|
|
@@ -96,23 +96,23 @@ This is a deep learning based model. More specifically, what I've done is combi
|
|
|
|
|
|
The beauty of this model is that it should be generally useful for all sorts of image modification, and it should do it quite well. What you're seeing above are the results of the colorization model, but that's just one component in a pipeline that I'm looking to develop here with the exact same model.
|
|
|
|
|
|
-What I develop next with this model will be based on trying to solve the problem of making these old images look great, so the next item on the agenda for me is the "defade" model. I've committed initial efforts on that and it's in the early stages of training as I write this. Basically it's just training the same model to reconstruct images that augmented with ridiculous contrast/brightness adjustments, as a simulation of fading photos and photos taken with old/bad equipment. I've already seen some promissing results on that as well:
|
|
|
+What I develop next with this model will be based on trying to solve the problem of making these old images look great, so the next item on the agenda for me is the "defade" model. I've committed initial efforts on that and it's in the early stages of training as I write this. Basically it's just training the same model to reconstruct images that augmented with ridiculous contrast/brightness adjustments, as a simulation of fading photos and photos taken with old/bad equipment. I've already seen some promising results on that as well:
|
|
|
|
|
|
|
|
|
|
|
|
### This Project, Going Forward
|
|
|
-So that's the gist of this project – I'm looking to make old photos look reeeeaaally good with GANs, and more importantly, make the project *useful*. And yes, I'm definitely interested in doing video, but first I need to sort out how to get this model under control with memory (it's a beast). It'd be nice if the models didn't take two to three days to train on a 1080TI as well (typical of GANs, unfortunately). In the meantime though this is going to be my baby and I'll be actively updating and improving the code over the forseeable future. I'll try to make this as user-friendly as possible, but I'm sure there's going to be hiccups along the way.
|
|
|
+So that's the gist of this project – I'm looking to make old photos look reeeeaaally good with GANs, and more importantly, make the project *useful*. And yes, I'm definitely interested in doing video, but first I need to sort out how to get this model under control with memory (it's a beast). It'd be nice if the models didn't take two to three days to train on a 1080TI as well (typical of GANs, unfortunately). In the meantime though this is going to be my baby and I'll be actively updating and improving the code over the foreseeable future. I'll try to make this as user-friendly as possible, but I'm sure there's going to be hiccups along the way.
|
|
|
|
|
|
Oh and I swear I'll document the code properly...eventually. Admittedly I'm *one of those* people who believes in "self documenting code" (LOL).
|
|
|
|
|
|
### Getting Started Yourself
|
|
|
-The easest way to get started is to simply try out colorization here on Colab: https://colab.research.google.com/github/mc-robinson/DeOldify/blob/master/DeOldify_colab.ipynb . This was contributed by Matt Robinson, and it's simply awesome.
|
|
|
+The easiest way to get started is to simply try out colorization here on Colab: https://colab.research.google.com/github/mc-robinson/DeOldify/blob/master/DeOldify_colab.ipynb . This was contributed by Matt Robinson, and it's simply awesome.
|
|
|
|
|
|
This project is built around the wonderful Fast.AI library. Unfortunately, it's the -old- version and I have yet to upgrade it to the new version. (That's definitely on the agenda.) So prereqs, in summary:
|
|
|
* ***Old* Fast.AI library** [**UPDATE 11/7/2018**] Easiest thing to do in my mind is just to take the fastai/fastai folder and drop it in the root of this project, right next to fasterai's folder. Just today, I found this thread on installing fast.ai 0.7- This is probably your best resource on this subject! https://forums.fast.ai/t/fastai-v0-7-install-issues-thread/24652 . Do this first- this will take you most of the way, including dependencies.
|
|
|
* **Pytorch 0.4.1** (needs spectral_norm, so latest stable release is needed). https://pytorch.org/get-started/locally/
|
|
|
* **Jupyter Lab** `conda install -c conda-forge jupyterlab`
|
|
|
-* **Tensorboard** (i.e. install Tensorflow) and **TensorboardX** (https://github.com/lanpa/tensorboardX). I guess you don't *have* to but man, life is so much better with it. And I've conveniently provided hooks/callbacks to automatically write all kinds of stuff to tensorboard for you already! The notebooks have examples of these being instantiated (or commented out since I didn't really need the ones doing histograms of the model weights). Noteably, progress images will be written to Tensorboard every 200 iterations by default, so you get a constant and convenient look at what the model is doing. `conda install -c anaconda tensorflow-gpu`
|
|
|
+* **Tensorboard** (i.e. install Tensorflow) and **TensorboardX** (https://github.com/lanpa/tensorboardX). I guess you don't *have* to but man, life is so much better with it. And I've conveniently provided hooks/callbacks to automatically write all kinds of stuff to tensorboard for you already! The notebooks have examples of these being instantiated (or commented out since I didn't really need the ones doing histograms of the model weights). Notably, progress images will be written to Tensorboard every 200 iterations by default, so you get a constant and convenient look at what the model is doing. `conda install -c anaconda tensorflow-gpu`
|
|
|
* **ImageNet** – Only if training of course. It proved to be a great dataset. http://www.image-net.org/download-images
|
|
|
* **BEEFY Graphics card**. I'd really like to have more memory than the 11 GB in my GeForce 1080TI (11GB). You'll have a tough time with less. The Unet and Critic are ridiculously large but honestly I just kept getting better results the bigger I made them.
|
|
|
* **Linux** (I'm using Ubuntu 16.04) is assumed, but nothing from the above precludes Windows 10 support as far as I know. I just haven't tested it and am not going to make it a priority for now.
|
Jason Antic