Github 项目- 基于YOLOV3 和 DeepSort 的实时多人追踪
原文：Github 项目- 基于YOLOV3 和 DeepSort 的实时多人追踪 - AIUAI
作者: Qidian213
QQ group: 姿态检测＆跟踪 781184396
https://github.com/nwojke/deep_sort
https://github.com/qqwweee/keras-yolo3
https://github.com/Qidian213/deep_sort_yolov3
采用 TensorFlow Backend 的 Keras 框架,基于 YOLOV3 和 Deep_Sort 实现的实时多人追踪. 还可以用于人流统计.
该项目现支持 tiny_yolo v3, 但仅用于测试. 如果需要进行模型训练, 可以采用在 darknet 中进行, 或者等待该项目的后续支持.
该项目可以追踪多个目标, 目标类为 COCO 类别. 如果是其它类别,需要修改 yolo.py 中的类别.
该项目也可以在测试时调用相机.
1. 依赖项
项目代码兼容 Python2.7 和 Python3.
追踪器(tracker) 代码依赖项:
NumPy
sklean
OpenCV
特征生成(feature generation) 需要基于 TensorFlow1.4.0.
注:
多目标跟踪算法 DeepSort 的模型文件 model_data/mars-small128.pb 需要转换为 TensorFlow1.4.0.
2. 测试结果
速度: 只运行 yolo 检测, 速率大概为 11-13 fps, 添加 deep_sort 多目标追踪后, 速率大概为 11.5 fps (显卡 GTX1060.)
测试结果: https://www.bilibili.com/video/av23500163/
3. 多目标追踪示例
[1] - 从 YOLO website 下载 YOLOV3 或 tiny_yolov3 权重.
[2] - 将下载的 Darknet YOLO 模型转换为 Keras 模型, 并放到 model_data/ 路径.
项目里提供了转换后的 yolo.h5模型:
https://drive.google.com/file/d/1uvXFacPnrSMw6ldWTyLLjGLETlEsUvcE/view?usp=sharing
(基于 TF-1.4.0)
3.1. 模型转换
convert.py
用法:
# 首先下载 darknet yolov3 权重
python convert.py yolov3.cfg yolov3.weights model_data/yolo.h5
convert.py:
#! /usr/bin/env python
"""
Reads Darknet config and weights
and
creates Keras model with TF backend.
"""
import argparse
import configparser
import io
import os
from collections import defaultdict
import numpy as np
from keras import backend as K
from keras.layers import (Conv2D, Input, ZeroPadding2D, Add,
UpSampling2D, Concatenate)
from keras.layers.advanced_activations import LeakyReLU
from keras.layers.normalization import BatchNormalization
from keras.models import Model
from keras.regularizers import l2
from keras.utils.vis_utils import plot_model as plot
parser = argparse.ArgumentParser(description='Darknet To Keras Converter.')
parser.add_argument('config_path', help='Path to Darknet cfg file.')
parser.add_argument('weights_path', help='Path to Darknet weights file.')
parser.add_argument('output_path', help='Path to output Keras model file.')
parser.add_argument(
'-p',
'--plot_model',
help='Plot generated Keras model and save as image.',
action='store_true')
def unique_config_sections(config_file):
"""
Convert all config sections to have unique names.
Adds unique suffixes to config sections for compability with configparser.
"""
section_counters = defaultdict(int)
output_stream = io.BytesIO() #io.StringIO()
with open(config_file) as fin:
for line in fin:
if line.startswith('['):
section = line.strip().strip('[]')
_section = section + '_' + str(section_counters[section])
section_counters[section] += 1
line = line.replace(section, _section)
output_stream.write(line)
output_stream.seek(0)
return output_stream
# %%
def _main(args):
config_path = os.path.expanduser(args.config_path)
weights_path = os.path.expanduser(args.weights_path)
assert config_path.endswith('.cfg'), '{} is not a .cfg file'.format(
config_path)
assert weights_path.endswith(
'.weights'), '{} is not a .weights file'.format(weights_path)
output_path = os.path.expanduser(args.output_path)
assert output_path.endswith(
'.h5'), 'output path {} is not a .h5 file'.format(output_path)
output_root = os.path.splitext(output_path)[0]
# Load weights and config.
print('Loading weights.')
weights_file = open(weights_path, 'rb')
major, minor, revision = np.ndarray(shape=(3, ),
dtype='int32',
buffer=weights_file.read(12))
if (major*10+minor)>=2 and major<1000 and minor<1000:
seen = np.ndarray(shape=(1,),
dtype='int64',
buffer=weights_file.read(8))
else:
seen = np.ndarray(shape=(1,),
dtype='int32',
buffer=weights_file.read(4))
print('Weights Header: ', major, minor, revision, seen)
print('Parsing Darknet config.')
