12. onnx转为rknn测试时有很多重叠框的修改（python）-编程知识

我们下载rknn-toolkit2-master后并进行前面的处理后，进入到rknn-toolkit2-master\examples\onnx\yolov5文件夹，里面有个test.py文件，打开该文件，其代码如下：

# -*- coding: utf-8 -*-
# coding:utf-8import os
import urllib
import traceback
import time
import sys
import numpy as np
import cv2
from rknn.api import RKNN# Model from https://github.com/airockchip/rknn_model_zoo
ONNX_MODEL = 'yolov5s_relu.onnx'
RKNN_MODEL = 'yolov5s_relu.rknn'
IMG_PATH = './bus.jpg'
DATASET = './dataset.txt'QUANTIZE_ON = TrueOBJ_THRESH = 0.25
NMS_THRESH = 0.45
IMG_SIZE = 640CLASSES = ("person", "bicycle", "car", "motorbike ", "aeroplane ", "bus ", "train", "truck ", "boat", "traffic light","fire hydrant", "stop sign ", "parking meter", "bench", "bird", "cat", "dog ", "horse ", "sheep", "cow", "elephant","bear", "zebra ", "giraffe", "backpack", "umbrella", "handbag", "tie", "suitcase", "frisbee", "skis", "snowboard", "sports ball", "kite","baseball bat", "baseball glove", "skateboard", "surfboard", "tennis racket", "bottle", "wine glass", "cup", "fork", "knife ","spoon", "bowl", "banana", "apple", "sandwich", "orange", "broccoli", "carrot", "hot dog", "pizza ", "donut", "cake", "chair", "sofa","pottedplant", "bed", "diningtable", "toilet ", "tvmonitor", "laptop	", "mouse	", "remote ", "keyboard ", "cell phone", "microwave ","oven ", "toaster", "sink", "refrigerator ", "book", "clock", "vase", "scissors ", "teddy bear ", "hair drier", "toothbrush ")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 xy[:, 1] = x[:, 1] - x[:, 3] / 2  # top left yy[:, 2] = x[:, 0] + x[:, 2] / 2  # bottom right xy[:, 3] = x[:, 1] + x[:, 3] / 2  # bottom right yreturn ydef process(input, mask, anchors):anchors = [anchors[i] for i in mask]grid_h, grid_w = map(int, input.shape[0:2])box_confidence = input[..., 4]box_confidence = np.expand_dims(box_confidence, axis=-1)box_class_probs = input[..., 5:]box_xy = input[..., :2]*2 - 0.5col = 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 += gridbox_xy *= int(IMG_SIZE/grid_h)box_wh = pow(input[..., 2:4]*2, 2)box_wh = box_wh * anchorsbox = np.concatenate((box_xy, box_wh), axis=-1)return box, box_confidence, box_class_probsdef filter_boxes(boxes, box_confidences, box_class_probs):"""Filter boxes with box threshold. It's a bit different with origin yolov5 post process!# Argumentsboxes: ndarray, boxes of objects.box_confidences: ndarray, confidences of objects.box_class_probs: ndarray, class_probs of objects.# Returnsboxes: ndarray, filtered boxes.classes: ndarray, classes for boxes.scores: ndarray, scores for boxes."""boxes = boxes.reshape(-1, 4)box_confidences = box_confidences.reshape(-1)box_class_probs = box_class_probs.reshape(-1, box_class_probs.shape[-1])_box_pos = np.where(box_confidences >= OBJ_THRESH)boxes = boxes[_box_pos]box_confidences = box_confidences[_box_pos]box_class_probs = box_class_probs[_box_pos]class_max_score = np.max(box_class_probs, axis=-1)classes = np.argmax(box_class_probs, axis=-1)_class_pos = np.where(class_max_score >= OBJ_THRESH)boxes = boxes[_class_pos]classes = classes[_class_pos]scores = (class_max_score* box_confidences)[_class_pos]return boxes, classes, scoresdef nms_boxes(boxes, scores):"""Suppress non-maximal boxes.# Argumentsboxes: ndarray, boxes of objects.scores: ndarray, scores of objects.# Returnskeep: ndarray, index of effective boxes."""x = boxes[:, 0]y = boxes[:, 1]w = boxes[:, 2] - boxes[:, 0]h = boxes[:, 3] - boxes[:, 1]areas = w * horder = 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 * h1ovr = inter / (areas[i] + areas[order[1:]] - inter)inds = np.where(ovr <= NMS_THRESH)[0]order = order[inds + 1]keep = np.array(keep)return keepdef 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, Noneboxes = np.concatenate(nboxes)classes = np.concatenate(nclasses)scores = np.concatenate(nscores)return boxes, classes, scoresdef 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):top, left, right, bottom = boxprint('class: {}, score: {}'.format(CLASSES[cl], score))print('box coordinate left,top,right,down: [{}, {}, {}, {}]'.format(top, left, right, bottom))top = int(top)left = int(left)right = int(right)bottom = int(bottom)cv2.rectangle(image, (top, left), (right, bottom), (255, 0, 0), 2)cv2.putText(image, '{0} {1:.2f}'.format(CLASSES[cl], score),(top, left - 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 constraintsshape = 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 paddingratio = r, r  # width, height ratiosnew_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 paddingdw /= 2  # divide padding into 2 sidesdh /= 2if shape[::-1] != new_unpad:  # resizeim = 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 borderreturn im, ratio, (dw, dh)if __name__ == '__main__':# Create RKNN objectrknn = RKNN(verbose=True)# pre-process configprint('--> Config model')#rknn.config(mean_values=[[0, 0, 0]], std_values=[[255, 255, 255]], target_platform='rk3588')rknn.config(mean_values=[[0, 0, 0]], std_values=[[255, 255, 255]], target_platform='rk3588')print('done')# Load ONNX modelprint('--> Loading model')ret = rknn.load_onnx(model=ONNX_MODEL)if ret != 0:print('Load model failed!')exit(ret)print('done')# Build modelprint('--> Building model')ret = rknn.build(do_quantization=QUANTIZE_ON, dataset=DATASET)if ret != 0:print('Build model failed!')exit(ret)print('done')# Export RKNN modelprint('--> Export rknn model')ret = rknn.export_rknn(RKNN_MODEL)if ret != 0:print('Export rknn model failed!')exit(ret)print('done')# Init runtime environmentprint('--> Init runtime environment')ret = rknn.init_runtime()if ret != 0:print('Init runtime environment failed!')exit(ret)print('done')# Set inputsimg = cv2.imread(IMG_PATH)img, ratio, (dw, dh) = letterbox(img, new_shape=(IMG_SIZE, IMG_SIZE))img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)img = cv2.resize(img, (IMG_SIZE, IMG_SIZE))# Inferenceprint('--> Running model')outputs = rknn.inference(inputs=[img])#np.save('./onnx_yolov5_0.npy', outputs[0])#np.save('./onnx_yolov5_1.npy', outputs[1])#np.save('./onnx_yolov5_2.npy', outputs[2])print('done')# post processinput0_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)))boxes, classes, scores = yolov5_post_process(input_data)img_1 = cv2.cvtColor(img, cv2.COLOR_RGB2BGR)if boxes is not None:draw(img_1, boxes, scores, classes)cv2.imwrite('result.jpg', img_1)rknn.release()

