first

Dockerfile

@@ -0,0 +1,24 @@
+# Use the official Python image as base
+FROM python:3.8-slim-buster
+
+# Set the working directory
+WORKDIR /code
+
+
+
+# Copy the requirements file into the container
+COPY requirements.txt requirements.txt
+
+# Install dependencies
+RUN pip install -r requirements.txt
+
+# Install libgl1-mesa-glx and libglib2.0-0
+RUN apt-get update && apt-get install -y libgl1-mesa-glx libglib2.0-0
+# Copy the rest of the application code into the container
+COPY . .
+
+# Expose the port the app runs on
+#EXPOSE 5000
+
+# Define the command to run the app when the container starts
+CMD ["python", "-m", "flask", "run", "--host", "0.0.0.0", "--port", "7860"]

app.py

@@ -0,0 +1,150 @@
+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', 'gif'}
+
+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/yolov8s.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)

detr/config.json

@@ -0,0 +1,232 @@
+{
+  "_name_or_path": "facebook/detr-resnet-50",
+  "activation_dropout": 0.0,
+  "activation_function": "relu",
+  "architectures": [
+    "DetrForObjectDetection"
+  ],
+  "attention_dropout": 0.0,
+  "auxiliary_loss": false,
+  "backbone": "resnet50",
+  "backbone_config": null,
+  "bbox_cost": 5,
+  "bbox_loss_coefficient": 5,
+  "class_cost": 1,
+  "classifier_dropout": 0.0,
+  "d_model": 256,
+  "decoder_attention_heads": 8,
+  "decoder_ffn_dim": 2048,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 6,
+  "dice_loss_coefficient": 1,
+  "dilation": false,
+  "dropout": 0.1,
+  "encoder_attention_heads": 8,
+  "encoder_ffn_dim": 2048,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 6,
+  "eos_coefficient": 0.1,
+  "giou_cost": 2,
+  "giou_loss_coefficient": 2,
+  "id2label": {
+    "0": "N/A",
+    "1": "person",
+    "2": "bicycle",
+    "3": "car",
+    "4": "motorcycle",
+    "5": "airplane",
+    "6": "bus",
+    "7": "train",
+    "8": "truck",
+    "9": "boat",
+    "10": "traffic light",
+    "11": "fire hydrant",
+    "12": "street sign",
+    "13": "stop sign",
+    "14": "parking meter",
+    "15": "bench",
+    "16": "bird",
+    "17": "cat",
+    "18": "dog",
+    "19": "horse",
+    "20": "sheep",
+    "21": "cow",
+    "22": "elephant",
+    "23": "bear",
+    "24": "zebra",
+    "25": "giraffe",
+    "26": "hat",
+    "27": "backpack",
+    "28": "umbrella",
+    "29": "shoe",
+    "30": "eye glasses",
+    "31": "handbag",
+    "32": "tie",
+    "33": "suitcase",
+    "34": "frisbee",
+    "35": "skis",
+    "36": "snowboard",
+    "37": "sports ball",
+    "38": "kite",
+    "39": "baseball bat",
+    "40": "baseball glove",
+    "41": "skateboard",
+    "42": "surfboard",
+    "43": "tennis racket",
+    "44": "bottle",
+    "45": "plate",
+    "46": "wine glass",
+    "47": "cup",
+    "48": "fork",
+    "49": "knife",
+    "50": "spoon",
+    "51": "bowl",
+    "52": "banana",
+    "53": "apple",
+    "54": "sandwich",
+    "55": "orange",
+    "56": "broccoli",
+    "57": "carrot",
+    "58": "hot dog",
+    "59": "pizza",
+    "60": "donut",
+    "61": "cake",
+    "62": "chair",
+    "63": "couch",
+    "64": "potted plant",
+    "65": "bed",
+    "66": "mirror",
+    "67": "dining table",
+    "68": "window",
+    "69": "desk",
+    "70": "toilet",
+    "71": "door",
+    "72": "tv",
+    "73": "laptop",
+    "74": "mouse",
+    "75": "remote",
+    "76": "keyboard",
+    "77": "cell phone",
+    "78": "microwave",
+    "79": "oven",
+    "80": "toaster",
+    "81": "sink",
+    "82": "refrigerator",
+    "83": "blender",
+    "84": "book",
+    "85": "clock",
+    "86": "vase",
+    "87": "scissors",
+    "88": "teddy bear",
+    "89": "hair drier",
+    "90": "toothbrush"
+  },
+  "init_std": 0.02,
+  "init_xavier_std": 1.0,
+  "is_encoder_decoder": true,
+  "label2id": {
+    "N/A": 0,
+    "airplane": 5,
+    "apple": 53,
+    "backpack": 27,
+    "banana": 52,
+    "baseball bat": 39,
+    "baseball glove": 40,
+    "bear": 23,
+    "bed": 65,
+    "bench": 15,
+    "bicycle": 2,
+    "bird": 16,
+    "blender": 83,
+    "boat": 9,
+    "book": 84,
+    "bottle": 44,
+    "bowl": 51,
+    "broccoli": 56,
+    "bus": 6,
+    "cake": 61,
+    "car": 3,
+    "carrot": 57,
+    "cat": 17,
+    "cell phone": 77,
+    "chair": 62,
+    "clock": 85,
+    "couch": 63,
+    "cow": 21,
+    "cup": 47,
+    "desk": 69,
+    "dining table": 67,
+    "dog": 18,
+    "donut": 60,
+    "door": 71,
+    "elephant": 22,
+    "eye glasses": 30,
+    "fire hydrant": 11,
+    "fork": 48,
+    "frisbee": 34,
+    "giraffe": 25,
+    "hair drier": 89,
+    "handbag": 31,
+    "hat": 26,
+    "horse": 19,
+    "hot dog": 58,
+    "keyboard": 76,
+    "kite": 38,
+    "knife": 49,
+    "laptop": 73,
+    "microwave": 78,
+    "mirror": 66,
+    "motorcycle": 4,
+    "mouse": 74,
+    "orange": 55,
+    "oven": 79,
+    "parking meter": 14,
+    "person": 1,
+    "pizza": 59,
+    "plate": 45,
+    "potted plant": 64,
+    "refrigerator": 82,
+    "remote": 75,
+    "sandwich": 54,
+    "scissors": 87,
+    "sheep": 20,
+    "shoe": 29,
+    "sink": 81,
+    "skateboard": 41,
+    "skis": 35,
+    "snowboard": 36,
+    "spoon": 50,
+    "sports ball": 37,
+    "stop sign": 13,
+    "street sign": 12,
+    "suitcase": 33,
+    "surfboard": 42,
+    "teddy bear": 88,
+    "tennis racket": 43,
+    "tie": 32,
+    "toaster": 80,
+    "toilet": 70,
+    "toothbrush": 90,
+    "traffic light": 10,
+    "train": 7,
+    "truck": 8,
+    "tv": 72,
+    "umbrella": 28,
+    "vase": 86,
+    "window": 68,
+    "wine glass": 46,
+    "zebra": 24
+  },
+  "mask_loss_coefficient": 1,
+  "max_position_embeddings": 1024,
+  "model_type": "detr",
+  "num_channels": 3,
+  "num_hidden_layers": 6,
+  "num_queries": 100,
+  "position_embedding_type": "sine",
+  "scale_embedding": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.33.0",
+  "use_pretrained_backbone": true,
+  "use_timm_backbone": true
+}