unique_config_file = unique_config_sections(config_path)
cfg_parser = configparser.ConfigParser()
cfg_parser.read_file(unique_config_file)
print('Creating Keras model.')
input_layer = Input(shape=(None, None, 3))
prev_layer = input_layer
all_layers = []
weight_decay = float(cfg_parser['net_0']['decay']
) if 'net_0' in cfg_parser.sections() else 5e-4
count = 0
out_index = []
for section in cfg_parser.sections():
print('Parsing section {}'.format(section))
if section.startswith('convolutional'):
filters = int(cfg_parser[section]['filters'])
size = int(cfg_parser[section]['size'])
stride = int(cfg_parser[section]['stride'])
pad = int(cfg_parser[section]['pad'])
activation = cfg_parser[section]['activation']
batch_normalize = 'batch_normalize' in cfg_parser[section]
padding = 'same' if pad == 1 and stride == 1 else 'valid'
# Setting weights.
# Darknet serializes convolutional weights as:
# [bias/beta, [gamma, mean, variance], conv_weights]
prev_layer_shape = K.int_shape(prev_layer)
weights_shape = (size, size, prev_layer_shape[-1], filters)
darknet_w_shape = (filters, weights_shape[2], size, size)
weights_size = np.product(weights_shape)
print('conv2d',
'bn' if batch_normalize else ' ',
activation,
weights_shape)
conv_bias = np.ndarray(
shape=(filters, ),
dtype='float32',
buffer=weights_file.read(filters * 4))
count += filters
if batch_normalize:
bn_weights = np.ndarray(
shape=(3, filters),
dtype='float32',
buffer=weights_file.read(filters * 12))
count += 3 * filters
bn_weight_list = [
bn_weights[0], # scale gamma
conv_bias, # shift beta
bn_weights[1], # running mean
bn_weights[2] # running var
]
conv_weights = np.ndarray(
shape=darknet_w_shape,
dtype='float32',
buffer=weights_file.read(weights_size * 4))
count += weights_size
# DarkNet conv_weights are serialized Caffe-style:
# (out_dim, in_dim, height, width)
# We would like to set these to Tensorflow order:
# (height, width, in_dim, out_dim)
conv_weights = np.transpose(conv_weights, [2, 3, 1, 0])
conv_weights = [conv_weights] if batch_normalize else [
conv_weights, conv_bias
]
# Handle activation.
act_fn = None
if activation == 'leaky':
pass # Add advanced activation later.
elif activation != 'linear':
raise ValueError(
'Unknown activation function `{}` in section {}'.format(
activation, section))
# Create Conv2D layer
if stride>1:
# Darknet uses left and top padding instead of 'same' mode
prev_layer = ZeroPadding2D(((1,0),(1,0)))(prev_layer)
conv_layer = (Conv2D(
filters, (size, size),
strides=(stride, stride),
kernel_regularizer=l2(weight_decay),
use_bias=not batch_normalize,
weights=conv_weights,
activation=act_fn,
padding=padding))(prev_layer)
if batch_normalize:
conv_layer = (BatchNormalization(
weights=bn_weight_list))(conv_layer)
prev_layer = conv_layer
if activation == 'linear':
all_layers.append(prev_layer)
elif activation == 'leaky':
act_layer = LeakyReLU(alpha=0.1)(prev_layer)
prev_layer = act_layer
all_layers.append(act_layer)
elif section.startswith('route'):
ids = [int(i) for i in cfg_parser[section]['layers'].split(',')]
layers = [all_layers[i] for i in ids]
if len(layers) > 1:
print('Concatenating route layers:', layers)
concatenate_layer = Concatenate()(layers)
all_layers.append(concatenate_layer)
prev_layer = concatenate_layer
else:
skip_layer = layers[0] # only one layer to route
all_layers.append(skip_layer)
prev_layer = skip_layer
elif section.startswith('shortcut'):
index = int(cfg_parser[section]['from'])
activation = cfg_parser[section]['activation']
assert activation == 'linear', 'Only linear activation supported.'
all_layers.append(Add()([all_layers[index], prev_layer]))
prev_layer = all_layers[-1]
elif section.startswith('upsample'):
stride = int(cfg_parser[section]['stride'])
assert stride == 2, 'Only stride=2 supported.'
