FLIP Base 32

🚀 FaceCLIP-base-32

A CLIP model post-trained on 80M human face images, offering enhanced performance in face-related tasks.

🚀 Quick Start

This FaceCLIP model is post-trained on 80M human face images. It was trained using the TencentPretrain framework on 8 * A100 GPUs.

📦 Installation

The installation process is mainly about running the training script. Here is the command used for training:

python3 pretrain.py --dataset_path faceclip.pt \
	--pretrained_model_path models/clip-b32.bin \
	--output_model_path models/faceclip-b32.bin \
	--config_path models/clip/base-32_config.json \
	--vocab_path vocab.json --merges_path merges.txt --tokenizer clip \
	--world_size 8 --gpu_ranks 0 1 2 3 4 5 6 7 --data_processor clip --accumulation_steps 8 --learning_rate 2e-5 \
	--total_steps 200000 --save_checkpoint_steps 20000 --batch_size 160 --report_steps 500

💻 Usage Examples

Basic Usage

from PIL import Image
import requests

from transformers import CLIPProcessor, CLIPModel

model = CLIPModel.from_pretrained("P01son/FaceCLIP-base-32")
processor = CLIPProcessor.from_pretrained("P01son/FaceCLIP-base-32")

url = "http://images.cocodataset.org/val2017/000000039769.jpg"
image = Image.open(requests.get(url, stream=True).raw)

inputs = processor(text=["a photo of a cat", "a photo of a dog"], images=image, return_tensors="pt", padding=True)

outputs = model(**inputs)
logits_per_image = outputs.logits_per_image # this is the image-text similarity score
probs = logits_per_image.softmax(dim=1) # we can take the softmax to get the label probabilities

📄 License

This project is licensed under the Apache-2.0 license.