Zero-Shot Image Classification
Transformers
Safetensors
English
Chinese
fgclip2
text-generation
clip
custom_code
Instructions to use qihoo360/fg-clip2-large with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use qihoo360/fg-clip2-large with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("zero-shot-image-classification", model="qihoo360/fg-clip2-large", trust_remote_code=True) pipe( "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png", candidate_labels=["animals", "humans", "landscape"], )# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("qihoo360/fg-clip2-large", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
复现模型主页的retrieval的测试代码的时候,logits_per_image返回的4个值几乎一模一样,不知道是为什么?
1
#2 opened 6 months ago
by
shumengwei