all_layers.append(UpSampling2D(stride)(prev_layer))
prev_layer = all_layers[-1]
elif section.startswith('yolo'):
out_index.append(len(all_layers)-1)
all_layers.append(None)
prev_layer = all_layers[-1]
elif section.startswith('net'):
pass
else:
raise ValueError(
'Unsupported section header type: {}'.format(section))
# Create and save model.
model = Model(inputs=input_layer, outputs=[all_layers[i] for i in out_index])
print(model.summary())
model.save('{}'.format(output_path))
print('Saved Keras model to {}'.format(output_path))
# Check to see if all weights have been read.
remaining_weights = len(weights_file.read()) / 4
weights_file.close()
print('Read {} of {} from Darknet weights.'.format(count, count +
remaining_weights))
if remaining_weights > 0:
print('Warning: {} unused weights'.format(remaining_weights))
if args.plot_model:
plot(model, to_file='{}.png'.format(output_root), show_shapes=True)
print('Saved model plot to {}.png'.format(output_root))
if __name__ == '__main__':
_main(parser.parse_args())
3.2. 多人目标追踪Demo
demo.py
#! /usr/bin/env python
# -*- coding: utf-8 -*-
from __future__ import division, print_function, absolute_import
from timeit import time
import warnings
import cv2
import numpy as np
from PIL import Image
from yolo import YOLO
from deep_sort import preprocessing
from deep_sort import nn_matching
from deep_sort.detection import Detection
from deep_sort.tracker import Tracker
from tools import generate_detections as gdet
from deep_sort.detection import Detection as ddet
warnings.filterwarnings('ignore')
def main(yolo):
# 参数定义
max_cosine_distance = 0.3
nn_budget = None
nms_max_overlap = 1.0
# deep_sort 目标追踪算法
model_filename = 'model_data/mars-small128.pb'
encoder = gdet.create_box_encoder(model_filename,batch_size=1)
metric = nn_matching.NearestNeighborDistanceMetric(
"cosine", max_cosine_distance, nn_budget)
tracker = Tracker(metric)
writeVideo_flag = True
video_capture = cv2.VideoCapture(0)
if writeVideo_flag:
# Define the codec and create VideoWriter object
w = int(video_capture.get(3))
h = int(video_capture.get(4))
fourcc = cv2.VideoWriter_fourcc(*'MJPG')
out = cv2.VideoWriter('output.avi', fourcc, 15, (w, h))
list_file = open('detection.txt', 'w')
frame_index = -1
fps = 0.0
while True:
ret, frame = video_capture.read() # frame shape 640*480*3
if ret != True:
break;
t1 = time.time()
image = Image.fromarray(frame)
boxs = yolo.detect_image(image)
# print("box_num",len(boxs))
features = encoder(frame,boxs)
# score to 1.0 here).
detections = [Detection(bbox, 1.0, feature) for
bbox, feature in zip(boxs, features)]
# Run non-maxima suppression.
boxes = np.array([d.tlwh for d in detections])
scores = np.array([d.confidence for d in detections])
indices = preprocessing.non_max_suppression(boxes, nms_max_overlap, scores)
detections = [detections[i] for i in indices]
# Call the tracker
tracker.predict()
tracker.update(detections)
for track in tracker.tracks:
if not track.is_confirmed() or track.time_since_update > 1:
continue
bbox = track.to_tlbr()
cv2.rectangle(frame,
(int(bbox[0]), int(bbox[1])),
(int(bbox[2]), int(bbox[3])),
(255,255,255),
2)
cv2.putText(frame,
str(track.track_id),
(int(bbox[0]), int(bbox[1])),
0, 5e-3 * 200, (0,255,0),2)
for det in detections:
bbox = det.to_tlbr()
cv2.rectangle(frame,
(int(bbox[0]), int(bbox[1])),
(int(bbox[2]), int(bbox[3])),
(255,0,0),
2)
cv2.imshow('', frame)
if writeVideo_flag:
# save a frame
out.write(frame)
frame_index = frame_index + 1
list_file.write(str(frame_index)+' ')
if len(boxs) != 0:
for i in range(0,len(boxs)):
list_file.write(str(boxs[i][0]) + ' '+
str(boxs[i][1]) + ' '+
str(boxs[i][2]) + ' '+
str(boxs[i][3]) + ' ')
list_file.write('\n')
fps = ( fps + (1./(time.time()-t1)) ) / 2
print("fps= %f"%(fps))
