Skip to content

GitLab

Commit b19fd646 authored by yaoht's avatar yaoht
Browse files

comment dynamic part

parent 04e4e763
Hide whitespace changes
Inline Side-by-side
Showing with 6 additions and 170 deletions
Python/yolox_infer_migraphx.py
View file @ b19fd646
......@@ -275,151 +275,6 @@ class YOLOX:
# Generate a color palette for the classes
self.color_palette = np.random.uniform(0, 255, size=(len(self.classNames), 3))
# def draw_detections(self, img, box, score, class_id):
# """
# Draws bounding boxes and labels on the input image based on the detected objects.
# Args:
# img: The input image to draw detections on.
# box: Detected bounding box.
# score: Corresponding detection score.
# class_id: Class ID for the detected object.
# Returns:
# None
# """
# # Extract the coordinates of the bounding box
# x1, y1, w, h = box
# # Retrieve the color for the class ID
# color = self.color_palette[class_id]
# # Draw the bounding box on the image
# cv2.rectangle(img, (int(x1), int(y1)), (int(x1 + w), int(y1 + h)), color, 2)
# # Create the label text with class name and score
# label = f'{self.classNames[class_id]}: {score:.2f}'
# # Calculate the dimensions of the label text
# (label_width, label_height), _ = cv2.getTextSize(label, cv2.FONT_HERSHEY_SIMPLEX, 0.5, 1)
# # Calculate the position of the label text
# label_x = x1
# label_y = y1 - 10 if y1 - 10 > label_height else y1 + 10
# # Draw a filled rectangle as the background for the label text
# cv2.rectangle(img, (label_x, label_y - label_height), (label_x + label_width, label_y + label_height), color,
# cv2.FILLED)
# # Draw the label text on the image
# cv2.putText(img, label, (label_x, label_y), cv2.FONT_HERSHEY_SIMPLEX, 0.5, (0, 0, 0), 1, cv2.LINE_AA)
# def preprocess(self, image):
# """
# Preprocesses the input image before performing inference.
# Returns:
# image_data: Preprocessed image data ready for inference.
# """
# # Read the input image using OpenCV
# # self.img = cv2.imread(self.input_image)
# self.img = image
# # Get the height and width of the input image
# self.img_height, self.img_width = self.img.shape[:2]
# # Convert the image color space from BGR to RGB
# img = cv2.cvtColor(self.img, cv2.COLOR_BGR2RGB)
# # Resize the image to match the input shape
# img = cv2.resize(img, (self.inputWidth, self.inputHeight))
# # Normalize the image data by dividing it by 255.0
# image_data = np.array(img) / 255.0
# # Transpose the image to have the channel dimension as the first dimension
# image_data = np.transpose(image_data, (2, 0, 1)) # Channel first
# # Expand the dimensions of the image data to match the expected input shape
# image_data = np.expand_dims(image_data, axis=0).astype(np.float32)
# # Make array memery contiguous
# image_data = np.ascontiguousarray(image_data)
# # Return the preprocessed image data
# return image_data
# def postprocess(self, input_image, output):
# """
# Performs post-processing on the model's output to extract bounding boxes, scores, and class IDs.
# Args:
# input_image (numpy.ndarray): The input image.
# output (numpy.ndarray): The output of the model.
# Returns:
# numpy.ndarray: The input image with detections drawn on it.
# """
# # Transpose and squeeze the output to match the expected shape
# outputs = np.transpose(np.squeeze(output[0]))
# # Get the number of rows in the outputs array
# rows = outputs.shape[0]
# # Lists to store the bounding boxes, scores, and class IDs of the detections
# boxes = []
# scores = []
# class_ids = []
# # Calculate the scaling factors for the bounding box coordinates
# x_factor = self.img_width / self.inputWidth
# y_factor = self.img_height / self.inputHeight
# # Iterate over each row in the outputs array
# for i in range(rows):
# # Extract the class scores from the current row
# classes_scores = outputs[i][4:]
# # Find the maximum score among the class scores
# max_score = np.amax(classes_scores)
# # If the maximum score is above the confidence threshold
# if max_score >= self.confThreshold:
# # Get the class ID with the highest score
# class_id = np.argmax(classes_scores)
# # Extract the bounding box coordinates from the current row
# x, y, w, h = outputs[i][0], outputs[i][1], outputs[i][2], outputs[i][3]
# # Calculate the scaled coordinates of the bounding box
# left = int((x - w / 2) * x_factor)
# top = int((y - h / 2) * y_factor)
# width = int(w * x_factor)
# height = int(h * y_factor)
# # Add the class ID, score, and box coordinates to the respective lists
# class_ids.append(class_id)
# scores.append(max_score)
# boxes.append([left, top, width, height])
# # Apply non-maximum suppression to filter out overlapping bounding boxes
# indices = cv2.dnn.NMSBoxes(boxes, scores, self.confThreshold, self.nmsThreshold)
# # Iterate over the selected indices after non-maximum suppression
# for i in indices:
# # Get the box, score, and class ID corresponding to the index
# box = boxes[i]
# score = scores[i]
# class_id = class_ids[i]
# # Draw the detection on the input image
# self.draw_detections(input_image, box, score, class_id)
# # Return the modified input image
# return input_image
def preproc(self, img, input_size, swap=(2, 0, 1)):
if len(img.shape) == 3:
padded_img = np.ones((input_size[0], input_size[1], 3), dtype=np.uint8) * 114
......@@ -466,27 +321,16 @@ class YOLOX:
# self.inputWidth = input_shape[3]
# self.inputHeight = input_shape[2]
# 输入图片预处理
# input_img = self.preprocess(image)
img, ratio = self.preproc(image, input_shape)
flat_predictions = np.array(img).ravel()
for i in range(min(100, len(flat_predictions))):
print(flat_predictions[i])
# 执行推理
start = time.time()
result = self.model.run({self.inputName: img})
print('net forward time: {:.4f}'.format(time.time() - start))
# 模型输出结果后处理
# dstimg = self.postprocess(image, result)
predictions = self.demo_postprocess(np.array(result[0]), input_shape)[0]
# flat_predictions = np.array(result[0]).ravel()
# for i in range(min(100, len(flat_predictions))):
# print(flat_predictions[i])
boxes = predictions[:, :4]
scores = predictions[:, 4:5] * predictions[:, 5:]
print("max(predictions[:, 4:5]):{}".format(np.amax(predictions[:, 4:5])))
print("max(predictions[:, 5:]):{}".format(np.amax(predictions[:, 5:])))
print("max(scores):{}".format(np.amax(scores)))
boxes_xyxy = np.ones_like(boxes)
boxes_xyxy[:, 0] = boxes[:, 0] - boxes[:, 2]/2.
boxes_xyxy[:, 1] = boxes[:, 1] - boxes[:, 3]/2.
......@@ -524,9 +368,6 @@ def yoloX_Static(imgpath, modelpath, confThreshold, nmsThreshold, output_dir, in
srcimg = cv2.imread(imgpath, 1)
dstimg = yoloX_detector.detect(srcimg, output_dir, imgpath, input_shape)
# 保存检测结果
# cv2.imwrite("./Result.jpg", dstimg)
print("Success to save result")
......@@ -545,11 +386,6 @@ def yoloX_dynamic(imgpath, modelpath, confThreshold, nmsThreshold, output_dir, i
for i, image in enumerate(image_lists):
print("Start to inference image{}".format(i))
dstimg = yoloX_detector.detect(image, output_dir, image_name_lists[i], input_shape)
# 保存检测结果
# result_name = "Result{}.jpg".format(i)
# cv2.imwrite(result_name, dstimg)
print("Success to save results")
if __name__ == '__main__':
......@@ -562,7 +398,7 @@ if __name__ == '__main__':
parser.add_argument('--confThreshold', default=0.5, type=float, help='class confidence')
parser.add_argument('--nmsThreshold', default=0.5, type=float, help='nms iou thresh')
parser.add_argument("--staticInfer",action="store_true",default=False,help="Performing static inference")
parser.add_argument("--dynamicInfer",action="store_true",default=False,help="Performing dynamic inference")
# parser.add_argument("--dynamicInfer",action="store_true",default=False,help="Performing dynamic inference")
parser.add_argument(
"-o",
"--output_dir",
......@@ -582,6 +418,6 @@ if __name__ == '__main__':
# 静态推理
if args.staticInfer:
yoloX_Static(args.imgPath, args.staticModelPath, args.confThreshold, args.nmsThreshold, args.output_dir, input_shape)
# 动态推理
if args.dynamicInfer:
yoloX_dynamic(args.imgFolderPath, args.dynamicModelPath, args.confThreshold, args.nmsThreshold, args.output_dir, input_shape)
# 动态推理 暂不支持
# if args.dynamicInfer:
# yoloX_dynamic(args.imgFolderPath, args.dynamicModelPath, args.confThreshold, args.nmsThreshold, args.output_dir, input_shape)
Src/main.cpp
View file @ b19fd646
......@@ -10,7 +10,7 @@ void MIGraphXSamplesUsage(char* programName)
printf("Usage : %s <index> \n", programName);
printf("index:\n");
printf("\t 0) YOLOX sample.\n");
printf("\t 1) YOLOX Dynamic sample.\n");
// printf("\t 1) YOLOX Dynamic sample.\n"); 暂不支持
}
void Sample_YOLOX();
......@@ -37,7 +37,7 @@ int main(int argc, char *argv[])
}
case '1':
{
Sample_YOLOX_Dynamic();
// Sample_YOLOX_Dynamic(); 暂不支持
break;
}
default :
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment