import os
import urllib
import traceback
import time
import sys
import numpy as np
import cv2
from rknn.api import RKNN
ONNX_MODEL = 'yolov5s.onnx'
RKNN_MODEL = 'yolov5s.rknn'
IMG_PATH = './bus.jpg'
DATASET = './dataset.txt'
QUANTIZE_ON = True
BOX_THRESH = 0.5
NMS_THRESH = 0.4
IMG_SIZE = 640
#CLASSES = ("face")
CLASSES = ("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 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])
print("grind_h::", grid_h)
print("grind_w::", grid_w)#这里就是20*20, 40*40, 80*80;
box_confidence = sigmoid(input[..., 4])
box_confidence = np.expand_dims(box_confidence, axis=-1)
#box_class_probs = sigmoid(input[..., 5:])
box_class_probs = sigmoid(input[..., 15:])
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)
print("col after tile:", col)
print("row after tile:", row)#这里的col row是0 1 2 3 4 5....20；
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)
print("col after reshape:", col)
print("row after reshape:", row)
grid = np.concatenate((col, row), axis=-1)#[col, row]
print("grid after concatenate::", grid)
box_xy += grid #[x+col, y+row]
box_xy *= int(IMG_SIZE/grid_h) #相当于C++里面的那个*stride。
box_wh = pow(sigmoid(input[..., 2:4])*2, 2)#pow表示x的y次方。
print("box_wh::", box_wh)
box_wh = box_wh * anchors
print("box_xy:::", box_xy)
box = np.concatenate((box_xy, box_wh), axis=-1)
print("input[..., 2:4]::", input[..., 5:15])
print("anchors:::",anchors)
lanmark1_xy = (input[..., 5:7]*anchors + grid)*(int(IMG_SIZE/grid_h))
lanmark2_xy = (input[..., 7:9]*anchors + grid)*(int(IMG_SIZE/grid_h))
lanmark3_xy = (input[..., 9:11]*anchors + grid)*(int(IMG_SIZE/grid_h))
lanmark4_xy = (input[..., 11:13]*anchors + grid)*(int(IMG_SIZE/grid_h))
lanmark5_xy = (input[..., 13:15]*anchors + grid)*(int(IMG_SIZE/grid_h))
print("lanmark1_xy:", lanmark1_xy)
print("lanmark2_xy:", lanmark2_xy)
print("lanmark3_xy:", lanmark3_xy)
print("lanmark4_xy:", lanmark4_xy)
print("lanmark5_xy:", lanmark5_xy)
lanmarks = np.concatenate((lanmark1_xy, lanmark2_xy, lanmark3_xy, lanmark4_xy, lanmark5_xy), axis=-1)
return box, box_confidence, box_class_probs, lanmarks
def filter_boxes(boxes, box_confidences, box_class_probs, landmarks):
"""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_classes = np.argmax(box_class_probs, axis=-1)
box_class_scores = np.max(box_class_probs, axis=-1)
pos = np.where(box_confidences[...,0] >= BOX_THRESH)
boxes = boxes[pos]
classes = box_classes[pos]
scores = box_class_scores[pos]
marks = landmarks[pos]
return boxes, classes, scores, marks
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, landmarks = [], [], [], []
for input,mask in zip(input_data, masks):
b, c, s, l = process(input, mask, anchors)
b, c, s, l = filter_boxes(b, c, s, l)
boxes.append(b)
classes.append(c)
scores.append(s)
landmarks.append(l)
boxes = np.concatenate(boxes)
boxes = xywh2xyxy(boxes)
classes = np.concatenate(classes)
scores = np.concatenate(scores)
landmarks = np.concatenate(landmarks)
nboxes, nclasses, nscores, nlandmarks = [], [], [], []
for c in set(classes):
inds = np.where(classes == c)
b = boxes[inds]
c = classes[inds]
s = scores[inds]
l = landmarks[inds]
keep = nms_boxes(b, s)
nboxes.append(b[keep])
nclasses.append(c[keep])
nscores.append(s[keep])
nlandmarks.append(l[keep])
if not nclasses and not nscores:
return None, None, None
boxes = np.concatenate(nboxes)
classes = np.concatenate(nclasses)
scores = np.concatenate(nscores)
landmarks = np.concatenate(nlandmarks)
return boxes, classes, scores, landmarks
def draw(image, boxes, scores, classes, landmarks):
"""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, landmark in zip(boxes, scores, classes, landmarks):
top, left, right, bottom = box
print('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)
print("(landmark[0], landmark[1])...:", landmark[0], landmark[1])
cv2.circle(image, (int(landmark[0]), int(landmark[1])), 3, (255,0,0),0)
cv2.circle(image, (int(landmark[2]), int(landmark[3])), 3, (255,0,0),0)
cv2.circle(image, (int(landmark[4]), int(landmark[5])), 3, (255,0,0),0)
cv2.circle(image, (int(landmark[6]), int(landmark[7])), 3, (255,0,0),0)
cv2.circle(image, (int(landmark[8]), int(landmark[9])), 3, (255,0,0),0)
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 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()
# Load rknn model
ret = rknn.load_rknn("./yolov5s-face.rknn")
if ret != 0:
print('Load RKNN model failed.')
exit(ret)
# init runtime environment
print('--> Init runtime environment')
ret = rknn.init_runtime()
# ret = rknn.init_runtime('rk1808', device_id='1808')
if ret != 0:
print('Init runtime environment failed')
exit(ret)
print('done')
# Set inputs
img = cv2.imread("ldh.jpeg")
# 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))
# Inference
print('--> Running model')
outputs = rknn.inference(inputs=[img])
# post process
input0_data = outputs[0]
input1_data = outputs[1]
input2_data = outputs[2]
print("input0_data::", input0_data.shape)
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, landmarks = yolov5_post_process(input_data)
print("classes:", classes)
print("landmarks::::", landmarks)
img_1 = cv2.cvtColor(img, cv2.COLOR_RGB2BGR)
if boxes is not None:
draw(img_1, boxes, scores, classes, landmarks)
#cv2.imshow("post process result", img_1)
cv2.imwrite("./result.jpg", img_1)
#cv2.waitKeyEx(0)
rknn.release()
|