Skip to content

Y
yolov4-pytorch

菜瓜爱吃瓜 / yolov4-pytorch
与 Fork 源项目一致

从无法访问的项目Fork

通知 2
Star 1
Fork 0
Y
yolov4-pytorch

前往新版Gitcode，体验更适合开发者的 AI 搜索 >>

未验证 提交 34d2e3e1 编写于 作者: B Bubbliiiing 提交者： GitHub
浏览文件
操作

Add files via upload

上级 52358268
展开全部 隐藏空白更改
内联 并排
Showing with 2650 addition and 2331 deletion
get_map.py
浏览文件 @ 34d2e3e1
此差异已折叠。
kmeans_for_anchors.py
浏览文件 @ 34d2e3e1
......@@ -24,32 +24,45 @@ def avg_iou(box,cluster):
return np.mean([np.max(cas_iou(box[i],cluster)) for i in range(box.shape[0])])
def kmeans(box,k):
# 取出一共有多少框
#-------------------------------------------------------------#
# 取出一共有多少框
#-------------------------------------------------------------#
row = box.shape[0]
# 每个框各个点的位置
#-------------------------------------------------------------#
# 每个框各个点的位置
#-------------------------------------------------------------#
distance = np.empty((row,k))
# 最后的聚类位置
#-------------------------------------------------------------#
# 最后的聚类位置
#-------------------------------------------------------------#
last_clu = np.zeros((row,))
np.random.seed()
# 随机选5个当聚类中心
#-------------------------------------------------------------#
# 随机选5个当聚类中心
#-------------------------------------------------------------#
cluster = box[np.random.choice(row,k,replace = False)]
# cluster = random.sample(row, k)
while True:
# 计算每一行距离五个点的iou情况。
#-------------------------------------------------------------#
# 计算每一行距离五个点的iou情况。
#-------------------------------------------------------------#
for i in range(row):
distance[i] = 1 - cas_iou(box[i],cluster)
# 取出最小点
#-------------------------------------------------------------#
# 取出最小点
#-------------------------------------------------------------#
near = np.argmin(distance,axis=1)
if (last_clu == near).all():
break
# 求每一个类的中位点
#-------------------------------------------------------------#
# 求每一个类的中位点
#-------------------------------------------------------------#
for j in range(k):
cluster[j] = np.median(
box[near == j],axis=0)
......@@ -60,7 +73,9 @@ def kmeans(box,k):
def load_data(path):
data = []
# 对于每一个xml都寻找box
#-------------------------------------------------------------#
# 对于每一个xml都寻找box
#-------------------------------------------------------------#
for xml_file in glob.glob('{}/*xml'.format(path)):
tree = ET.parse(xml_file)
height = int(tree.findtext('./size/height'))
......@@ -68,7 +83,9 @@ def load_data(path):
if height<=0 or width<=0:
continue
# 对于每一个目标都获得它的宽高
#-------------------------------------------------------------#
# 对于每一个目标都获得它的宽高
#-------------------------------------------------------------#
for obj in tree.iter('object'):
xmin = int(float(obj.findtext('bndbox/xmin'))) / width
ymin = int(float(obj.findtext('bndbox/ymin'))) / height
......@@ -85,18 +102,26 @@ def load_data(path):
if __name__ == '__main__':
# 运行该程序会计算'./VOCdevkit/VOC2007/Annotations'的xml
# 会生成yolo_anchors.txt
SIZE = 416
#-------------------------------------------------------------#
# 运行该程序会计算'./VOCdevkit/VOC2007/Annotations'的xml
# 会生成yolo_anchors.txt
#-------------------------------------------------------------#
SIZE = 416
anchors_num = 9
# 载入数据集，可以使用VOC的xml
path = r'./VOCdevkit/VOC2007/Annotations'
#-------------------------------------------------------------#
# 载入数据集，可以使用VOC的xml
#-------------------------------------------------------------#
path = r'./VOCdevkit/VOC2007/Annotations'
# 载入所有的xml
# 存储格式为转化为比例后的width,height
#-------------------------------------------------------------#