# Press Q to stop!
if cv2.waitKey(1) & 0xFF == ord('q'):
break
video_capture.release()
if writeVideo_flag:
out.release()
list_file.close()
cv2.destroyAllWindows()
if __name__ == '__main__':
main(YOLO())
3.3. 多人目标检测Demo
#! /usr/bin/env python
# -*- coding: utf-8 -*-
from __future__ import division, print_function, absolute_import
import os
from timeit import time
import warnings
import sys
import cv2
import numpy as np
from PIL import Image
import matplotlib.pyplot as plt
from yolo import YOLO
from deep_sort import preprocessing
from deep_sort.detection import Detection
from tools import generate_detections as gdet
warnings.filterwarnings('ignore')
def main(yolo):
nms_max_overlap = 1.0
# deep_sort
model_filename = 'model_data/mars-small128.pb'
encoder = gdet.create_box_encoder(model_filename, batch_size=1)
imgs_dir = "/path/to/test/"
imgs_list = os.listdir(imgs_dir)[20:]
imgs_file = [os.path.join(imgs_dir, tmp) for tmp in imgs_list]
for idx in range(len(imgs_file)):
frame = np.array(Image.open(imgs_file[idx]))
image = Image.fromarray(frame)
boxs = yolo.detect_image(image)
# print("box_num",len(boxs))
features = encoder(frame, boxs)
# score to 1.0 here).
detections = [Detection(bbox, 1.0, feature)
for bbox, feature in zip(boxs, features)]
# Run non-maxima suppression.
boxes = np.array([d.tlwh for d in detections])
scores = np.array([d.confidence for d in detections])
indices = preprocessing.non_max_suppression(
boxes, nms_max_overlap, scores)
detections = [detections[i] for i in indices]
for det in detections:
bbox = det.to_tlbr()
cv2.rectangle(frame,
(int(bbox[0]), int(bbox[1])),
(int(bbox[2]), int(bbox[3])),
(255, 0, 0), 2)
plt.imshow(frame)
plt.show()
if __name__ == '__main__':
main(YOLO())
如:
4. YOLOV3 检测模型
4.1. yolo3/model.py
yolo3/model.py
"""YOLO_v3 Model Defined in Keras."""
from functools import wraps
import numpy as np
import tensorflow as tf
from keras import backend as K
from keras.layers import Conv2D, Add, ZeroPadding2D, UpSampling2D, Concatenate
from keras.layers.advanced_activations import LeakyReLU
from keras.layers.normalization import BatchNormalization
from keras.models import Model
from keras.regularizers import l2
from yolo3.utils import compose
@wraps(Conv2D)
def DarknetConv2D(*args, **kwargs):
"""
Wrapper to set Darknet parameters for Convolution2D.
"""
darknet_conv_kwargs = {'kernel_regularizer': l2(5e-4)}
darknet_conv_kwargs['padding'] = 'valid' if kwargs.get('strides')==(2,2) else 'same'
darknet_conv_kwargs.update(kwargs)
return Conv2D(*args, **darknet_conv_kwargs)
def DarknetConv2D_BN_Leaky(*args, **kwargs):
"""
Darknet Convolution2D followed by BatchNormalization and LeakyReLU.
"""
no_bias_kwargs = {'use_bias': False}
no_bias_kwargs.update(kwargs)
return compose(
DarknetConv2D(*args, **no_bias_kwargs),
BatchNormalization(),
LeakyReLU(alpha=0.1))
def resblock_body(x, num_filters, num_blocks):
'''
A series of resblocks starting with a downsampling Convolution2D
'''
# Darknet uses left and top padding instead of 'same' mode
x = ZeroPadding2D(((1,0),(1,0)))(x)
x = DarknetConv2D_BN_Leaky(num_filters, (3,3), strides=(2,2))(x)
for i in range(num_blocks):
y = compose(
DarknetConv2D_BN_Leaky(num_filters//2, (1,1)),
DarknetConv2D_BN_Leaky(num_filters, (3,3)))(x)
x = Add()([x,y])
return x
def darknet_body(x):
'''
Darknent body having 52 Convolution2D layers
'''
x = DarknetConv2D_BN_Leaky(32, (3,3))(x)
x = resblock_body(x, 64, 1)
x = resblock_body(x, 128, 2)
x = resblock_body(x, 256, 8)
x = resblock_body(x, 512, 8)
x = resblock_body(x, 1024, 4)
return x
def make_last_layers(x, num_filters, out_filters):
'''
6 Conv2D_BN_Leaky layers followed by a Conv2D_linear layer
'''
x = compose(
DarknetConv2D_BN_Leaky(num_filters, (1,1)),
DarknetConv2D_BN_Leaky(num_filters*2, (3,3)),
DarknetConv2D_BN_Leaky(num_filters, (1,1)),
DarknetConv2D_BN_Leaky(num_filters*2, (3,3)),
DarknetConv2D_BN_Leaky(num_filters, (1,1)))(x)
y = compose(
DarknetConv2D_BN_Leaky(num_filters*2, (3,3)),
DarknetConv2D(out_filters, (1,1)))(x)
return x, y
def yolo_body(inputs, num_anchors, num_classes):
"""
Create YOLO_V3 model CNN body in Keras.