该文件可以直接预测自带的rknn文件，但测试我们自己转换的rknn文件时，会有很多重叠的框，如下图：

我们分析上面的代码会发现，上面的代码是直接对图片处理，而我们训练时对图片进行了sigmoid函数处理，所以要对上面的代码进行修改如下：

# -*- coding: utf-8 -*-
# coding:utf-8import os
import urllib
import traceback
import time
import sys
import numpy as np
import cv2
from rknn.api import RKNN# Model from https://github.com/airockchip/rknn_model_zoo
ONNX_MODEL = 'best.onnx'
RKNN_MODEL = 'best.rknn'
IMG_PATH = './02.jpg'
DATASET = './dataset.txt'QUANTIZE_ON = TrueOBJ_THRESH = 0.5
NMS_THRESH = 0.45
IMG_SIZE = 640CLASSES = ("car", "moto", "persons")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 xy[:, 1] = x[:, 1] - x[:, 3] / 2  # top left yy[:, 2] = x[:, 0] + x[:, 2] / 2  # bottom right xy[:, 3] = x[:, 1] + x[:, 3] / 2  # bottom right yreturn ydef 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 - 0.5col = 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 += gridbox_xy *= int(IMG_SIZE/grid_h)box_wh = pow(sigmoid(input[..., 2:4]) * 2, 2)box_wh = box_wh * anchorsbox = np.concatenate((box_xy, box_wh), axis=-1)return box, box_confidence, box_class_probsdef filter_boxes(boxes, box_confidences, box_class_probs):"""Filter boxes with box threshold. It's a bit different with origin yolov5 post process!# Argumentsboxes: ndarray, boxes of objects.box_confidences: ndarray, confidences of objects.box_class_probs: ndarray, class_probs of objects.# Returnsboxes: ndarray, filtered boxes.classes: ndarray, classes for boxes.scores: ndarray, scores for boxes."""boxes = boxes.reshape(-1, 4)box_confidences = box_confidences.reshape(-1)box_class_probs = box_class_probs.reshape(-1, box_class_probs.shape[-1])_box_pos = np.where(box_confidences >= OBJ_THRESH)boxes = boxes[_box_pos]box_confidences = box_confidences[_box_pos]box_class_probs = box_class_probs[_box_pos]class_max_score = np.max(box_class_probs, axis=-1)classes = np.argmax(box_class_probs, axis=-1)_class_pos = np.where(class_max_score >= OBJ_THRESH)boxes = boxes[_class_pos]classes = classes[_class_pos]scores = (class_max_score* box_confidences)[_class_pos]return boxes, classes, scoresdef nms_boxes(boxes, scores):"""Suppress non-maximal boxes.# Argumentsboxes: ndarray, boxes of objects.scores: ndarray, scores of objects.# Returnskeep: ndarray, index of effective boxes."""x = boxes[:, 0]y = boxes[:, 1]w = boxes[:, 2] - boxes[:, 0]h = boxes[:, 3] - boxes[:, 1]areas = w * horder = 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 * h1ovr = inter / (areas[i] + areas[order[1:]] - inter)inds = np.where(ovr <= NMS_THRESH)[0]order = order[inds + 1]keep = np.array(keep)return keepdef yolov5_post_process(input_data):masks = [[0, 1, 2], [3, 4, 5], [6, 7, 8]]anchors = [[15,20], [20, 75], [28, 25], [31,136], [44,42],[53,215], [75,76], [98,421], [148,226]]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, Noneboxes = np.concatenate(nboxes)classes = np.concatenate(nclasses)scores = np.concatenate(nscores)return boxes, classes, scoresdef 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):top, left, right, bottom = boxprint('class: {}, score: {}'.format(CLASSES[cl], score))print('box coordinate left,top,right,down: [{}, {}, {}, {}]'.format(top, left, right, bottom))top = int(top)left = int(left)right = int(right)bottom = int(bottom)cv2.rectangle(image, (top, left), (right, bottom), (255, 0, 0), 2)cv2.putText(image, '{0} {1:.2f}'.format(CLASSES[cl], score),(top, left - 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 constraintsshape = 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 paddingratio = r, r  # width, height ratiosnew_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 paddingdw /= 2  # divide padding into 2 sidesdh /= 2if shape[::-1] != new_unpad:  # resizeim = 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 borderreturn im, ratio, (dw, dh)if __name__ == '__main__':# Create RKNN objectrknn = RKNN(verbose=True)# pre-process configprint('--> Config model')#rknn.config(mean_values=[[0, 0, 0]], std_values=[[255, 255, 255]], target_platform='rk3588')rknn.config(mean_values=[[0, 0, 0]], std_values=[[255, 255, 255]], target_platform='rk3588')print('done')# Load ONNX modelprint('--> Loading model')ret = rknn.load_onnx(model=ONNX_MODEL)if ret != 0:print('Load model failed!')exit(ret)print('done')# Build modelprint('--> Building model')ret = rknn.build(do_quantization=QUANTIZE_ON, dataset=DATASET)if ret != 0:print('Build model failed!')exit(ret)print('done')# Export RKNN modelprint('--> Export rknn model')ret = rknn.export_rknn(RKNN_MODEL)if ret != 0:print('Export rknn model failed!')exit(ret)print('done')# Init runtime environmentprint('--> Init runtime environment')ret = rknn.init_runtime()if ret != 0:print('Init runtime environment failed!')exit(ret)print('done')# Set inputsimg = cv2.imread(IMG_PATH)img, ratio, (dw, dh) = letterbox(img, new_shape=(IMG_SIZE, IMG_SIZE))img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)img = cv2.resize(img, (IMG_SIZE, IMG_SIZE))# Inferenceprint('--> Running model')outputs = rknn.inference(inputs=[img])#np.save('./onnx_yolov5_0.npy', outputs[0])#np.save('./onnx_yolov5_1.npy', outputs[1])#np.save('./onnx_yolov5_2.npy', outputs[2])print('done')# post processinput0_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)))boxes, classes, scores = yolov5_post_process(input_data)img_1 = cv2.cvtColor(img, cv2.COLOR_RGB2BGR)if boxes is not None:draw(img_1, boxes, scores, classes)cv2.imwrite('result.jpg', img_1)rknn.release()

用自己的模型预测结果如下：