# 载入所有的xml
# 存储格式为转化为比例后的width,height
#-------------------------------------------------------------#
data = load_data(path)
# 使用k聚类算法
#-------------------------------------------------------------#
# 使用k聚类算法
#-------------------------------------------------------------#
out = kmeans(data,anchors_num)
out = out[np.argsort(out[:,0])]
print('acc:{:.2f}%'.format(avg_iou(data,out) * 100))
......
nets/CSPdarknet.py
浏览文件 @ 34d2e3e1
import math
from collections import OrderedDict
import torch
import torch.nn as nn
......
nets/__init__.py 0 → 100644
浏览文件 @ 34d2e3e1
#
\ No newline at end of file
nets/yolo.py 0 → 100644
浏览文件 @ 34d2e3e1
from collections import OrderedDict
import torch
import torch.nn as nn
from nets.CSPdarknet import darknet53
def conv2d(filter_in, filter_out, kernel_size, stride=1):
pad = (kernel_size - 1) // 2 if kernel_size else 0
return nn.Sequential(OrderedDict([
("conv", nn.Conv2d(filter_in, filter_out, kernel_size=kernel_size, stride=stride, padding=pad, bias=False)),
("bn", nn.BatchNorm2d(filter_out)),
("relu", nn.LeakyReLU(0.1)),
]))
#---------------------------------------------------#
# SPP结构，利用不同大小的池化核进行池化
# 池化后堆叠
#---------------------------------------------------#
class SpatialPyramidPooling(nn.Module):
def __init__(self, pool_sizes=[5, 9, 13]):
super(SpatialPyramidPooling, self).__init__()
self.maxpools = nn.ModuleList([nn.MaxPool2d(pool_size, 1, pool_size//2) for pool_size in pool_sizes])
def forward(self, x):
features = [maxpool(x) for maxpool in self.maxpools[::-1]]
features = torch.cat(features + [x], dim=1)
return features
#---------------------------------------------------#
# 卷积 + 上采样
#---------------------------------------------------#
class Upsample(nn.Module):
def __init__(self, in_channels, out_channels):
super(Upsample, self).__init__()
self.upsample = nn.Sequential(
conv2d(in_channels, out_channels, 1),
nn.Upsample(scale_factor=2, mode='nearest')
)
def forward(self, x,):
x = self.upsample(x)
return x
#---------------------------------------------------#
# 三次卷积块
#---------------------------------------------------#
def make_three_conv(filters_list, in_filters):
m = nn.Sequential(
conv2d(in_filters, filters_list[0], 1),
conv2d(filters_list[0], filters_list[1], 3),
conv2d(filters_list[1], filters_list[0], 1),
)
return m
#---------------------------------------------------#
# 五次卷积块
#---------------------------------------------------#
def make_five_conv(filters_list, in_filters):
m = nn.Sequential(
conv2d(in_filters, filters_list[0], 1),
conv2d(filters_list[0], filters_list[1], 3),
conv2d(filters_list[1], filters_list[0], 1),
conv2d(filters_list[0], filters_list[1], 3),
conv2d(filters_list[1], filters_list[0], 1),
)
return m
#---------------------------------------------------#
# 最后获得yolov4的输出
#---------------------------------------------------#
def yolo_head(filters_list, in_filters):
m = nn.Sequential(
conv2d(in_filters, filters_list[0], 3),
nn.Conv2d(filters_list[0], filters_list[1], 1),
)
return m
#---------------------------------------------------#
# yolo_body
#---------------------------------------------------#
class YoloBody(nn.Module):
def __init__(self, anchors_mask, num_classes):
super(YoloBody, self).__init__()
#---------------------------------------------------#
# 生成CSPdarknet53的主干模型
# 获得三个有效特征层，他们的shape分别是：
# 52,52,256
# 26,26,512
# 13,13,1024
#---------------------------------------------------#
