- python list_dataset_file.py
复制代码
- git clone https://github.com/EASY-EAI/yolov5.git
复制代码
- python train.py --data mask.yaml --cfg yolov5s.yaml --weights "" --batch-size 64
复制代码
- python export.py --include onnx --rknpu RV1126 --weights ./runs/train/exp/weights/best.pt
复制代码
- docker load --input /home/developer/rknn-toolkit/rknn-toolkit-1.7.1-docker.tar.gz
复制代码
7.4.3 进入镜像bash环境- docker run -t -i --privileged -v /dev/bus/usb:/dev/bus/usb rknn-toolkit:1.7.1 /bin/bash
复制代码
- docker run -t -i --privileged -v /dev/bus/usb:/dev/bus/usb -v /home/developer/rknn-toolkit/model_convert:/test rknn-toolkit:1.7.1 /bin/bash
复制代码
- cd /test/mask_object_detect/
复制代码
- python gen_list.py
复制代码
- import os
- import urllib
- import traceback
- import time
- import sys
- import numpy as np
- import cv2
- from rknn.api import RKNN
- ONNX_MODEL = 'best.onnx'
- RKNN_MODEL = './yolov5_mask_rv1126.rknn'
- DATASET = './pic_path.txt'
- QUANTIZE_ON = True
- if __name__ == '__main__':
- # Create RKNN object
- rknn = RKNN(verbose=True)
- if not os.path.exists(ONNX_MODEL):
- print('model not exist')
- exit(-1)
- # pre-process config
- print('--> Config model')
- rknn.config(reorder_channel='0 1 2',
- mean_values=[[0, 0, 0]],
- std_values=[[255, 255, 255]],
- optimization_level=3,
- target_platform = 'rv1126',
- output_optimize=1,
- quantize_input_node=QUANTIZE_ON)
- print('done')
- # Load ONNX model
- print('--> Loading model')
- ret = rknn.load_onnx(model=ONNX_MODEL)
- if ret != 0:
- print('Load yolov5 failed!')
- exit(ret)
- print('done')
- # Build model
- print('--> Building model')
- ret = rknn.build(do_quantization=QUANTIZE_ON, dataset=DATASET)
- if ret != 0:
- print('Build yolov5 failed!')
- exit(ret)
- print('done')
- # Export RKNN model
- print('--> Export RKNN model')
- ret = rknn.export_rknn(RKNN_MODEL)
- if ret != 0:
- print('Export yolov5rknn failed!')
- exit(ret)
- print('done')
复制代码
- python rknn_convert.py
复制代码
- import os
- import urllib
- import traceback
- import time
- import sys
- import numpy as np
- import cv2
- import random
- from rknn.api import RKNN
- RKNN_MODEL = 'yolov5_mask_rv1126.rknn'
- IMG_PATH = './test.jpg'
- DATASET = './dataset.txt'
- BOX_THRESH = 0.25
- NMS_THRESH = 0.6
- IMG_SIZE = 640
- CLASSES = ("head", "mask")
- def sigmoid(x):
- return 1 / (1 + np.exp(-x))
- def xywh2xyxy(x):
- # Convert [x, y, w, h] to [x1, y1, x2, y2]
- y = np.copy(x)
- y[:, 0] = x[:, 0] - x[:, 2] / 2 # top left x
- y[:, 1] = x[:, 1] - x[:, 3] / 2 # top left y
- y[:, 2] = x[:, 0] + x[:, 2] / 2 # bottom right x
- y[:, 3] = x[:, 1] + x[:, 3] / 2 # bottom right y
- return y
- def process(input, mask, anchors):
- anchors = [anchors[i] for i in mask]
- grid_h, grid_w = map(int, input.shape[0:2])
- box_confidence = sigmoid(input[..., 4])
- box_confidence = np.expand_dims(box_confidence, axis=-1)
- box_class_probs = sigmoid(input[..., 5:])
- box_xy = sigmoid(input[..., :2])*2 - 0.5
- col = np.tile(np.arange(0, grid_w), grid_w).reshape(-1, grid_w)
- row = np.tile(np.arange(0, grid_h).reshape(-1, 1), grid_h)
- col = col.reshape(grid_h, grid_w, 1, 1).repeat(3, axis=-2)
- row = row.reshape(grid_h, grid_w, 1, 1).repeat(3, axis=-2)
- grid = np.concatenate((col, row), axis=-1)
- box_xy += grid
- box_xy *= int(IMG_SIZE/grid_h)
- box_wh = pow(sigmoid(input[..., 2:4])*2, 2)
- box_wh = box_wh * anchors
- box = np.concatenate((box_xy, box_wh), axis=-1)
- return box, box_confidence, box_class_probs
- def filter_boxes(boxes, box_confidences, box_class_probs):
- """Filter boxes with box threshold. It's a bit different with origin yolov5 post process!
