File size: 7,425 Bytes
477da44 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 |
import numpy as np
import re
import math
import random
import cv2
from rknn.api import RKNN
INPUT_SIZE = 300
NUM_RESULTS = 1917
NUM_CLASSES = 91
Y_SCALE = 10.0
X_SCALE = 10.0
H_SCALE = 5.0
W_SCALE = 5.0
CLASSES = ('__background__', 'person', 'bicycle', 'car', 'motorcycle', 'airplane', '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', 'couch', 'potted plant', 'bed', '???', 'dining table', '???', '???', 'toilet',
'???', 'tv', 'laptop', 'mouse', 'remote', 'keyboard', 'cell phone', 'microwave', 'oven', 'toaster', 'sink',
'refrigerator', '???', 'book', 'clock', 'vase', 'scissors', 'teddy bear', 'hair drier', 'toothbrush')
def expit(x):
return 1. / (1. + math.exp(-x))
def unexpit(y):
return -1.0 * math.log((1.0 / y) - 1.0)
def CalculateOverlap(xmin0, ymin0, xmax0, ymax0, xmin1, ymin1, xmax1, ymax1):
w = max(0.0, min(xmax0, xmax1) - max(xmin0, xmin1))
h = max(0.0, min(ymax0, ymax1) - max(ymin0, ymin1))
i = w * h
u = (xmax0 - xmin0) * (ymax0 - ymin0) + (xmax1 - xmin1) * (ymax1 - ymin1) - i
if u <= 0.0:
return 0.0
return i / u
def load_box_priors():
box_priors_ = []
fp = open('./box_priors.txt', 'r')
ls = fp.readlines()
for s in ls:
aList = re.findall('([-+]?\d+(\.\d*)?|\.\d+)([eE][-+]?\d+)?', s)
for ss in aList:
aNum = float((ss[0]+ss[2]))
box_priors_.append(aNum)
fp.close()
box_priors = np.array(box_priors_)
box_priors = box_priors.reshape(4, NUM_RESULTS)
return box_priors
if __name__ == '__main__':
# Create RKNN object
rknn = RKNN(verbose=True)
# Pre-process config
print('--> Config model')
rknn.config(mean_values=[127.5, 127.5, 127.5], std_values=[127.5, 127.5, 127.5], target_platform='rk3566')
print('done')
# Load model (from https://github.com/fvmassoli/Deep-Learning-SSD-Object-Detection)
print('--> Loading model')
ret = rknn.load_tensorflow(tf_pb='./ssd_mobilenet_v1_coco_2017_11_17.pb',
inputs=['Preprocessor/sub'],
outputs=['concat', 'concat_1'],
input_size_list=[[1, INPUT_SIZE, INPUT_SIZE, 3]])
if ret != 0:
print('Load model failed!')
exit(ret)
print('done')
# Build Model
print('--> Building model')
ret = rknn.build(do_quantization=True, dataset='./dataset.txt')
if ret != 0:
print('Build model failed!')
exit(ret)
print('done')
# Export rknn model
print('--> Export rknn model')
ret = rknn.export_rknn('./ssd_mobilenet_v1_coco.rknn')
if ret != 0:
print('Export rknn model failed!')
exit(ret)
print('done')
# Set inputs
orig_img = cv2.imread('./road.bmp')
img = cv2.cvtColor(orig_img, cv2.COLOR_BGR2RGB)
img = cv2.resize(img, (INPUT_SIZE, INPUT_SIZE), interpolation=cv2.INTER_CUBIC)
img = np.expand_dims(img, 0)
# Init runtime environment
print('--> Init runtime environment')
ret = rknn.init_runtime()
if ret != 0:
print('Init runtime environment failed!')