self.backbone = darknet53(None)
self.conv1 = make_three_conv([512,1024],1024)
self.SPP = SpatialPyramidPooling()
self.conv2 = make_three_conv([512,1024],2048)
self.upsample1 = Upsample(512,256)
self.conv_for_P4 = conv2d(512,256,1)
self.make_five_conv1 = make_five_conv([256, 512],512)
self.upsample2 = Upsample(256,128)
self.conv_for_P3 = conv2d(256,128,1)
self.make_five_conv2 = make_five_conv([128, 256],256)
# 3*(5+num_classes) = 3*(5+20) = 3*(4+1+20)=75
self.yolo_head3 = yolo_head([256, len(anchors_mask[0]) * (5 + num_classes)],128)
self.down_sample1 = conv2d(128,256,3,stride=2)
self.make_five_conv3 = make_five_conv([256, 512],512)
# 3*(5+num_classes) = 3*(5+20) = 3*(4+1+20)=75
self.yolo_head2 = yolo_head([512, len(anchors_mask[1]) * (5 + num_classes)],256)
self.down_sample2 = conv2d(256,512,3,stride=2)
self.make_five_conv4 = make_five_conv([512, 1024],1024)
# 3*(5+num_classes)=3*(5+20)=3*(4+1+20)=75
self.yolo_head1 = yolo_head([1024, len(anchors_mask[2]) * (5 + num_classes)],512)
def forward(self, x):
# backbone
x2, x1, x0 = self.backbone(x)
# 13,13,1024 -> 13,13,512 -> 13,13,1024 -> 13,13,512 -> 13,13,2048
P5 = self.conv1(x0)
P5 = self.SPP(P5)
# 13,13,2048 -> 13,13,512 -> 13,13,1024 -> 13,13,512
P5 = self.conv2(P5)
# 13,13,512 -> 13,13,256 -> 26,26,256
P5_upsample = self.upsample1(P5)
# 26,26,512 -> 26,26,256
P4 = self.conv_for_P4(x1)
# 26,26,256 + 26,26,256 -> 26,26,512
P4 = torch.cat([P4,P5_upsample],axis=1)
# 26,26,512 -> 26,26,256 -> 26,26,512 -> 26,26,256 -> 26,26,512 -> 26,26,256
P4 = self.make_five_conv1(P4)
# 26,26,256 -> 26,26,128 -> 52,52,128
P4_upsample = self.upsample2(P4)
# 52,52,256 -> 52,52,128
P3 = self.conv_for_P3(x2)
# 52,52,128 + 52,52,128 -> 52,52,256
P3 = torch.cat([P3,P4_upsample],axis=1)
# 52,52,256 -> 52,52,128 -> 52,52,256 -> 52,52,128 -> 52,52,256 -> 52,52,128
P3 = self.make_five_conv2(P3)
# 52,52,128 -> 26,26,256
P3_downsample = self.down_sample1(P3)
# 26,26,256 + 26,26,256 -> 26,26,512
P4 = torch.cat([P3_downsample,P4],axis=1)
# 26,26,512 -> 26,26,256 -> 26,26,512 -> 26,26,256 -> 26,26,512 -> 26,26,256
P4 = self.make_five_conv3(P4)
# 26,26,256 -> 13,13,512
P4_downsample = self.down_sample2(P4)
# 13,13,512 + 13,13,512 -> 13,13,1024
P5 = torch.cat([P4_downsample,P5],axis=1)
# 13,13,1024 -> 13,13,512 -> 13,13,1024 -> 13,13,512 -> 13,13,1024 -> 13,13,512
P5 = self.make_five_conv4(P5)
#---------------------------------------------------#
# 第三个特征层
# y3=(batch_size,75,52,52)
#---------------------------------------------------#
out2 = self.yolo_head3(P3)
#---------------------------------------------------#
# 第二个特征层
# y2=(batch_size,75,26,26)
#---------------------------------------------------#
out1 = self.yolo_head2(P4)
#---------------------------------------------------#
# 第一个特征层
# y1=(batch_size,75,13,13)
#---------------------------------------------------#
out0 = self.yolo_head1(P5)
return out0, out1, out2
nets/yolo_training.py
浏览文件 @ 34d2e3e1
此差异已折叠。
predict.py
浏览文件 @ 34d2e3e1
#----------------------------------------------------#
# 对视频中的predict.py进行了修改，
# 将单张图片预测、摄像头检测和FPS测试功能
#-----------------------------------------------------------------------#
# predict.py将单张图片预测、摄像头检测、FPS测试和目录遍历检测等功能
# 整合到了一个py文件中，通过指定mode进行模式的修改。
#----------------------------------------------------#
#-----------------------------------------------------------------------#
import time
import cv2
......@@ -13,33 +12,44 @@ from yolo import YOLO