"""
darknet = Model(inputs, darknet_body(inputs))
x, y1 = make_last_layers(darknet.output,
512,
num_anchors*(num_classes+5))
x = compose(DarknetConv2D_BN_Leaky(256, (1,1)),
UpSampling2D(2))(x)
x = Concatenate()([x,darknet.layers[152].output])
x, y2 = make_last_layers(x, 256, num_anchors*(num_classes+5))
x = compose(DarknetConv2D_BN_Leaky(128, (1,1)),
UpSampling2D(2))(x)
x = Concatenate()([x,darknet.layers[92].output])
x, y3 = make_last_layers(x, 128, num_anchors*(num_classes+5))
return Model(inputs, [y1,y2,y3])
def yolo_head(feats, anchors, num_classes, input_shape):
"""
Convert final layer features to bounding box parameters.
"""
num_anchors = len(anchors)
# Reshape to batch, height, width, num_anchors, box_params.
anchors_tensor = K.reshape(K.constant(anchors), [1, 1, 1, num_anchors, 2])
grid_shape = K.shape(feats)[1:3] # height, width
grid_y = K.tile(
K.reshape(K.arange(0, stop=grid_shape[0]), [-1, 1, 1, 1]),
[1, grid_shape[1], 1, 1])
grid_x = K.tile(
K.reshape(K.arange(0, stop=grid_shape[1]), [1, -1, 1, 1]),
[grid_shape[0], 1, 1, 1])
grid = K.concatenate([grid_x, grid_y])
grid = K.cast(grid, K.dtype(feats))
feats = K.reshape(feats,
[-1,
grid_shape[0],
grid_shape[1],
num_anchors,
num_classes + 5])
box_xy = K.sigmoid(feats[..., :2])
box_wh = K.exp(feats[..., 2:4])
box_confidence = K.sigmoid(feats[..., 4:5])
box_class_probs = K.sigmoid(feats[..., 5:])
# Adjust preditions to each spatial grid point and anchor size.
box_xy = (box_xy + grid) / K.cast(grid_shape[::-1], K.dtype(feats))
box_wh = box_wh * anchors_tensor / K.cast(input_shape[::-1], K.dtype(feats))
return box_xy, box_wh, box_confidence, box_class_probs
def yolo_correct_boxes(box_xy, box_wh, input_shape, image_shape):
'''
Get corrected boxes
'''
box_yx = box_xy[..., ::-1]
box_hw = box_wh[..., ::-1]
input_shape = K.cast(input_shape, K.dtype(box_yx))
image_shape = K.cast(image_shape, K.dtype(box_yx))
new_shape = K.round(image_shape * K.min(input_shape/image_shape))
offset = (input_shape-new_shape)/2./input_shape
scale = input_shape/new_shape
box_yx = (box_yx - offset) * scale
box_hw *= scale
box_mins = box_yx - (box_hw / 2.)
box_maxes = box_yx + (box_hw / 2.)
boxes = K.concatenate([
box_mins[..., 0:1], # y_min
box_mins[..., 1:2], # x_min
box_maxes[..., 0:1], # y_max
box_maxes[..., 1:2] # x_max
])
# Scale boxes back to original image shape.
boxes *= K.concatenate([image_shape, image_shape])
return boxes
def yolo_boxes_and_scores(feats, anchors, num_classes, input_shape, image_shape):
'''
Process Conv layer output
'''
box_xy, box_wh, box_confidence, box_class_probs = yolo_head(feats,
anchors, num_classes, input_shape)
boxes = yolo_correct_boxes(box_xy, box_wh, input_shape, image_shape)
boxes = K.reshape(boxes, [-1, 4])
box_scores = box_confidence * box_class_probs
box_scores = K.reshape(box_scores, [-1, num_classes])
return boxes, box_scores
def yolo_eval(yolo_outputs,
anchors,
num_classes,
image_shape,
max_boxes=20,
score_threshold=.6,
iou_threshold=.5):
"""
Evaluate YOLO model on given input and return filtered boxes.
