ayushshah commited on
Commit
ff4f6fc
·
verified ·
1 Parent(s): a70fb5c

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -16,7 +16,7 @@ pipeline_tag: image-to-image
16
  # Image colorization
17
  A UNet architecture, utilizing transfer learning by using a pretrained ResNet-34 as an encoder.
18
 
19
- Try the model on [Colab](https://colab.research.google.com/drive/1JYbSLtDuFSw2NYe-YW-kZHLNkt4-v7jd) or [Huggingface space](https://huggingface.co/spaces/ayushshah/imagecolorization).
20
  <img src="https://cdn-uploads.huggingface.co/production/uploads/6318256d212fce5a3cde0fe3/To7FVLusBz1kl8g9HhPIf.png" width="800px"/>
21
 
22
  The model takes a 1x224x224 L tensor as input and outputs 2x224x224 ab channels. The decoder has been trained from scratch. The encoder (ResNet-34) was initially frozen for the decoder to adapt to the task, then it was progressively unfreezed layer by layer. Initial layers were not unfreezed, only deeper layers were fine-tuned. Read various research papers. It took 20+ hours of training on Google Colab and Kaggle T4 GPUs to train the model.
 
16
  # Image colorization
17
  A UNet architecture, utilizing transfer learning by using a pretrained ResNet-34 as an encoder.
18
 
19
+ Try the model on [Google Colab](https://colab.research.google.com/drive/1JYbSLtDuFSw2NYe-YW-kZHLNkt4-v7jd) or [Huggingface space](https://huggingface.co/spaces/ayushshah/imagecolorization).
20
  <img src="https://cdn-uploads.huggingface.co/production/uploads/6318256d212fce5a3cde0fe3/To7FVLusBz1kl8g9HhPIf.png" width="800px"/>
21
 
22
  The model takes a 1x224x224 L tensor as input and outputs 2x224x224 ab channels. The decoder has been trained from scratch. The encoder (ResNet-34) was initially frozen for the decoder to adapt to the task, then it was progressively unfreezed layer by layer. Initial layers were not unfreezed, only deeper layers were fine-tuned. Read various research papers. It took 20+ hours of training on Google Colab and Kaggle T4 GPUs to train the model.