I'm an Experienced AI Engineer with over 10 years of hands-on experience in applying deep and shallow machine learning methods for solving tasks in the fields of:
- Time Series
- Computer Vision
- Natural Language Processing
- Data Mining
Keras implementation of "Image Inpainting via Generative Multi-column Convolutional Neural Networks" paper published at NIPS 2018
License: MIT License
Hi,
Thank you so much for publishing the Keras implementation of gmcnn on Github.
Can you also provide the code for testing the model?
Hi,
I'm trying to test this inpainting alternative. I'm using code from branch tensorflow-1.15.2 and when execute runner.py this run only one step of training.
In the outputs folder, I see only step_000.png
Do you know why?
Thanks
Hi,
I'm trying to run the colab notebook but I keep getting the following error when running this line:
Actually it first gives an error saying --experiment_name
is required, but after passing that arg in I get the error below
!python inpainting-gmcnn-keras/runner.py --train_path images --mask_path mask -warm_up_generator --experiment_name tester
Traceback (most recent call last): File "inpainting-gmcnn-keras/runner.py", line 105, in <module> main() File "inpainting-gmcnn-keras/runner.py", line 52, in main config = main_config.MainConfig(MAIN_CONFIG_FILE) File "/content/inpainting-gmcnn-keras/config/main_config.py", line 22, in __init__ self.model = ModelConfig(model_config['MODEL']) File "/content/inpainting-gmcnn-keras/config/main_config.py", line 41, in __init__ self.add_mask_as_generator_input = parse_bool(model_section['ADD_MASK_AS_GENERATOR_INPUT']) File "/usr/lib/python3.6/configparser.py", line 1233, in __getitem__ raise KeyError(key) KeyError: 'ADD_MASK_AS_GENERATOR_INPUT'
outputs file is not being made, not able to get output
Please help me in that
Hi,
I hope you still give support for this repository. I tried converting this repository model to Tensorflow 2x step by step (also following the original repository by shepnerd). I think everything was fine, but when training and testing the model the results were not very satisfactory. So, maybe there is a problem with my conversion that I can't find it. I tried to train the model on a small subset of OpenImages V6. The principal parameters that I used (sorry, because names can be slightly different than yours):
--img_size 256x256x3
--batch_size 4
--learning_rate 1e-4
--gaussian_steps 7
--gaussian_kernel_size 32
--gaussian_kernel_std 20.0
--reconstruction_loss_weight 1.2
--adversarial_loss_weight 0.001
--gradient_penalty_loss_weight 10
--id_mrf_loss_weight' 0.03
--nn_stretch_sigma 0.5
--id_mrf_style_weight 1.0
--id_mrf_content_weight 1.0
I pretrained the model with only confidence reconstruction loss for the recommended steps, and results for this phase seem fine.
![imagen](https://
user-images.githubusercontent.com/39574343/111080637-a3871d00-84ff-11eb-90cb-c6de09d587f6.png)
However, in the training phase, after some steps, the results do not seem to converge and eliminate the mask.
I would like to know if you have any idea of what could be happening, or you have experienced any similar issue. I reviewed the code, networks, and losses many times, but could not find any solution.
Thank you very much.
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.