Update limitations image
Browse files
README.md
CHANGED
|
@@ -24,7 +24,7 @@ The model takes a 1x224x224 L tensor as input and outputs 2x224x224 ab channels.
|
|
| 24 |
There are no dedicated datasets for image colorisation, hence I curated my own dataset and used it to train the model. The COCO 2017 dataset was filtered to remove grayscale images, heavily filtered images, and other artifacts not suitable for training a natural colorization model. Also the images were center-cropped and resized to 224x224. The dataset can be found [here](https://huggingface.co/datasets/ayushshah/coco-2017-image-colorization-224). This repository contains the model weights and the UNet architecture to load the weights into.
|
| 25 |
|
| 26 |
<img src="https://cdn-uploads.huggingface.co/production/uploads/6318256d212fce5a3cde0fe3/5eKOaiTUK4uDeq07MdJIY.png" width="650px"/>
|
| 27 |
-
<img src="https://cdn-uploads.huggingface.co/production/uploads/6318256d212fce5a3cde0fe3/
|
| 28 |
|
| 29 |
# Usage
|
| 30 |
Download the architecture file and model weights
|
|
|
|
| 24 |
There are no dedicated datasets for image colorisation, hence I curated my own dataset and used it to train the model. The COCO 2017 dataset was filtered to remove grayscale images, heavily filtered images, and other artifacts not suitable for training a natural colorization model. Also the images were center-cropped and resized to 224x224. The dataset can be found [here](https://huggingface.co/datasets/ayushshah/coco-2017-image-colorization-224). This repository contains the model weights and the UNet architecture to load the weights into.
|
| 25 |
|
| 26 |
<img src="https://cdn-uploads.huggingface.co/production/uploads/6318256d212fce5a3cde0fe3/5eKOaiTUK4uDeq07MdJIY.png" width="650px"/>
|
| 27 |
+
<img src="https://cdn-uploads.huggingface.co/production/uploads/6318256d212fce5a3cde0fe3/gzOVQdRbOhoPZbGMA9Ldy.png" width="650px"/>
|
| 28 |
|
| 29 |
# Usage
|
| 30 |
Download the architecture file and model weights
|