deploy v1

.gitignore

@@ -0,0 +1,7 @@
+flagged/
+*.pt
+*.png
+*.jpg
+*.mp4
+*.mkv
+gradio_cached_examples/

app.py

@@ -1,146 +1,104 @@
 import gradio as gr
-import torch
-from sahi.prediction import ObjectPrediction
-from sahi.utils.cv import visualize_object_predictions, read_image
-from ultralytics import YOLO
 import cv2
-import numpy as np
-from math import atan2, cos, sin, sqrt, pi
+import requests
+import os
 
-# Images
-torch.hub.download_url_to_file('https://github.com/lucarei/orientation-detection-robotic-grasping/assets/22428774/cefd9731-c57c-428b-b401-fd54a8bd0a95', 'highway.jpg')
-torch.hub.download_url_to_file('https://github.com/lucarei/orientation-detection-robotic-grasping/assets/22428774/acbad76a-33f9-4028-b012-4ece5998c272', 'highway1.jpg')
-torch.hub.download_url_to_file('https://github.com/lucarei/orientation-detection-robotic-grasping/assets/22428774/7fa95f52-3c8b-4ea0-8bca-7374792a4c55', 'small-vehicles1.jpeg')
+from ultralytics import YOLO
 
-# def drawAxis(img, p_, q_, color, scale):
-#   p = list(p_)
-#   q = list(q_)
- 
-#   ## [visualization1]
-#   angle = atan2(p[1] - q[1], p[0] - q[0]) # angle in radians
-#   hypotenuse = sqrt((p[1] - q[1]) * (p[1] - q[1]) + (p[0] - q[0]) * (p[0] - q[0]))
- 
-#   # Here we lengthen the arrow by a factor of scale
-#   q[0] = p[0] - scale * hypotenuse * cos(angle)
-#   q[1] = p[1] - scale * hypotenuse * sin(angle)
-#   cv2.line(img, (int(p[0]), int(p[1])), (int(q[0]), int(q[1])), color, 3, cv2.LINE_AA)
- 
-#   # create the arrow hooks
-#   p[0] = q[0] + 9 * cos(angle + pi / 4)
-#   p[1] = q[1] + 9 * sin(angle + pi / 4)
-#   cv2.line(img, (int(p[0]), int(p[1])), (int(q[0]), int(q[1])), color, 3, cv2.LINE_AA)
- 
-#   p[0] = q[0] + 9 * cos(angle - pi / 4)
-#   p[1] = q[1] + 9 * sin(angle - pi / 4)
-#   cv2.line(img, (int(p[0]), int(p[1])), (int(q[0]), int(q[1])), color, 3, cv2.LINE_AA)
-#   ## [visualization1]
- 
+file_urls = [
+    'https://github.com/lucarei/orientation-detection-robotic-grasping/assets/22428774/cefd9731-c57c-428b-b401-fd54a8bd0a95',
+    'https://github.com/lucarei/orientation-detection-robotic-grasping/assets/22428774/acbad76a-33f9-4028-b012-4ece5998c272',
+    'https://www.dropbox.com/s/7sjfwncffg8xej2/video_7.mp4?dl=1'
+]
 
-# def getOrientation(pts, img):
-#   ## [pca]
-#   # Construct a buffer used by the pca analysis
-#   sz = len(pts)
-#   data_pts = np.empty((sz, 2), dtype=np.float64)
-#   for i in range(data_pts.shape[0]):
-#     data_pts[i,0] = pts[i,0,0]
-#     data_pts[i,1] = pts[i,0,1]
- 
-#   # Perform PCA analysis
-#   mean = np.empty((0))
-#   mean, eigenvectors, eigenvalues = cv2.PCACompute2(data_pts, mean)
- 
-#   # Store the center of the object
-#   cntr = (int(mean[0,0]), int(mean[0,1]))
-#   ## [pca]
- 
-#   ## [visualization]
-#   # Draw the principal components
-#   cv2.circle(img, cntr, 3, (255, 0, 255), 10)
-#   p1 = (cntr[0] + 0.02 * eigenvectors[0,0] * eigenvalues[0,0], cntr[1] + 0.02 * eigenvectors[0,1] * eigenvalues[0,0])
-#   p2 = (cntr[0] - 0.02 * eigenvectors[1,0] * eigenvalues[1,0], cntr[1] - 0.02 * eigenvectors[1,1] * eigenvalues[1,0])
-#   drawAxis(img, cntr, p1, (255, 255, 0), 1)
-#   drawAxis(img, cntr, p2, (0, 0, 255), 3)
- 
-#   angle = atan2(eigenvectors[0,1], eigenvectors[0,0]) # orientation in radians
-#   ## [visualization]
-#   angle_deg = -(int(np.rad2deg(angle))-180) % 180
- 
-#   # Label with the rotation angle
-#   label = " Rotation Angle: " + str(int(np.rad2deg(angle))) + " degrees"
-#   textbox = cv2.rectangle(img, (cntr[0], cntr[1]-25), (cntr[0] + 250, cntr[1] + 10), (255,255,255), -1)
-#   cv2.putText(img, label, (cntr[0], cntr[1]), cv2.FONT_HERSHEY_SIMPLEX, 0.5, (0,0,0), 1, cv2.LINE_AA)
+def download_file(url, save_name):
+    url = url
+    if not os.path.exists(save_name):
+        file = requests.get(url)
+        open(save_name, 'wb').write(file.content)
 
