[Python] Yolo v11 obj detection custom inference gives totally different results than yolo cli...

I am trying to run an exported verision of a fine-tunned yolov11n to detect roadsigns. When I run the model with the yolo cli on this exact same image, I get an object detected with confidence 0.86. But when I run it with my custom script, I get no meaningful detections - all confidence values are around 1e-7. I have been struggling to solve this for the past few days. I tried TensorFlow, Pillow, OpenCV, different normalization methods for preprocessing, but nothing seems to work. Since the model works, this either has to do with the preprocessing step, or with the post-processing step - does anyone have any ideas?

Netron architecture graph(input/output)

import onnxruntime as ort
import numpy as np
import cv2



class YoloInference:
# List of class names for YOLO model
classes = [
'speed20', 'speed30', 'speed50', 'speed60', 'speed70', 'speed80', 'speed100', 'speed120'
]

def __init__(self, model_path):
self.session = ort.InferenceSession(model_path)
self.input_name = self.session.get_inputs()[0].name
self.output_name = self.session.get_outputs()[0].name

def preprocess(self, image):
"""This functions preprocess the image before inference
preprocesses:resize(640x640),normalize,HWC to CHW,adds batch
Returns:
img preprocessed
"""
img = cv2.resize(image, (640, 640)) # Resize to model input size
img = img.astype(np.float32)
img = img / 255.0 # Normalize
img = np.transpose(img, [2, 0, 1]) # Change data layout from HWC to CHW
img = np.expand_dims(img, axis=0) # Add batch dimension
return img

def postprocess(self, output, conf_threshold=0.5, nms_threshold=0.1):
detections = output[0].T # Transpose the array

boxes = []
confidences = []
class_ids = []

for detection in detections: # Iterate through each of the 8400 predictions
box = detection[:4]
class_scores = detection[4:]

class_id = np.argmax(class_scores)
confidence = class_scores[class_id]
if confidence > conf_threshold:
# Convert from center coordinates to corner coordinates
cx, cy,box_width, box_height = box # Note the order: x, y, height, width
cx = cx.item()
cy = cy.item()
box_height = box_height.item()
box_width = box_width.item()
x1 = int((cx - box_width / 2))
y1 = int((cy - box_height / 2))
x2 = int(cx + box_width / 2)
y2 = int(cy + box_height / 2)
boxes.append([x1, y1, x2, y2])
confidences.append(float(confidence.item()))
class_ids.append(class_id)

# Apply non-maximum suppression (NMS)
indices = cv2.dnn.NMSBoxes(boxes, confidences, conf_threshold, nms_threshold)

print(confidences)

processed_results = []
if len(indices) > 0:
for i in indices.flatten():
x1, y1, x2, y2 = boxes
processed_results.append({
'class_id': self.classes[class_ids],
'confidence': confidences,
'box': [x1, y1, x2, y2]
})
return processed_results

def infer(self, image,desired_class_id=None): # 77-tedy 21-bear
h,w,_ = image.shape
input_image = self.preprocess(image)
output = self.session.run([self.output_name], {self.input_name: input_image})
processed_results = self.postprocess(output)
orig_height, orig_width = image.shape[:2]
scale_x = orig_width / w
scale_y = orig_height / h
if desired_class_id is not None:
boxes = [result['box'] for result in processed_results if result['class_id']==self.classes[desired_class_id]]
scores = [result['confidence'] for result in processed_results if result['class_id']==self.classes[desired_class_id]]
class_ids = [result['class_id'] for result in processed_results if result['class_id']==self.classes[desired_class_id]]
else:
boxes = [result['box'] for result in processed_results]
scores = [result['confidence'] for result in processed_results]
class_ids = [result['class_id'] for result in processed_results]
return boxes, scores, class_ids, scale_x, scale_y

def draw_detections(self,image, boxes, scores, class_ids, scale_x, scale_y):
for box, score, class_id in zip(boxes, scores, class_ids):
x1, y1, x2, y2 = box

# Scale the coordinates back to the original image size
x1 = int(x1 * scale_x)
y1 = int(y1 * scale_y)
x2 = int(x2 * scale_x)
y2 = int(y2 * scale_y)

print(x1, y1, x2, y2)

# Ensure class_id is used correctly to fetch class name
class_name = class_id if isinstance(class_id, str) else self.classes[class_id]

# Draw the bounding box
cv2.rectangle(image, (x1, y1), (x2, y2), (0, 255, 0), 2)

# Label the bounding box with class name and confidence score
label = f'{class_name}: {score:.2f}'
cv2.putText(image, label, (x1, y1 - 10), cv2.FONT_HERSHEY_SIMPLEX, 0.9, (36, 255, 12), 2)

return image

if __name__ == "__main__":
model_path = r"D:\Research licenta\yolo-speedlimits-combined-dataset-nano.onnx"
image_path = r"D:\AndroidStudioProjects\Licenta\app\src\main\assets\0000000089.png"

# Load and run inference
yolo = YoloInference(model_path)
image = cv2.imread(image_path)
boxes, scores, class_ids, scale_x, scale_y = yolo.infer(image)

# Draw and display detections
image_with_detections = yolo.draw_detections(image, boxes, scores, class_ids, scale_x, scale_y)
cv2.imwrite("Detectionsl.jpg", image_with_detections)

Continue reading...