redlessone
/

DermLIP_PanDerm-base-w-PubMed-256

Zero-Shot Image Classification

image-text-to-text

zero-shot-classification

image-classification

Model card Files Files and versions

redlessone commited on Oct 15

Commit

b079489

·

verified ·

1 Parent(s): 8abceff

Update README.md

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -43,8 +43,8 @@ library_name: transformers
 - **Training data:** 403,563 skin image-text pairs from Derm1M datasets. Images include both dermoscopic and clinical images.
 - **Training objective:** image-text contrastive loss
-- **Hardware:** 1 x Nvidia H200
-- **Hours used:**  ~21.5 hours
 ## Intended Uses

 - **Training data:** 403,563 skin image-text pairs from Derm1M datasets. Images include both dermoscopic and clinical images.
 - **Training objective:** image-text contrastive loss
+- **Hardware:** 1 x Nvidia H200（～90GB memory usage）
+- **Hours used:**  ~9.5 hours
 ## Intended Uses