-#   return angle_deg
+for i, url in enumerate(file_urls):
+    if 'mp4' in file_urls[i]:
+        download_file(
+            file_urls[i],
+            f"video.mp4"
+        )
+    else:
+        download_file(
+            file_urls[i],
+            f"image_{i}.jpg"
+        )
 
-def yolov8_inference(
-    image: gr.inputs.Image = None,
-    model_path: gr.inputs.Dropdown = None,
-    image_size: gr.inputs.Slider = 640,
-    conf_threshold: gr.inputs.Slider = 0.25,
-    iou_threshold: gr.inputs.Slider = 0.45,
-):
-    """
-    YOLOv8 inference function
-    Args:
-        image: Input image
-        model_path: Path to the model
-        image_size: Image size
-        conf_threshold: Confidence threshold
-        iou_threshold: IOU threshold
-    Returns:
-        Rendered image
-    """
-    model = YOLO(model_path)
-    model.conf = conf_threshold
-    model.iou = iou_threshold
-    results = model.predict(image, imgsz=image_size, return_outputs=True)
-    object_prediction_list = []
-    for _, image_results in enumerate(results):
-        if len(image_results)!=0:
-            image_predictions_in_xyxy_format = image_results['det']
-            for pred in image_predictions_in_xyxy_format:
-                x1, y1, x2, y2 = (
-                    int(pred[0]),
-                    int(pred[1]),
-                    int(pred[2]),
-                    int(pred[3]),
-                )
-                bbox = [x1, y1, x2, y2]
-                score = pred[4]
-                category_name = model.model.names[int(pred[5])]
-                category_id = pred[5]
-                object_prediction = ObjectPrediction(
-                    bbox=bbox,
-                    category_id=int(category_id),
-                    score=score,
-                    category_name=category_name,
-                )
-                object_prediction_list.append(object_prediction)
+model = YOLO('best.pt')
+path  = [['image_0.jpg'], ['image_1.jpg']]
+video_path = [['video.mp4']]
 
-    image = read_image(image)
-    output_image = visualize_object_predictions(image=image, object_prediction_list=object_prediction_list)
-    return output_image['image']
+def show_preds_image(image_path):
+    image = cv2.imread(image_path)
+    outputs = model.predict(source=image_path)
+    results = outputs[0].cpu().numpy()
+    for i, det in enumerate(results.boxes.xyxy):
+        cv2.rectangle(
+            image,
+            (int(det[0]), int(det[1])),
+            (int(det[2]), int(det[3])),
+            color=(0, 0, 255),
+            thickness=2,
+            lineType=cv2.LINE_AA
+        )
+    return cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
 