- # Arguments
- boxes: ndarray, boxes of objects.
- box_confidences: ndarray, confidences of objects.
- box_class_probs: ndarray, class_probs of objects.
- # Returns
- boxes: ndarray, filtered boxes.
- classes: ndarray, classes for boxes.
- scores: ndarray, scores for boxes.
- """
- box_scores = box_confidences * box_class_probs
- box_classes = np.argmax(box_class_probs, axis=-1)
- box_class_scores = np.max(box_scores, axis=-1)
- pos = np.where(box_confidences[...,0] >= BOX_THRESH)
- boxes = boxes[pos]
- classes = box_classes[pos]
- scores = box_class_scores[pos]
- return boxes, classes, scores
- def nms_boxes(boxes, scores):
- """Suppress non-maximal boxes.
- # Arguments
- boxes: ndarray, boxes of objects.
- scores: ndarray, scores of objects.
- # Returns
- keep: ndarray, index of effective boxes.
- """
- x = boxes[:, 0]
- y = boxes[:, 1]
- w = boxes[:, 2] - boxes[:, 0]
- h = boxes[:, 3] - boxes[:, 1]
- areas = w * h
- order = scores.argsort()[::-1]
- keep = []
- while order.size > 0:
- i = order[0]
- keep.append(i)
- xx1 = np.maximum(x[i], x[order[1:]])
- yy1 = np.maximum(y[i], y[order[1:]])
- xx2 = np.minimum(x[i] + w[i], x[order[1:]] + w[order[1:]])
- yy2 = np.minimum(y[i] + h[i], y[order[1:]] + h[order[1:]])
- w1 = np.maximum(0.0, xx2 - xx1 + 0.00001)
- h1 = np.maximum(0.0, yy2 - yy1 + 0.00001)
- inter = w1 * h1
- ovr = inter / (areas[i] + areas[order[1:]] - inter)
- inds = np.where(ovr <= NMS_THRESH)[0]
- order = order[inds + 1]
- keep = np.array(keep)
- return keep
- def yolov5_post_process(input_data):
- masks = [[0, 1, 2], [3, 4, 5], [6, 7, 8]]
- anchors = [[10, 13], [16, 30], [33, 23], [30, 61], [62, 45],
- [59, 119], [116, 90], [156, 198], [373, 326]]
- boxes, classes, scores = [], [], []
- for input,mask in zip(input_data, masks):
- b, c, s = process(input, mask, anchors)
- b, c, s = filter_boxes(b, c, s)
- boxes.append(b)
- classes.append(c)
- scores.append(s)
- boxes = np.concatenate(boxes)
- boxes = xywh2xyxy(boxes)
- classes = np.concatenate(classes)
- scores = np.concatenate(scores)
- nboxes, nclasses, nscores = [], [], []
- for c in set(classes):
- inds = np.where(classes == c)
- b = boxes[inds]
- c = classes[inds]
- s = scores[inds]
- keep = nms_boxes(b, s)
- nboxes.append(b[keep])
- nclasses.append(c[keep])
- nscores.append(s[keep])
- if not nclasses and not nscores:
- return None, None, None
- boxes = np.concatenate(nboxes)
- classes = np.concatenate(nclasses)
- scores = np.concatenate(nscores)
- return boxes, classes, scores
- def scale_coords(x1, y1, x2, y2, dst_width, dst_height):
-
- dst_top, dst_left, dst_right, dst_bottom = 0, 0, 0, 0
- gain = 0
- if dst_width > dst_height:
- image_max_len = dst_width
- gain = IMG_SIZE / image_max_len
