luoxd96 commited on
Commit
3cee81c
·
verified ·
1 Parent(s): 6ec5f7a

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +0 -2
README.md CHANGED
@@ -26,7 +26,6 @@ This Hub repo contains the **inference-only** slide encoder: interpolate → Lay
26
 
27
  | | |
28
  |---|---|
29
- | Developed by | Li Lab, Stanford University |
30
  | Model type | Slide-level ABMIL aggregator |
31
  | Inputs | Patch features \(X \in \mathbb{R}^{N \times C}\), \(C \in \{768, 1024, 1280, 1536\}\) |
32
  | Outputs | `features_dim` \([1, C]\), `features` \([1, 768]\), `attention_weights` \([1, 1, N]\) |
@@ -99,7 +98,6 @@ Research feature extraction for computational pathology (classification, biomark
99
 
100
  - Requires pre-extracted tile embeddings from the five foundation models above; it does not encode RGB tiles.
101
  - Virchow2 inputs of dimension ≥ 2560 are averaged as CLS + mean → 1280, matching the paper.
102
- - Licensed for non-commercial academic use.
103
 
104
  ## Citation
105
 
 
26
 
27
  | | |
28
  |---|---|
 
29
  | Model type | Slide-level ABMIL aggregator |
30
  | Inputs | Patch features \(X \in \mathbb{R}^{N \times C}\), \(C \in \{768, 1024, 1280, 1536\}\) |
31
  | Outputs | `features_dim` \([1, C]\), `features` \([1, 768]\), `attention_weights` \([1, 1, N]\) |
 
98
 
99
  - Requires pre-extracted tile embeddings from the five foundation models above; it does not encode RGB tiles.
100
  - Virchow2 inputs of dimension ≥ 2560 are averaged as CLS + mean → 1280, matching the paper.
 
101
 
102
  ## Citation
103