wi-lab commited on
Commit
d75b6d0
·
verified ·
1 Parent(s): a9c2596

Update app.py

Browse files
Files changed (1) hide show
  1. app.py +1 -1
app.py CHANGED
@@ -692,7 +692,7 @@ with gr.Blocks(css="""
692
  ```
693
  """)
694
  with gr.Tab("LWM Model and Framework"):
695
- gr.Image("images/lwm.PNG")
696
  gr.Markdown("This figure depicts the offline pre-training and online embedding generation process for LWM. The channel is divided into fixed-size patches, which are linearly embedded and combined with positional encodings before being passed through a Transformer encoder. During self-supervised pre-training, some embeddings are masked, and LWM leverages self-attention to extract deep features, allowing the decoder to reconstruct the masked values. For downstream tasks, the generated LWM embeddings enhance performance. The right block shows the LWM architecture, inspired by the original Transformer introduced in the [**Attention Is All You Need**](https://arxiv.org/abs/1706.03762) paper.")
697
 
698
  # Launch the app
 
692
  ```
693
  """)
694
  with gr.Tab("LWM Model and Framework"):
695
+ gr.Image("images/lwm_model_v2.png")
696
  gr.Markdown("This figure depicts the offline pre-training and online embedding generation process for LWM. The channel is divided into fixed-size patches, which are linearly embedded and combined with positional encodings before being passed through a Transformer encoder. During self-supervised pre-training, some embeddings are masked, and LWM leverages self-attention to extract deep features, allowing the decoder to reconstruct the masked values. For downstream tasks, the generated LWM embeddings enhance performance. The right block shows the LWM architecture, inspired by the original Transformer introduced in the [**Attention Is All You Need**](https://arxiv.org/abs/1706.03762) paper.")
697
 
698
  # Launch the app