Spaces:
Runtime error
Runtime error
File size: 3,528 Bytes
d10f466 65f769b 69c84d2 d10f466 65f769b d10f466 bf51623 d10f466 69c84d2 d10f466 69c84d2 d10f466 69c84d2 65f769b 69c84d2 d10f466 bf51623 69c84d2 bf51623 d10f466 |
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 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 |
import gradio as gr
import cv2
import torch
from PIL import Image
from transformers import DetrImageProcessor, DetrForObjectDetection
import numpy as np
# Load the pre-trained DETR model
processor = DetrImageProcessor.from_pretrained("facebook/detr-resnet-50", revision="no_timm")
model = DetrForObjectDetection.from_pretrained("facebook/detr-resnet-50", revision="no_timm")
model.eval()
# Function for image object detection
def image_object_detection(image_pil):
# Process the image with the DETR model
inputs = processor(images=image_pil, return_tensors="pt")
outputs = model(**inputs)
# Convert the image to numpy array for drawing bounding boxes
image_np = cv2.cvtColor(cv2.cvtColor(cv2.cvtColor(np.array(image_pil), cv2.COLOR_RGB2BGR), cv2.COLOR_BGR2RGB), cv2.COLOR_RGB2BGR)
# convert outputs (bounding boxes and class logits) to COCO API
# let's only keep detections with score > 0.9
target_sizes = torch.tensor([image_pil.size[::-1]])
results = processor.post_process_object_detection(outputs, target_sizes=target_sizes, threshold=0.9)[0]
# Draw bounding boxes on the image
for score, label, box in zip(results["scores"], results["labels"], results["boxes"]):
box = [int(round(i)) for i in box.tolist()]
cv2.rectangle(image_np, (box[0], box[1]), (box[2], box[3]), (0, 255, 0), 2)
label_text = f"{model.config.id2label[label.item()]}: {round(score.item(), 3)}"
cv2.putText(image_np, label_text, (box[0], box[1] - 10), cv2.FONT_HERSHEY_SIMPLEX, 0.5, (0, 255, 0), 2)
return image_np
# Function for live object detection from the camera
def live_object_detection():
# Open a connection to the camera (replace with your own camera setup)
cap = cv2.VideoCapture(0)
while True:
# Capture frame-by-frame
ret, frame = cap.read()
# Convert the frame to PIL Image
frame_pil = Image.fromarray(cv2.cvtColor(frame, cv2.COLOR_BGR2RGB))
# Process the frame with the DETR model
inputs = processor(images=frame_pil, return_tensors="pt")
outputs = model(**inputs)
# convert outputs (bounding boxes and class logits) to COCO API
# let's only keep detections with score > 0.9
target_sizes = torch.tensor([frame_pil.size[::-1]])
results = processor.post_process_object_detection(outputs, target_sizes=target_sizes, threshold=0.9)[0]
# Draw bounding boxes on the frame
for score, label, box in zip(results["scores"], results["labels"], results["boxes"]):
box = [int(round(i)) for i in box.tolist()]
cv2.rectangle(frame, (box[0], box[1]), (box[2], box[3]), (0, 255, 0), 2)
label_text = f"{model.config.id2label[label.item()]}: {round(score.item(), 3)}"
cv2.putText(frame, label_text, (box[0], box[1] - 10), cv2.FONT_HERSHEY_SIMPLEX, 0.5, (0, 255, 0), 2)
# Display the resulting frame
cv2.imshow('Object Detection', frame)
# Break the loop when 'q' key is pressed
if cv2.waitKey(1) & 0xFF == ord('q'):
break
# Release the camera and close all windows
cap.release()
cv2.destroyAllWindows()
# Define the Gradio interface
iface = gr.Interface(
fn=[image_object_detection, live_object_detection],
inputs=[
gr.Image(type="pil", label="Upload an image for object detection") # Remove this line
],
outputs=[
"image",
"image",
],
live=True,
)
# Launch the Gradio interface
iface.launch()
|