Merge branch 'saic-mdal:main' into main

Author: elimohl

README.md

@@ -5,6 +5,13 @@ Official implementation by Samsung Research
 by Roman Suvorov, Elizaveta Logacheva, Anton Mashikhin, 
 Anastasia Remizova, Arsenii Ashukha, Aleksei Silvestrov, Naejin Kong, Harshith Goka, Kiwoong Park, Victor Lempitsky.
 
+<p align="center" "font-size:30px;">
+  🔥🔥🔥
+  <br>
+  <b>
+Our model generalizes surprisingly well to much higher resolutions (~2k❗️) than it saw during training (256x256), and achieves the excellent performance even in challenging scenarios, e.g. completion of periodic structures.</b>
+</p>
+
 [[Project page](https://saic-mdal.github.io/lama-project/)] [[arXiv](https://arxiv.org/abs/2109.07161)] [[Supplementary](https://ashukha.com/projects/lama_21/lama_supmat_2021.pdf)] [[BibTeX](https://senya-ashukha.github.io/projects/lama_21/paper.txt)]
 
 <p align="center">
@@ -70,17 +77,17 @@ Install tool for yandex disk link extraction:
 pip3 install wldhx.yadisk-direct
 ```
 
-The best model (Places):
+The best model (Places2, Places Challenge):
     
 ```    
 curl -L $(yadisk-direct https://disk.yandex.ru/d/ouP6l8VJ0HpMZg) -o big-lama.zip
 unzip big-lama.zip
 ```
 
-All models (Places):
+All models (Places & CelebA):
 
 ```
-curl -L $(yadisk-direct https://disk.yandex.ru/d/AmdeG-bIjmvSug) -o lama-models.zip
+curl -L $(yadisk-direct https://disk.yandex.ru/d/EgqaSnLohjuzAg) -o lama-models.zip
 unzip lama-models.zip
 ```
 
@@ -263,16 +270,18 @@ Config names for models from paper (substitude into the training command):
 
 Which are seated in configs/training/folder
 
-### Training time
+### Links
+- All the data (models, test images, etc.) https://disk.yandex.ru/d/AmdeG-bIjmvSug
+- Test images from the paper https://disk.yandex.ru/d/xKQJZeVRk5vLlQ
+- The pre-trained models https://disk.yandex.ru/d/EgqaSnLohjuzAg
+- The models for perceptual loss https://disk.yandex.ru/d/ncVmQlmT_kTemQ
+- Our training logs are available at https://disk.yandex.ru/d/9Bt1wNSDS4jDkQ
 
-TODO
 
-### Our training logs
+### Training time & resources
 
-The training logs are available at [https://disk.yandex.ru/d/9Bt1wNSDS4jDkQ](https://disk.yandex.ru/d/9Bt1wNSDS4jDkQ).
-TODO: IPython with tables?
+TODO
 
------
 ## Acknowledgments
 
 * Segmentation code and models if form [CSAILVision](https://github.com/CSAILVision/semantic-segmentation-pytorch).