- resized_height = dst_height * gain
- height_pading = (IMG_SIZE - resized_height)/2
- print("height_pading:", height_pading)
- y1 = (y1 - height_pading)
- y2 = (y2 - height_pading)
-
- print("gain:", gain)
- dst_x1 = int(x1 / gain)
- dst_y1 = int(y1 / gain)
- dst_x2 = int(x2 / gain)
- dst_y2 = int(y2 / gain)
- return dst_x1, dst_y1, dst_x2, dst_y2
- def plot_one_box(x, img, color=None, label=None, line_thickness=None):
- tl = line_thickness or round(0.002 * (img.shape[0] + img.shape[1]) / 2) + 1 # line/font thickness
- color = color or [random.randint(0, 255) for _ in range(3)]
- c1, c2 = (int(x[0]), int(x[1])), (int(x[2]), int(x[3]))
- cv2.rectangle(img, c1, c2, color, thickness=tl, lineType=cv2.LINE_AA)
- if label:
- tf = max(tl - 1, 1) # font thickness
- t_size = cv2.getTextSize(label, 0, fontScale=tl / 3, thickness=tf)[0]
- c2 = c1[0] + t_size[0], c1[1] - t_size[1] - 3
- cv2.rectangle(img, c1, c2, color, -1, cv2.LINE_AA) # filled
- cv2.putText(img, label, (c1[0], c1[1] - 2), 0, tl / 3, [225, 255, 255], thickness=tf, lineType=cv2.LINE_AA)
- def draw(image, boxes, scores, classes):
- """Draw the boxes on the image.
- # Argument:
- image: original image.
- boxes: ndarray, boxes of objects.
- classes: ndarray, classes of objects.
- scores: ndarray, scores of objects.
- all_classes: all classes name.
- """
- for box, score, cl in zip(boxes, scores, classes):
- x1, y1, x2, y2 = box
- print('class: {}, score: {}'.format(CLASSES[cl], score))
- print('box coordinate x1,y1,x2,y2: [{}, {}, {}, {}]'.format(x1, y1, x2, y2))
- x1 = int(x1)
- y1 = int(y1)
- x2 = int(x2)
- y2 = int(y2)
- dst_x1, dst_y1, dst_x2, dst_y2 = scale_coords(x1, y1, x2, y2, image.shape[1], image.shape[0])
- #print("img.cols:", image.cols)
- plot_one_box((dst_x1, dst_y1, dst_x2, dst_y2), image, label='{0} {1:.2f}'.format(CLASSES[cl], score))
-
- '''
- cv2.rectangle(image, (dst_x1, dst_y1), (dst_x2, dst_y2), (255, 0, 0), 2)
- cv2.putText(image, '{0} {1:.2f}'.format(CLASSES[cl], score),
- (dst_x1, dst_y1 - 6),
- cv2.FONT_HERSHEY_SIMPLEX,
- 0.6, (0, 0, 255), 2)
- '''
- def letterbox(im, new_shape=(640, 640), color=(0, 0, 0)):
- # Resize and pad image while meeting stride-multiple constraints
- shape = im.shape[:2] # current shape [height, width]
- if isinstance(new_shape, int):
- new_shape = (new_shape, new_shape)
- # Scale ratio (new / old)
- r = min(new_shape[0] / shape[0], new_shape[1] / shape[1])
- # Compute padding
- ratio = r, r # width, height ratios
- new_unpad = int(round(shape[1] * r)), int(round(shape[0] * r))
- dw, dh = new_shape[1] - new_unpad[0], new_shape[0] - new_unpad[1] # wh padding
- dw /= 2 # divide padding into 2 sides
- dh /= 2
- if shape[::-1] != new_unpad: # resize