exit(ret)
print('done')
# Inference
print('--> Running model')
outputs = rknn.inference(inputs=[img], data_format=['nhwc'])
print('done')
predictions = outputs[0].reshape((1, NUM_RESULTS, 4))
np.save('./tensorflow_ssd_mobilenet_v1_0.npy', outputs[0])
outputClasses = outputs[1].reshape((1, NUM_RESULTS, NUM_CLASSES))
np.save('./tensorflow_ssd_mobilenet_v1_1.npy', outputs[0])
candidateBox = np.zeros([2, NUM_RESULTS], dtype=int)
classScore = [-1000.0] * NUM_RESULTS
vaildCnt = 0
box_priors = load_box_priors()
# Post Process
# got valid candidate box
for i in range(0, NUM_RESULTS):
topClassScore = -1000
topClassScoreIndex = -1
# Skip the first catch-all class.
for j in range(1, NUM_CLASSES):
score = expit(outputClasses[0][i][j])
if score > topClassScore:
topClassScoreIndex = j
topClassScore = score
if topClassScore > 0.4:
candidateBox[0][vaildCnt] = i
candidateBox[1][vaildCnt] = topClassScoreIndex
classScore[vaildCnt] = topClassScore
vaildCnt += 1
# calc position
for i in range(0, vaildCnt):
if candidateBox[0][i] == -1:
continue
n = candidateBox[0][i]
ycenter = predictions[0][n][0] / Y_SCALE * box_priors[2][n] + box_priors[0][n]
xcenter = predictions[0][n][1] / X_SCALE * box_priors[3][n] + box_priors[1][n]
h = math.exp(predictions[0][n][2] / H_SCALE) * box_priors[2][n]
w = math.exp(predictions[0][n][3] / W_SCALE) * box_priors[3][n]
ymin = ycenter - h / 2.
xmin = xcenter - w / 2.
ymax = ycenter + h / 2.
xmax = xcenter + w / 2.
predictions[0][n][0] = ymin
predictions[0][n][1] = xmin
predictions[0][n][2] = ymax
predictions[0][n][3] = xmax
# NMS
for i in range(0, vaildCnt):
if candidateBox[0][i] == -1:
continue
n = candidateBox[0][i]
xmin0 = predictions[0][n][1]
ymin0 = predictions[0][n][0]
xmax0 = predictions[0][n][3]
ymax0 = predictions[0][n][2]
for j in range(i+1, vaildCnt):
m = candidateBox[0][j]
if m == -1:
continue
xmin1 = predictions[0][m][1]
ymin1 = predictions[0][m][0]
xmax1 = predictions[0][m][3]
ymax1 = predictions[0][m][2]
iou = CalculateOverlap(xmin0, ymin0, xmax0, ymax0, xmin1, ymin1, xmax1, ymax1)
if iou >= 0.45:
candidateBox[0][j] = -1
# Draw result
if vaildCnt != 0:
print("{:^12} {:^12} {}".format('class', 'score', 'xmin, ymin, xmax, ymax'))
print('-' * 50)
for i in range(0, vaildCnt):
if candidateBox[0][i] == -1:
continue
n = candidateBox[0][i]
xmin = max(0.0, min(1.0, predictions[0][n][1])) * INPUT_SIZE
ymin = max(0.0, min(1.0, predictions[0][n][0])) * INPUT_SIZE
xmax = max(0.0, min(1.0, predictions[0][n][3])) * INPUT_SIZE
ymax = max(0.0, min(1.0, predictions[0][n][2])) * INPUT_SIZE
print("{:^12} {:^12.3f} [{:>4}, {:>4}, {:>4}, {:>4}]".format(CLASSES[candidateBox[1][i]], classScore[i],
int(xmin), int(ymin), int(xmax), int(ymax)))
cv2.rectangle(orig_img, (int(xmin), int(ymin)), (int(xmax), int(ymax)),
(random.random()*255, random.random()*255, random.random()*255), 3)
cv2.imwrite("result.jpg", orig_img)
print('Save results to result.jpg!')
rknn.release()
|