deblur-gan
deblur-gan copied to clipboard
Keras implementation of "DeblurGAN: Blind Motion Deblurring Using Conditional Adversarial Networks"
What metric can be used to evaluate GANs output?
https://github.com/RaphaelMeudec/deblur-gan/blob/0c0c0296f143b7a070a0969cb64a8774f8e79f1d/train.py#L43 https://github.com/RaphaelMeudec/deblur-gan/blob/0c0c0296f143b7a070a0969cb64a8774f8e79f1d/train.py#L62 **d_loss_fake** always be ZERO?
Can anyone get better result?
WGAN-GP
Hi, Thanks for your contribution, in the paper, author used WGAN-GP as the critic function, but you only used WGAN in your codes, I am wondering how to write WGAN-GP...
``` (Deblur) S:\deblur-gan>python deblur_image.py --image_path=S:\deblur-gan\images\test\a C:\Users\motor\Anaconda3\envs\Deblur\lib\site-packages\h5py\__init__.py:36: FutureWarning: Conversion of the second argument of issubdtype from `float` to `np.floating` is deprecated. In future, it will be treated as `np.float64 == np.dtype(float).type`....
Thanks for your contribution. Here is my problem: When loading a big dataset for training, i find that too much memory is needed. My 128g memory is also not enough....
Bumps [protobuf](https://github.com/protocolbuffers/protobuf) from 3.5.1 to 3.18.3. Release notes Sourced from protobuf's releases. Protocol Buffers v3.18.3 C++ Reduce memory consumption of MessageSet parsing This release addresses a Security Advisory for C++...
Bumps [pillow](https://github.com/python-pillow/Pillow) from 6.2.0 to 9.3.0. Release notes Sourced from pillow's releases. 9.3.0 https://pillow.readthedocs.io/en/stable/releasenotes/9.3.0.html Changes Initialize libtiff buffer when saving #6699 [@radarhere] Limit SAMPLESPERPIXEL to avoid runtime DOS #6700 [@wiredfool]...
Bumps [tensorflow](https://github.com/tensorflow/tensorflow) from 1.5.0 to 2.9.3. Release notes Sourced from tensorflow's releases. TensorFlow 2.9.3 Release 2.9.3 This release introduces several vulnerability fixes: Fixes an overflow in tf.keras.losses.poisson (CVE-2022-41887) Fixes a...
Hi bro. May i know whether the generator.h5 is the complete file which I can run without retraining it?