"""
anchor_mask = [[6,7,8], [3,4,5], [0,1,2]]
input_shape = K.shape(yolo_outputs[0])[1:3] * 32
boxes = []
box_scores = []
for l in range(3):
_boxes, _box_scores = yolo_boxes_and_scores(yolo_outputs[l],
anchors[anchor_mask[l]], num_classes, input_shape, image_shape)
boxes.append(_boxes)
box_scores.append(_box_scores)
boxes = K.concatenate(boxes, axis=0)
box_scores = K.concatenate(box_scores, axis=0)
mask = box_scores >= score_threshold
max_boxes_tensor = K.constant(max_boxes, dtype='int32')
boxes_ = []
scores_ = []
classes_ = []
for c in range(num_classes):
# TODO: use keras backend instead of tf.
class_boxes = tf.boolean_mask(boxes, mask[:, c])
class_box_scores = tf.boolean_mask(box_scores[:, c], mask[:, c])
nms_index = tf.image.non_max_suppression(
class_boxes,
class_box_scores,
max_boxes_tensor,
iou_threshold=iou_threshold)
class_boxes = K.gather(class_boxes, nms_index)
class_box_scores = K.gather(class_box_scores, nms_index)
classes = K.ones_like(class_box_scores, 'int32') * c
boxes_.append(class_boxes)
scores_.append(class_box_scores)
classes_.append(classes)
boxes_ = K.concatenate(boxes_, axis=0)
scores_ = K.concatenate(scores_, axis=0)
classes_ = K.concatenate(classes_, axis=0)
return boxes_, scores_, classes_
def preprocess_true_boxes(true_boxes, input_shape, anchors, num_classes):
'''
Preprocess true boxes to training input format
Parameters
----------
true_boxes: array, shape=(m, T, 5)
Absolute x_min, y_min, x_max, y_max, class_code reletive to input_shape.
input_shape: array-like, hw, multiples of 32
anchors: array, shape=(N, 2), wh
num_classes: integer
Returns
-------
y_true: list of array, shape like yolo_outputs, xywh are reletive value
'''
anchor_mask = [[6,7,8], [3,4,5], [0,1,2]]
true_boxes = np.array(true_boxes, dtype='float32')
input_shape = np.array(input_shape, dtype='int32')
boxes_xy = (true_boxes[..., 0:2] + true_boxes[..., 2:4]) // 2
boxes_wh = true_boxes[..., 2:4] - true_boxes[..., 0:2]
true_boxes[..., 0:2] = boxes_xy/input_shape[::-1]
true_boxes[..., 2:4] = boxes_wh/input_shape[::-1]
m = true_boxes.shape[0]
grid_shapes = [input_shape//{0:32, 1:16, 2:8}[l] for l in range(3)]
y_true = [
np.zeros((m,
grid_shapes[l][0],
grid_shapes[l][1],
len(anchor_mask[l]),
5+num_classes),
dtype='float32') for l in range(3)]
# Expand dim to apply broadcasting.
anchors = np.expand_dims(anchors, 0)
anchor_maxes = anchors / 2.
anchor_mins = -anchor_maxes
valid_mask = boxes_wh[..., 0]>0
for b in range(m):
# Discard zero rows.
wh = boxes_wh[b, valid_mask[b]]
# Expand dim to apply broadcasting.
wh = np.expand_dims(wh, -2)
box_maxes = wh / 2.
box_mins = -box_maxes
intersect_mins = np.maximum(box_mins, anchor_mins)
intersect_maxes = np.minimum(box_maxes, anchor_maxes)
intersect_wh = np.maximum(intersect_maxes - intersect_mins, 0.)
intersect_area = intersect_wh[..., 0] * intersect_wh[..., 1]
box_area = wh[..., 0] * wh[..., 1]
anchor_area = anchors[..., 0] * anchors[..., 1]
iou = intersect_area / (box_area + anchor_area - intersect_area)
# Find best anchor for each true box
best_anchor = np.argmax(iou, axis=-1)
for t, n in enumerate(best_anchor):
for l in range(3):
if n in anchor_mask[l]:
i = np.floor(true_boxes[b,t,0]*grid_shapes[l][1]).astype('int32')
j = np.floor(true_boxes[b,t,1]*grid_shapes[l][0]).astype('int32')
n = anchor_mask[l].index(n)
c = true_boxes[b,t, 4].astype('int32')
y_true[l][b, j, i, n, 0:4] = true_boxes[b,t, 0:4]
y_true[l][b, j, i, n, 4] = 1
y_true[l][b, j, i, n, 5+c] = 1
break
return y_true
def box_iou(b1, b2):
'''
Return iou tensor
Parameters
----------
b1: tensor, shape=(i1,...,iN, 4), xywh
b2: tensor, shape=(j, 4), xywh
Returns
-------
iou: tensor, shape=(i1,...,iN, j)
'''
# Expand dim to apply broadcasting.
b1 = K.expand_dims(b1, -2)
b1_xy = b1[..., :2]
b1_wh = b1[..., 2:4]
b1_wh_half = b1_wh/2.
