kartiknarayan commited on
Commit
37a67d1
1 Parent(s): 06c5bf6

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +5 -2
README.md CHANGED
@@ -21,7 +21,7 @@ FaceXFormer is an end-to-end unified model capable of handling a comprehensive r
21
  landmark detection, head pose estimation, attributes recognition, age/gender/race estimation and landmarks visibility prediction.
22
 
23
  <div align="center">
24
- <!-- <img src='assets/samples_short.jpg'> -->
25
  </div>
26
 
27
  ## Model Details
@@ -29,6 +29,9 @@ landmark detection, head pose estimation, attributes recognition, age/gender/rac
29
  FaceXFormer is a transformer-based encoder-decoder architecture where each task is treated as a learnable token, enabling the
30
  integration of multiple tasks within a single framework.
31
 
 
 
 
32
 
33
  ## Usage
34
 
@@ -36,7 +39,7 @@ The models can be downloaded directly from this repository or using python:
36
  ```python
37
  from huggingface_hub import hf_hub_download
38
 
39
- hf_hub_download(repo_id="kartiknarayan/facexformer", filename="facexformer/ckpts/model.pt", local_dir="./models")
40
  ```
41
 
42
  Please check our [GitHub repository](https://github.com/Kartik-3004/facexformer) for complete inference instructions.
 
21
  landmark detection, head pose estimation, attributes recognition, age/gender/race estimation and landmarks visibility prediction.
22
 
23
  <div align="center">
24
+ <img src='assets/intro_viz.png'>
25
  </div>
26
 
27
  ## Model Details
 
29
  FaceXFormer is a transformer-based encoder-decoder architecture where each task is treated as a learnable token, enabling the
30
  integration of multiple tasks within a single framework.
31
 
32
+ <div align="center">
33
+ <img src='assets/main_archi.png'>
34
+ </div>
35
 
36
  ## Usage
37
 
 
39
  ```python
40
  from huggingface_hub import hf_hub_download
41
 
42
+ hf_hub_download(repo_id="kartiknarayan/facexformer", filename="facexformer/ckpts/model.pt", local_dir="./ckpts")
43
  ```
44
 
45
  Please check our [GitHub repository](https://github.com/Kartik-3004/facexformer) for complete inference instructions.