Upload folder using huggingface_hub
Browse files
README.md
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model:
|
3 |
+
- openai/clip-vit-large-patch14
|
4 |
+
datasets:
|
5 |
+
- svhn
|
6 |
+
metrics:
|
7 |
+
- accuracy
|
8 |
+
---
|
9 |
+
|
10 |
+
# Model Card
|
11 |
+
|
12 |
+
## Model Details
|
13 |
+
|
14 |
+
- Architecture: ViT-Large with patch size 14
|
15 |
+
- Training Data: SVHN dataset
|
16 |
+
|
17 |
+
## Training Details
|
18 |
+
|
19 |
+
Adam Optimizer with a constant learning rate 1e-5 for 4000 steps training (batch_size=32).
|
20 |
+
Only the vision encoder is fine-tuned.
|
21 |
+
|
22 |
+
## Evaluation Results
|
23 |
+
|
24 |
+
- pre-trained: 0.6830110549926758
|
25 |
+
- fine-tuned: 0.9790836572647095
|
26 |
+
|