b1_mins = b1_xy - b1_wh_half
b1_maxes = b1_xy + b1_wh_half
# Expand dim to apply broadcasting.
b2 = K.expand_dims(b2, 0)
b2_xy = b2[..., :2]
b2_wh = b2[..., 2:4]
b2_wh_half = b2_wh/2.
b2_mins = b2_xy - b2_wh_half
b2_maxes = b2_xy + b2_wh_half
intersect_mins = K.maximum(b1_mins, b2_mins)
intersect_maxes = K.minimum(b1_maxes, b2_maxes)
intersect_wh = K.maximum(intersect_maxes - intersect_mins, 0.)
intersect_area = intersect_wh[..., 0] * intersect_wh[..., 1]
b1_area = b1_wh[..., 0] * b1_wh[..., 1]
b2_area = b2_wh[..., 0] * b2_wh[..., 1]
iou = intersect_area / (b1_area + b2_area - intersect_area)
return iou
def yolo_loss(args, anchors, num_classes, ignore_thresh=.5):
'''
Return yolo_loss tensor
Parameters
----------
yolo_outputs: list of tensor, the output of yolo_body
y_true: list of array, the output of preprocess_true_boxes
anchors: array, shape=(T, 2), wh
num_classes: integer
ignore_thresh: float, the iou threshold whether to ignore object confidence loss
Returns
-------
loss: tensor, shape=(1,)
'''
yolo_outputs = args[:3]
y_true = args[3:]
anchor_mask = [[6,7,8], [3,4,5], [0,1,2]]
input_shape = K.cast(K.shape(yolo_outputs[0])[1:3] * 32, K.dtype(y_true[0]))
grid_shapes = [K.cast(K.shape(yolo_outputs[l])[1:3], K.dtype(y_true[0])) for l in range(3)]
loss = 0
m = K.shape(yolo_outputs[0])[0]
for l in range(3):
object_mask = y_true[l][..., 4:5]
true_class_probs = y_true[l][..., 5:]
pred_xy, pred_wh, pred_confidence, pred_class_probs = yolo_head(
yolo_outputs[l],
anchors[anchor_mask[l]],
num_classes,
input_shape)
pred_box = K.concatenate([pred_xy, pred_wh])
# Darknet box loss.
xy_delta = (y_true[l][..., :2]-pred_xy)*grid_shapes[l][::-1]
wh_delta = K.log(y_true[l][..., 2:4]) - K.log(pred_wh)
# Avoid log(0)=-inf.
wh_delta = K.switch(object_mask, wh_delta, K.zeros_like(wh_delta))
box_delta = K.concatenate([xy_delta, wh_delta], axis=-1)
box_delta_scale = 2 - y_true[l][...,2:3]*y_true[l][...,3:4]
# Find ignore mask, iterate over each of batch.
ignore_mask = tf.TensorArray(K.dtype(y_true[0]), size=1, dynamic_size=True)
object_mask_bool = K.cast(object_mask, 'bool')
def loop_body(b, ignore_mask):
true_box = tf.boolean_mask(y_true[l][b,...,0:4], object_mask_bool[b,...,0])
iou = box_iou(pred_box[b], true_box)
best_iou = K.max(iou, axis=-1)
ignore_mask = ignore_mask.write(b, K.cast(best_iou<ignore_thresh, K.dtype(true_box)))
return b+1, ignore_mask
_, ignore_mask = K.control_flow_ops.while_loop(lambda b,*args: b<m, loop_body, [0, ignore_mask])
ignore_mask = ignore_mask.stack()
ignore_mask = K.expand_dims(ignore_mask, -1)
box_loss = object_mask * K.square(box_delta*box_delta_scale)
confidence_loss = object_mask * K.square(1-pred_confidence) + \
(1-object_mask) * K.square(0-pred_confidence) * ignore_mask
class_loss = object_mask * K.square(true_class_probs-pred_class_probs)
loss += K.sum(box_loss) + K.sum(confidence_loss) + K.sum(class_loss)
return loss / K.cast(m, K.dtype(loss))
4.2. yolov3/utils.py
yolov3/utils.py
"""Miscellaneous utility functions."""
from functools import reduce
from PIL import Image
def compose(*funcs):
"""
Compose arbitrarily many functions, evaluated left to right.
