Instructions to use hy1111/CLIP-RS with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use hy1111/CLIP-RS with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("zero-shot-classification", model="hy1111/CLIP-RS")# Load model directly from transformers import AutoProcessor, AutoModelForZeroShotImageClassification processor = AutoProcessor.from_pretrained("hy1111/CLIP-RS") model = AutoModelForZeroShotImageClassification.from_pretrained("hy1111/CLIP-RS") - Notebooks
- Google Colab
- Kaggle
Upload meta.yaml
Browse files
meta.yaml
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# CLIP-RS Model Metadata
|
| 2 |
+
name: CLIP-RS
|
| 3 |
+
version: 1.0.0
|
| 4 |
+
description: Vision-Language Pre-training with Data Purification for Remote Sensing
|
| 5 |
+
model_type: clip
|
| 6 |
+
base_model: openai/clip-vit-large-patch14-336
|
| 7 |
+
training_dataset: CLIP-RS-10M
|
| 8 |
+
developer: WHU-RS institute for AI and Machine Vision
|