Adding Dana edits to readme

README.md

@@ -183,13 +183,13 @@ The notebooks should be able to guide you from here.
 -------------------------
 ### Stuff That Should Probably Be In A Paper
 
-#### **How Stable Video Achieved**
+#### **How to Achieve Stable Video**
 
-NoGAN training is crucial to getting the kind of stable and colorful results achieved here. NoGAN training is elaborated on in more detail below but the gist is that it is that it enables getting the benefits of GAN training (wonderful colorization) without the nasty side effects (like flickering objects in video). It just takes 30-60 minutes of the GAN portion of NoGAN training, using 1% to 3% of imagenet data once.  Believe it or not, video is rendered just using isolated image generation without any sort of temporal modeling tacked on.  That is to say, we're literally just DeOldifying individual frames just like we'd do for normal image colorization. 
+NoGAN training is crucial to getting the kind of stable and colorful images seen in this iteration of DeOldify. NoGAN training combines the benefits of GAN training (wonderful colorization) while eliminating the nasty side effects (like flickering objects in video). Believe it or not, video is rendered using isolated image generation without any sort of temporal modeling tacked on. The process performs 30-60 minutes of the GAN portion of "NoGAN" training, using 1% to 3% of imagenet data once.  Then, as with still image colorization, we "DeOldify" individual frames before rebuilding the video.
 
-There's more to the stability however, as I think there's an interesting thing going on here worth mentioning.  It turns out the models I run, even different ones and with different training structures, keep arriving at more or less the same exact solution.  That's even the case for the colorization of things you may think would be arbitrary and unknowable, like the color of clothing, cars, and even special effects in Metropolis.  So I think the models must be learning some interesting rules about how to colorize based on some cues present in the black and white images that I certainly wouldn't expect to exist.  This leads to nicely deterministic and consistent results, and that means you don't have to things like track model colorization decisions because they're not arbitrary.  Additionally, they seem remarkably robust so that even in moving scenes the renders are very consistent.
+In addition to improved video stability, there is an interesting thing going on here worth mentioning. It turns out the models I run, even different ones and with different training structures, keep arriving at more or less the same solution.  That's even the case for the colorization of things you may think would be arbitrary and unknowable, like the color of clothing, cars, and even special effects (as seen in "Metropolis").  My best guess is that the models are learning some interesting rules about how to colorize based on subtle cues present in the black and white images that I certainly wouldn't expect to exist.  This result leads to nicely deterministic and consistent results, and that means you don't have track model colorization decisions because they're not arbitrary.  Additionally, they seem remarkably robust so that even in moving scenes the renders are very consistent.
 
-Other ways to stabilize video add up as well. First, generally speaking rendering at a higher resolution (higher render_factor) will increase stability of colorization decisions.  This stands to reason because the model has higher fidelity image information to work with and will have a greater chance of making the "right" decision consistently.  Closely related to this is the use of resnet101 instead of resnet34 as the backbone of the generator- objects are detected more consistently and corrrectly with this. This is especially important for getting good and consistent skin rendering, which can be particular jarring if it's missed and you wind up with "zombie limbs" and whatnot.
+Other ways to stabilize video add up as well. First, generally speaking rendering at a higher resolution (higher render_factor) will increase stability of colorization decisions.  This stands to reason because the model has higher fidelity image information to work with and will have a greater chance of making the "right" decision consistently.  Closely related to this is the use of resnet101 instead of resnet34 as the backbone of the generator- objects are detected more consistently and corrrectly with this. This is especially important for getting good, consistent skin rendering.  It can be particularly visually jarring if you wind up with "zombie limbs", for example.
 
 Additionally, gaussian noise augmentation during training appears to help but at this point the conclusions as to just how much are bit more tenuous (I just haven't formally measured this yet).  This is loosely based on work done in style transfer video, described here:  https://medium.com/element-ai-research-lab/stabilizing-neural-style-transfer-for-video-62675e203e42.  
 
@@ -198,9 +198,9 @@ Special thanks go to Rani Horev for his contributions in implementing this noise
 -------------------------
 #### **What is NoGAN???**
 
-This is a new type of GAN training that I've developed to solve some key problems in the previous DeOldify model. The gist is that you get the benefits of GAN training while spending minimal time doing direct GAN training.  Instead, most of the training is done pretraining the generator and critic separately with more straight forward, fast and reliable conventional methods. During the very short amount of actual GAN training the generator not only gets the full realistic colorization capabilities that used to take days of progressively resized GAN training, but it also doesn't accrue nearly as much of the artifacts and other ugly baggage of GANs. In fact, you can pretty much eliminate glitches and artifacts almost entirely depending on your approach. As far as I know this is a new technique. And it's incredibly effective. 
+This is a new type of GAN training that I've developed to solve some key problems in the previous DeOldify model. It provides the benefits of GAN training while spending minimal time doing direct GAN training.  Instead, most of the training time is spent pretraining the generator and critic separately with more straight-forward, fast and reliable conventional methods.  A key insight here is that those more "conventional" methods generally get you most of the results you need, and that GANs can be used to close the gap on realism. During the very short amount of actual GAN training the generator not only gets the full realistic colorization capabilities that used to take days of progressively resized GAN training, but it also doesn't accrue nearly as much of the artifacts and other ugly baggage of GANs. In fact, you can pretty much eliminate glitches and artifacts almost entirely depending on your approach. As far as I know this is a new technique. And it's incredibly effective. 
 
-The steps are as follows: First train the generator in a conventional way by itself with just the feature loss. Next, generate images from that, and train the critic on distinguishing between those outputs and real images as a basic binary classifier. Finally, train the generator and critic together in a GAN setting (starting right at the target size of 192px in this case).  Now for the weird part:  All the useful GAN training here only takes place within a very small window of time.  There's an inflection point where it appears the critic has transferred everything it can that is useful to the generator. Past this point, image quality just go back and forth between either the best that you can get at the inflection point, or bad in a predictable way (orangish skin, overly red lips, etc).  There appears to be no productive training after this point.  And this point lies within training on just 1% to 3% of the Imagenet Data!  That amounts to about 30-60 minutes of training at 192px.  
+The steps are as follows: First train the generator in a conventional way by itself with just the feature loss. Next, generate images from that, and train the critic on distinguishing between those outputs and real images as a basic binary classifier. Finally, train the generator and critic together in a GAN setting (starting right at the target size of 192px in this case).  Now for the weird part:  All the useful GAN training here only takes place within a very small window of time.  There's an inflection point where it appears the critic has transferred everything it can that is useful to the generator. Past this point, image quality oscillates between the best that you can get at the inflection point, or bad in a predictable way (orangish skin, overly red lips, etc).  There appears to be no productive training after the inflection point.  And this point lies within training on just 1% to 3% of the Imagenet Data!  That amounts to about 30-60 minutes of training at 192px.  
 
 The hard part is finding this inflection point.  So far, I've accomplished this by making a whole bunch of model save checkpoints (every 0.1% of data iterated on) and then just looking for the point where images look great before they go totally bonkers with orange skin (always the first thing to go). Additionally, generator rendering starts immediately getting glitchy and inconsistent at this point, which is no good particularly for video. What I'd really like to figure out is what the tell-tale sign of the inflection point is that can be easily automated as an early stopping point.  Unfortunately, nothing definitive is jumping out at me yet.  For one, it's happening in the middle of training loss decreasing- not when it flattens out, which would seem more reasonable on the surface.