-inputs = [
-    gr.inputs.Image(type="filepath", label="Input Image"),
-    gr.inputs.Dropdown(["turhancan97/yolov8m-trash"], 
-                       default="turhancan97/yolov8m-trash", label="Model"),
-    gr.inputs.Slider(minimum=320, maximum=1280, default=640, step=32, label="Image Size"),
-    gr.inputs.Slider(minimum=0.0, maximum=1.0, default=0.25, step=0.05, label="Confidence Threshold"),
-    gr.inputs.Slider(minimum=0.0, maximum=1.0, default=0.45, step=0.05, label="IOU Threshold"),
+inputs_image = [
+    gr.components.Image(type="filepath", label="Input Image"),
+]
+outputs_image = [
+    gr.components.Image(type="numpy", label="Output Image"),
 ]
+interface_image = gr.Interface(
+    fn=show_preds_image,
+    inputs=inputs_image,
+    outputs=outputs_image,
+    title="Pothole detector app",
+    examples=path,
+    cache_examples=False,
+)
+
+def show_preds_video(video_path):
+    cap = cv2.VideoCapture(video_path)
+    while(cap.isOpened()):
+        ret, frame = cap.read()
+        if ret:
+            frame_copy = frame.copy()
+            outputs = model.predict(source=frame)
+            results = outputs[0].cpu().numpy()
+            for i, det in enumerate(results.boxes.xyxy):
+                cv2.rectangle(
+                    frame_copy,
+                    (int(det[0]), int(det[1])),
+                    (int(det[2]), int(det[3])),
+                    color=(0, 0, 255),
+                    thickness=2,
+                    lineType=cv2.LINE_AA
+                )
+            yield cv2.cvtColor(frame_copy, cv2.COLOR_BGR2RGB)
 
-outputs = gr.outputs.Image(type="filepath", label="Output Image")
-title = "Ultralytics YOLOv8: State-of-the-Art YOLO Models"
+inputs_video = [
+    gr.components.Video(type="filepath", label="Input Video"),
 
-examples = [['highway.jpg', 'turhancan97/yolov8m-trash', 640, 0.25, 0.45], ['highway1.jpg', 'turhancan97/yolov8m-trash', 640, 0.25, 0.45], ['small-vehicles1.jpeg', 'turhancan97/yolov8m-trash', 1280, 0.25, 0.45]]
-demo_app = gr.Interface(
-    fn=yolov8_inference,
-    inputs=inputs,
-    outputs=outputs,
-    title=title,
-    examples=examples,
-    cache_examples=True,
-    theme='huggingface',
+]
+outputs_video = [
+    gr.components.Image(type="numpy", label="Output Image"),
+]
+interface_video = gr.Interface(
+    fn=show_preds_video,
+    inputs=inputs_video,
+    outputs=outputs_video,
+    title="Pothole detector",
+    examples=video_path,
+    cache_examples=False,
 )
-demo_app.launch(debug=True, enable_queue=True)
+
+gr.TabbedInterface(
+    [interface_image, interface_video],
+    tab_names=['Image inference', 'Video inference']
+).queue().launch()

requirements.txt

@@ -1,5 +1,47 @@
-opencv_python
-torch
-sahi
-ultralytics==8.0.4
-ultralyticsplus==0.0.3
+# Ultralytics requirements
+# Usage: pip install -r requirements.txt
+
+# Base ----------------------------------------
+hydra-core>=1.2.0
+matplotlib>=3.2.2
+numpy>=1.18.5
+opencv-python>=4.1.1
+Pillow>=7.1.2
+PyYAML>=5.3.1
+requests>=2.23.0
+scipy>=1.4.1
+torch>=1.7.0
+torchvision>=0.8.1
+tqdm>=4.64.0
+ultralytics
+
+# Logging -------------------------------------
+tensorboard>=2.4.1
+# clearml
+# comet
+
+# Plotting ------------------------------------
+pandas>=1.1.4
+seaborn>=0.11.0
+
+# Export --------------------------------------
+# coremltools>=6.0  # CoreML export
+# onnx>=1.12.0  # ONNX export
+# onnx-simplifier>=0.4.1  # ONNX simplifier
+# nvidia-pyindex  # TensorRT export
+# nvidia-tensorrt  # TensorRT export
+# scikit-learn==0.19.2  # CoreML quantization
+# tensorflow>=2.4.1  # TF exports (-cpu, -aarch64, -macos)
+# tensorflowjs>=3.9.0  # TF.js export
+# openvino-dev  # OpenVINO export
+
+# Extras --------------------------------------
+ipython  # interactive notebook
+psutil  # system utilization
+thop>=0.1.1  # FLOPs computation
+# albumentations>=1.0.3
+# pycocotools>=2.0.6  # COCO mAP
+# roboflow
+
+# HUB -----------------------------------------
+GitPython>=3.1.24