Reference: https://mathieularose.com/function-composition-in-python/
"""
# return lambda x: reduce(lambda v, f: f(v), funcs, x)
if funcs:
return reduce(lambda f, g: lambda *a, **kw: g(f(*a, **kw)), funcs)
else:
raise ValueError('Composition of empty sequence not supported.')
def letterbox_image(image, size):
'''
resize image with unchanged aspect ratio using padding
'''
image_w, image_h = image.size
w, h = size
new_w = int(image_w * min(w*1.0/image_w, h*1.0/image_h))
new_h = int(image_h * min(w*1.0/image_w, h*1.0/image_h))
resized_image = image.resize((new_w,new_h), Image.BICUBIC)
boxed_image = Image.new('RGB', size, (128,128,128))
boxed_image.paste(resized_image, ((w-new_w)//2,(h-new_h)//2))
return boxed_image
4.3. yolo.py
yolo.py
#! /usr/bin/env python
# -*- coding: utf-8 -*-
"""
Run a YOLO_v3 style detection model on test images.
"""
import colorsys
import os
import random
import numpy as np
from keras import backend as K
from keras.models import load_model
from yolo3.model import yolo_eval
from yolo3.utils import letterbox_image
class YOLO(object):
def __init__(self):
self.model_path = 'model_data/yolo.h5'
self.anchors_path = 'model_data/yolo_anchors.txt'
self.classes_path = 'model_data/coco_classes.txt'
self.score = 0.5
self.iou = 0.5
self.class_names = self._get_class()
self.anchors = self._get_anchors()
self.sess = K.get_session()
self.model_image_size = (416, 416) # fixed size or (None, None)
self.is_fixed_size = self.model_image_size != (None, None)
self.boxes, self.scores, self.classes = self.generate()
def _get_class(self):
classes_path = os.path.expanduser(self.classes_path)
with open(classes_path) as f:
class_names = f.readlines()
class_names = [c.strip() for c in class_names]
return class_names
def _get_anchors(self):
anchors_path = os.path.expanduser(self.anchors_path)
with open(anchors_path) as f:
anchors = f.readline()
anchors = [float(x) for x in anchors.split(',')]
anchors = np.array(anchors).reshape(-1, 2)
return anchors
def generate(self):
model_path = os.path.expanduser(self.model_path)
assert model_path.endswith('.h5'), 'Keras model must be a .h5 file.'
self.yolo_model = load_model(model_path, compile=False)
print('{} model, anchors, and classes loaded.'.format(model_path))
# Generate colors for drawing bounding boxes.
hsv_tuples = [(x / len(self.class_names), 1., 1.)
for x in range(len(self.class_names))]
self.colors = list(map(lambda x: colorsys.hsv_to_rgb(*x), hsv_tuples))
self.colors = list(
map(lambda x: (int(x[0] * 255), int(x[1] * 255), int(x[2] * 255)),
self.colors))
random.seed(10101) # Fixed seed for consistent colors across runs.
random.shuffle(self.colors) # Shuffle colors to decorrelate adjacent classes.
random.seed(None) # Reset seed to default.
# Generate output tensor targets for filtered bounding boxes.
self.input_image_shape = K.placeholder(shape=(2, ))
boxes, scores, classes = yolo_eval(self.yolo_model.output, self.anchors,
len(self.class_names), self.input_image_shape,
score_threshold=self.score, iou_threshold=self.iou)
return boxes, scores, classes
def detect_image(self, image):
if self.is_fixed_size:
assert self.model_image_size[0]%32 == 0, 'Multiples of 32 required'
assert self.model_image_size[1]%32 == 0, 'Multiples of 32 required'
boxed_image = letterbox_image(
image,
tuple(reversed(self.model_image_size)))
else:
new_image_size = (image.width - (image.width % 32),
image.height - (image.height % 32))
boxed_image = letterbox_image(image, new_image_size)
image_data = np.array(boxed_image, dtype='float32')
#print(image_data.shape)
image_data /= 255.
image_data = np.expand_dims(image_data, 0) # Add batch dimension.
out_boxes, out_scores, out_classes = self.sess.run(
[self.boxes, self.scores, self.classes],
feed_dict={
self.yolo_model.input: image_data,
self.input_image_shape: [image.size[1], image.size[0]],
K.learning_phase(): 0
})
return_boxs = []
for i, c in reversed(list(enumerate(out_classes))):
predicted_class = self.class_names[c]
if predicted_class != 'person' :
continue
box = out_boxes[i]
# score = out_scores[i]
x = int(box[1])
y = int(box[0])
w = int(box[3]-box[1])
h = int(box[2]-box[0])
if x < 0 :
w = w + x
x = 0
if y < 0 :
h = h + y
y = 0
return_boxs.append([x,y,w,h])
return return_boxs
def close_session(self):
self.sess.close()