File size: 1,724 Bytes
90d7fd0 6b07f33 90d7fd0 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 |
from transformers import DetrImageProcessor, DetrForObjectDetection
from transformers import BlipProcessor, BlipForConditionalGeneration
import torch
from PIL import Image
import requests
import gradio as gr
box_processor = DetrImageProcessor.from_pretrained("facebook/detr-resnet-50")
box_model = DetrForObjectDetection.from_pretrained("facebook/detr-resnet-50")
caption_processor = BlipProcessor.from_pretrained("Salesforce/blip-image-captioning-large")
caption_model = BlipForConditionalGeneration.from_pretrained("Salesforce/blip-image-captioning-large")
def predict_bounding_boxes(imageurl:str):
try:
response = requests.get(imageurl, stream=True)
response.raise_for_status()
image_data = Image.open(response.raw)
inputs = box_processor(images=image_data, return_tensors="pt")
outputs = box_model(**inputs)
target_sizes = torch.tensor([image_data.size[::-1]])
results = box_processor.post_process_object_detection(outputs, target_sizes=target_sizes, threshold=0.70)[0]
detections = [{"score": score.item(), "label": box_model.config.id2label[label.item()], "box": box.tolist()} for score, label, box in zip(results["scores"], results["labels"], results["boxes"])]
raw_image = image_data.convert('RGB')
inputs = caption_processor(raw_image, return_tensors="pt")
out = caption_model.generate(**inputs)
label = caption_processor.decode(out[0], skip_special_tokens=True)
return {"image label": label, "detections": detections}
except Exception as e:
return {"error": str(e)}
app = gr.Interface(fn=predict_bounding_boxes, inputs="text", outputs="json")
app.api = True
app.launch()
|