detr/preprocessor_config.json

@@ -0,0 +1,25 @@
+{
+  "do_normalize": true,
+  "do_pad": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "feature_extractor_type": "DetrFeatureExtractor",
+  "format": "coco_detection",
+  "image_mean": [
+    0.485,
+    0.456,
+    0.406
+  ],
+  "image_processor_type": "DetrImageProcessor",
+  "image_std": [
+    0.229,
+    0.224,
+    0.225
+  ],
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "longest_edge": 1333,
+    "shortest_edge": 800
+  }
+}

detr/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c560657017d19d334bb6f0d0f51eee92b7a3d873b4603f4e4f08f90050ae9efa
+size 166699733

detr/yolov8s.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:268e5bb54c640c96c3510224833bc2eeacab4135c6deb41502156e39986b562d
+size 22573363

requirements.txt

@@ -0,0 +1,6 @@
+transformers
+flask
+torch
+ultralytics
+opencv-python
+timm

templates/index.html

@@ -0,0 +1,66 @@
+<!DOCTYPE html>
+<html>
+<head>
+    <title>Image Upload and Display</title>
+    <style>
+        body {
+            font-family: Arial, sans-serif;
+            text-align: center;
+        }
+
+        h1 {
+            color: #333;
+        }
+
+        form {
+            margin: 20px auto;
+            padding: 20px;
+            border: 1px solid #ccc;
+            max-width: 400px;
+        }
+
+        input[type="file"] {
+            margin-bottom: 10px;
+        }
+
+        .image-container {
+            display: flex;
+            justify-content: center;
+            align-items: flex-start;
+        }
+
+        .image-column {
+            flex: 1;
+            padding: 10px;
+        }
+
+        img {
+            max-width: 100%;
+            max-height: 500px;
+        }
+    </style>
+</head>
+<body>
+    <h1>Upload an Image</h1>
+    <form method="POST" enctype="multipart/form-data">
+        <input type="file" name="image">
+        <input type="submit" value="Upload">
+    </form>
+    
+    <div class="image-container">
+        <div class="image-column">
+            {% if image1 %}
+                <h2>YOLO model Image:</h2>
+                <img src="{{ image1 }}" alt="YOLO Annotated Image">
+            {% endif %}
+        </div>
+        
+        <div class="image-column">
+            {% if image2 %}
+                <h2>DETR Model Image:</h2>
+                <img src="{{ image2 }}" alt="DETR Annotated Image">
+            {% endif %}
+        </div>
+    </div>
+</body>
+</html>

yolo/yolov8s.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:268e5bb54c640c96c3510224833bc2eeacab4135c6deb41502156e39986b562d
+size 22573363