- im = cv2.resize(im, new_unpad, interpolation=cv2.INTER_LINEAR)
- top, bottom = int(round(dh - 0.1)), int(round(dh + 0.1))
- left, right = int(round(dw - 0.1)), int(round(dw + 0.1))
- im = cv2.copyMakeBorder(im, top, bottom, left, right, cv2.BORDER_CONSTANT, value=color) # add border
- return im, ratio, (dw, dh)
- if __name__ == '__main__':
- # Create RKNN object
- rknn = RKNN(verbose=True)
- print('--> Loading model')
- ret = rknn.load_rknn(RKNN_MODEL)
- if ret != 0:
- print('load rknn model failed')
- exit(ret)
- print('done')
- # init runtime environment
- print('--> Init runtime environment')
- ret = rknn.init_runtime()
- # ret = rknn.init_runtime('rv1126', device_id='1126')
- if ret != 0:
- print('Init runtime environment failed')
- exit(ret)
- print('done')
- # Set inputs
- img = cv2.imread(IMG_PATH)
- letter_img, ratio, (dw, dh) = letterbox(img, new_shape=(IMG_SIZE, IMG_SIZE))
- letter_img = cv2.cvtColor(letter_img, cv2.COLOR_BGR2RGB)
- # Inference
- print('--> Running model')
- outputs = rknn.inference(inputs=[letter_img])
- print('--> inference done')
- # post process
- input0_data = outputs[0]
- input1_data = outputs[1]
- input2_data = outputs[2]
- input0_data = input0_data.reshape([3,-1]+list(input0_data.shape[-2:]))
- input1_data = input1_data.reshape([3,-1]+list(input1_data.shape[-2:]))
- input2_data = input2_data.reshape([3,-1]+list(input2_data.shape[-2:]))
- input_data = list()
- input_data.append(np.transpose(input0_data, (2, 3, 0, 1)))
- input_data.append(np.transpose(input1_data, (2, 3, 0, 1)))
- input_data.append(np.transpose(input2_data, (2, 3, 0, 1)))
- print('--> transpose done')
- boxes, classes, scores = yolov5_post_process(input_data)
- print('--> get result done')
- #img_1 = cv2.cvtColor(img, cv2.COLOR_RGB2BGR)
- if boxes is not None:
- draw(img, boxes, scores, classes)
- cv2.imwrite('./result.jpg', img)
- #cv2.imshow("post process result", img_1)
- #cv2.waitKeyEx(0)
- rknn.release()
复制代码
- python precompile_rknn.py
复制代码
- tar -xvf yolov5_detect_C_demo.tar.bz2
复制代码
9.3.2 编译yolov5 demo- ./build.sh
复制代码
- adb push yolov5_detect_demo_release/ /userdata
复制代码
- adb shell
- cd /userdata/yolov5_detect_demo_release/
- ./yolov5_detect_demo
复制代码
- adb pull /userdata/yolov5_detect_demo_release/result.jpg .
复制代码
- tar -xvf yolov5_detect_camera_demo.tar.tar.bz2
复制代码
10.3.2 编译yolov5 camera demo- ./build.sh
复制代码
- adb push yolov5_detect_camera_demo_release/ /userdata
复制代码
- adb shell
- cd /userdata/yolov5_detect_camera_demo_release/
- ./yolov5_detect_camera_demo
复制代码
资料名称 | 链接 |
训练代码github | |
算法教程完整源码包 | |
硬件外设库源码github https://github.com/EASY-EAI/EASY-EAI-Toolkit-C-SDK] |
欢迎光临 Toybrick (https://t.rock-chips.com/) | Powered by Discuz! X3.3 |