trial

app.py

@@ -1,74 +1,13 @@
 import gradio as gr
 import torch
-from ultralytics import YOLO
-import cv2
-import numpy as np
-from math import atan2, cos, sin, sqrt, pi
+from sahi.prediction import ObjectPrediction
+from sahi.utils.cv import visualize_object_predictions, read_image
+from ultralyticsplus import YOLO
 
 # 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')
-
-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]
- 
-
-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)
-
-  return angle_deg
+torch.hub.download_url_to_file('https://raw.githubusercontent.com/kadirnar/dethub/main/data/images/highway.jpg', 'highway.jpg')
+torch.hub.download_url_to_file('https://user-images.githubusercontent.com/34196005/142742872-1fefcc4d-d7e6-4c43-bbb7-6b5982f7e4ba.jpg', 'highway1.jpg')
+torch.hub.download_url_to_file('https://raw.githubusercontent.com/obss/sahi/main/tests/data/small-vehicles1.jpeg', 'small-vehicles1.jpeg')
 
 def yolov8_inference(
     image: gr.inputs.Image = None,
@@ -91,35 +30,34 @@ def yolov8_inference(
     model = YOLO(model_path)
     model.conf = conf_threshold
     model.iou = iou_threshold
-    #read image
-    image = cv2.imread(image)
-    #resize image (optional)
-    img_res_toshow = cv2.resize(image, None, fx= 0.5, fy= 0.5, interpolation= cv2.INTER_LINEAR)
-    height=img_res_toshow.shape[0]
-    width=img_res_toshow.shape[1]
-    dim=(width,height)
     results = model.predict(image, imgsz=image_size, return_outputs=True)
-    #obtain BW image
-    bw=(results[0].masks.masks[0].cpu().numpy() * 255).astype("uint8")
-    #BW image with same dimention of initial image
-    bw=cv2.resize(bw, dim, interpolation = cv2.INTER_AREA)
-    img=img_res_toshow
-    contours, _ = cv2.findContours(bw, cv2.RETR_LIST, cv2.CHAIN_APPROX_NONE)
-    for i, c in enumerate(contours):
-        # Calculate the area of each contour
-        area = cv2.contourArea(c)
-        
-        # Ignore contours that are too small or too large
-        if area < 3700 or 100000 < area:
-            continue
-        
-        # Draw each contour only for visualisation purposes
-        cv2.drawContours(img, contours, i, (0, 0, 255), 2)
-        
-        # Find the orientation of each shape
-        print(getOrientation(c, img))
+    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)
+
+    image = read_image(image)
+    output_image = visualize_object_predictions(image=image, object_prediction_list=object_prediction_list)
+    return output_image['image']
         
-    return img
 
 inputs = [
     gr.inputs.Image(type="filepath", label="Input Image"),

requirements.txt

@@ -1,3 +1,5 @@
-opencv-python==4.7.0.72
-torch==2.0.1
-ultralytics==8.0.100
+opencv_python
+sahi
+torch
+ultralytics==8.0.4
+ultralyticsplus==0.0.3