KimRass / MAE

PyTorch implementation of 'MAE' (He et al., 2021) from scratch.

Samples from Pseudo-trained Model

Masked image, reconstructed image and original image

2. To-Dos

• [✓] MAE architecture for pre-training
• [✓] MAE architecture for self-supervised learning
• [✗] Training on ImageNet-1K
• [✗] Fine-tuning
• [✗] Linear probing

3. References

• [1] https://github.com/IcarusWizard/MAE