|
|
import numpy as np |
|
|
import cv2 |
|
|
import os |
|
|
import urllib.request |
|
|
|
|
|
NUM_CLS = 80 |
|
|
MAX_BOXES = 500 |
|
|
OBJ_THRESH = 0.5 |
|
|
NMS_THRESH = 0.6 |
|
|
|
|
|
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 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]) |
|
|
box_wh = np.exp(input[..., 2:4]) |
|
|
box_wh = box_wh * anchors |
|
|
|
|
|
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 /= (grid_w, grid_h) |
|
|
box_wh /= (416, 416) |
|
|
box_xy -= (box_wh / 2.) |
|
|
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 object threshold. |
|
|
|
|
|
# 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_scores, axis=-1) |
|
|
box_class_scores = np.max(box_scores, axis=-1) |
|
|
pos = np.where(box_class_scores >= OBJ_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] |
|
|
h = boxes[:, 3] |
|
|
|
|
|
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 yolov3_post_process(input_data): |
|
|
|
|
|
masks = [[6, 7, 8], [3, 4, 5], [0, 1, 2]] |
|
|
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) |
|
|
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 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. |
|
|
""" |
|
|
print("{:^12} {:^12} {}".format('class', 'score', 'xmin, ymin, xmax, ymax')) |
|
|
print('-' * 50) |
|
|
for box, score, cl in zip(boxes, scores, classes): |
|
|
x, y, w, h = box |
|
|
x *= image.shape[1] |
|
|
y *= image.shape[0] |
|
|
w *= image.shape[1] |
|
|
h *= image.shape[0] |
|
|
top = max(0, np.floor(x + 0.5).astype(int)) |
|
|
left = max(0, np.floor(y + 0.5).astype(int)) |
|
|
right = min(image.shape[1], np.floor(x + w + 0.5).astype(int)) |
|
|
bottom = min(image.shape[0], np.floor(y + h + 0.5).astype(int)) |
|
|
|
|
|
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) |
|
|
|
|
|
print("{:^12} {:^12.3f} [{:>4}, {:>4}, {:>4}, {:>4}]".format(CLASSES[cl], score, top, left, right, bottom)) |
|
|
|
|
|
def download_yolov3_weight(dst_path): |
|
|
if os.path.exists(dst_path): |
|
|
print('yolov3.weight exist.') |
|
|
return |
|
|
print('Downloading yolov3.weights...') |
|
|
url = 'https://pjreddie.com/media/files/yolov3.weights' |
|
|
try: |
|
|
urllib.request.urlretrieve(url, dst_path) |
|
|
except urllib.error.HTTPError as e: |
|
|
print('HTTPError code: ', e.code) |
|
|
print('HTTPError reason: ', e.reason) |
|
|
exit(-1) |
|
|
except urllib.error.URLError as e: |
|
|
print('URLError reason: ', e.reason) |
|
|
else: |
|
|
print('Download yolov3.weight success.') |
|
|
|
