by_name, skip_mismatch)
File "/home/ubuntu/.local/lib/python3.6/site-packages/tensorflow/python/keras/engine/network.py", line 1266, in load_weights
hdf5_format.load_weights_from_hdf5_group(f, self.layers)
File "/home/ubuntu/.local/lib/python3.6/site-packages/tensorflow/python/keras/saving/hdf5_format.py", line 707, in load_weights_from_hdf5_group
K.batch_set_value(weight_value_tuples)
File "/home/ubuntu/.local/lib/python3.6/site-packages/tensorflow/python/keras/backend.py", line 3384, in batch_set_value
x.assign(np.asarray(value, dtype=dtype(x)))
File "/home/ubuntu/.local/lib/python3.6/site-packages/tensorflow/python/ops/resource_variable_ops.py", line 846, in assign
self._shape.assert_is_compatible_with(value_tensor.shape)
File "/home/ubuntu/.local/lib/python3.6/site-packages/tensorflow/python/framework/tensor_shape.py", line 1117, in assert_is_compatible_with
raise ValueError("Shapes %s and %s are incompatible" % (self, other))
ValueError: Shapes (3, 3, 256, 512) and (256, 256, 3, 3) are incompatible
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.