Spaces:
Running
Running
File size: 5,725 Bytes
4f0b54e 074135b 4f0b54e 0fd272d 4f0b54e |
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 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 |
import os
from flask import Flask, render_template, request, redirect, url_for,send_from_directory
import cv2
import numpy as np
from transformers import DetrImageProcessor, DetrForObjectDetection
from torchvision.transforms import functional as F
from ultralytics import YOLO
import torch
app = Flask(__name__)
UPLOAD_FOLDER = 'uploads'
ALLOWED_EXTENSIONS = {'png', 'jpg', 'jpeg'}
app.config['UPLOAD_FOLDER'] = UPLOAD_FOLDER
def allowed_file(filename):
return '.' in filename and filename.rsplit('.', 1)[1].lower() in ALLOWED_EXTENSIONS
@app.route('/uploads/<filename>')
def uploaded_file(filename):
return send_from_directory(app.config['UPLOAD_FOLDER'], filename)
@app.route('/', methods=['GET', 'POST'])
def index():
annotated_image_url = None
if request.method == 'POST':
# Load the YOLOv8 model
yolo_model = YOLO('yolo/best.pt')
# Load the DETR model
processor = DetrImageProcessor.from_pretrained("detr")
model = DetrForObjectDetection.from_pretrained("detr")
# Check if a file is selected
if 'image' not in request.files:
return redirect(request.url)
image = request.files['image']
# Check if the file has a valid extension
if image and allowed_file(image.filename):
constant_filename = 'my_uploaded_image.jpg' # Specify the constant name
filename = os.path.join(app.config['UPLOAD_FOLDER'], constant_filename)
image.save(filename)
# Load the image for processing
image = cv2.imread(filename)
# Perform YOLO object detection and annotation
yolo_results = yolo_model(image, save=False)
yolo_image = image.copy()
yolo_names=yolo_results[0].names
for row in yolo_results[0].boxes.data:
x1, y1, x2, y2, score, class_id = row.tolist()
x1, y1, x2, y2 = map(int, [x1, y1, x2, y2])
class_name = yolo_names.get(int(class_id), 'Unknown')
label_text = f"Class: {class_name}, Score: {score:.2f}"
box_color = (0, 0, 255)
label_color = (255, 255, 255)
cv2.rectangle(yolo_image, (x1, y1), (x2, y2), box_color, thickness=2)
label_size = cv2.getTextSize(label_text, cv2.FONT_HERSHEY_SIMPLEX, 0.5, 1)[0]
label_bottom_left = (x1, y1 - 5)
label_top_right = (label_bottom_left[0] + label_size[0], label_bottom_left[1] - label_size[1])
cv2.rectangle(yolo_image, label_bottom_left, label_top_right, box_color, cv2.FILLED)
cv2.putText(yolo_image, label_text, (x1, y1 - 5), cv2.FONT_HERSHEY_SIMPLEX, 0.5, label_color, 1, cv2.LINE_AA)
annotated_filename = 'annotated_my_uploaded_image.jpg'
annotated_filepath = os.path.join(app.config['UPLOAD_FOLDER'], annotated_filename)
cv2.imwrite(annotated_filepath, yolo_image)
annotated_image_url = url_for('uploaded_file', filename=annotated_filename)
# Process the image using the processor
inputs = processor(images=image, return_tensors="pt")
outputs = model(**inputs)
# Convert outputs (bounding boxes and class logits) to COCO API format
# Let's only keep detections with score > 0.9
target_sizes = torch.tensor([image.shape[:2:]])
results = processor.post_process_object_detection(outputs, target_sizes=target_sizes, threshold=0.3)[0]
# Convert PIL image to NumPy array for OpenCV
#image_np = np.array(image)
#image_cv2 = cv2.cvtColor(image_np, cv2.COLOR_RGB2BGR)
image_cv2 = image.copy()
# Define the font for labels
font = cv2.FONT_HERSHEY_SIMPLEX
font_scale = 0.5
font_thickness = 1
font_color = (255, 255, 255) # White color
# Iterate over the results and draw bounding boxes and labels using OpenCV
for score, label, box in zip(results["scores"], results["labels"], results["boxes"]):
box = [round(i, 2) for i in box.tolist()]
# Draw the bounding box
box = [int(b) for b in box] # Convert to integers for drawing
cv2.rectangle(image_cv2, (box[0], box[1]), (box[2], box[3]), (0, 0, 255), 2) # Red rectangle
# Draw the label
label_text = f"{model.config.id2label[label.item()]}: {round(score.item(), 3)}"
label_size = cv2.getTextSize(label_text, font, font_scale, font_thickness)[0]
label_bottom_left = (box[0], box[1] - 5) # Adjust label position
label_top_right = (label_bottom_left[0] + label_size[0], label_bottom_left[1] - label_size[1])
cv2.rectangle(image_cv2, label_bottom_left, label_top_right, (0, 0, 255), cv2.FILLED) # Red filled rectangle
cv2.putText(image_cv2, label_text, (box[0], box[1] - 5), font, font_scale, font_color, font_thickness, cv2.LINE_AA)
annotated_filename = 'dert_annotated_my_uploaded_image.jpg'
annotated_filepath = os.path.join(app.config['UPLOAD_FOLDER'], annotated_filename)
cv2.imwrite(annotated_filepath, image_cv2)
dertannotated_image_url = url_for('uploaded_file', filename=annotated_filename)
return render_template('index.html', image1=annotated_image_url ,image2= dertannotated_image_url)
return render_template('index.html', image1=annotated_image_url,image2=annotated_image_url)
if __name__ == '__main__':
app.run(debug=True,port=7860) |