if __name__ == "__main__":
yolo = YOLO()
#-------------------------------------------------------------------------#
#----------------------------------------------------------------------------------------------------------#
# mode用于指定测试的模式：
# 'predict'表示单张图片预测
# 'video'表示视频检测
# 'fps'表示测试fps
#-------------------------------------------------------------------------#
# 'predict'表示单张图片预测，如果想对预测过程进行修改，如保存图片，截取对象等，可以先看下方详细的注释
# 'video'表示视频检测，可调用摄像头或者视频进行检测，详情查看下方注释。
# 'fps'表示测试fps，使用的图片是img里面的street.jpg，详情查看下方注释。
# 'dir_predict'表示遍历文件夹进行检测并保存。默认遍历img文件夹，保存img_out文件夹，详情查看下方注释。
#----------------------------------------------------------------------------------------------------------#
mode = "predict"
#-------------------------------------------------------------------------#
# video_path用于指定视频的路径，当video_path=0时表示检测摄像头
# video_save_path表示视频保存的路径，当video_save_path=""时表示不保存
# video_fps用于保存的视频的fps
# video_path、video_save_path和video_fps仅在mode='video'时有效
# 保存视频时需要ctrl+c退出才会完成完整的保存步骤，不可直接结束程序。
# 保存视频时需要ctrl+c退出或者运行到最后一帧才会完成完整的保存步骤。
#-------------------------------------------------------------------------#
video_path = 0
video_save_path = ""
video_fps = 25.0
#-------------------------------------------------------------------------#
# test_interval用于指定测量fps的时候，图片检测的次数
# 理论上test_interval越大，fps越准确。
#-------------------------------------------------------------------------#
test_interval = 100
#-------------------------------------------------------------------------#
# dir_origin_path指定了用于检测的图片的文件夹路径
# dir_save_path指定了检测完图片的保存路径
# dir_origin_path和dir_save_path仅在mode='dir_predict'时有效
#-------------------------------------------------------------------------#
dir_origin_path = "img/"
dir_save_path = "img_out/"
if mode == "predict":
'''
1、该代码无法直接进行批量预测，如果想要批量预测，可以利用os.listdir()遍历文件夹，利用Image.open打开图片文件进行预测。
具体流程可以参考get_dr_txt.py，在get_dr_txt.py即实现了遍历还实现了目标信息的保存。
2、如果想要进行检测完的图片的保存，利用r_image.save("img.jpg")即可保存，直接在predict.py里进行修改即可。
3、如果想要获得预测框的坐标，可以进入yolo.detect_image函数，在绘图部分读取top，left，bottom，right这四个值。
4、如果想要利用预测框截取下目标，可以进入yolo.detect_image函数，在绘图部分利用获取到的top，left，bottom，right这四个值
1、如果想要进行检测完的图片的保存，利用r_image.save("img.jpg")即可保存，直接在predict.py里进行修改即可。
2、如果想要获得预测框的坐标，可以进入yolo.detect_image函数，在绘图部分读取top，left，bottom，right这四个值。
3、如果想要利用预测框截取下目标，可以进入yolo.detect_image函数，在绘图部分利用获取到的top，left，bottom，right这四个值
在原图上利用矩阵的方式进行截取。
5、如果想要在预测图上写额外的字，比如检测到的特定目标的数量，可以进入yolo.detect_image函数，在绘图部分对predicted_class进行判断，
4、如果想要在预测图上写额外的字，比如检测到的特定目标的数量，可以进入yolo.detect_image函数，在绘图部分对predicted_class进行判断，
比如判断if predicted_class == 'car': 即可判断当前目标是否为车，然后记录数量即可。利用draw.text即可写字。
'''
while True:
......@@ -54,11 +64,11 @@ if __name__ == "__main__":
r_image.show()
elif mode == "video":
capture=cv2.VideoCapture(video_path)
capture = cv2.VideoCapture(video_path)
if video_save_path!="":
fourcc = cv2.VideoWriter_fourcc(*'XVID')
size = (int(capture.get(cv2.CAP_PROP_FRAME_WIDTH)), int(capture.get(cv2.CAP_PROP_FRAME_HEIGHT)))
out = cv2.VideoWriter(video_save_path, fourcc, video_fps, size)
fourcc = cv2.VideoWriter_fourcc(*'XVID')
size = (int(capture.get(cv2.CAP_PROP_FRAME_WIDTH)), int(capture.get(cv2.CAP_PROP_FRAME_HEIGHT)))
out = cv2.VideoWriter(video_save_path, fourcc, video_fps, size)
fps = 0.0
while(True):
......@@ -91,9 +101,23 @@ if __name__ == "__main__":
cv2.destroyAllWindows()
elif mode == "fps":
test_interval = 100
img = Image.open('img/street.jpg')
tact_time = yolo.get_FPS(img, test_interval)
print(str(tact_time) + ' seconds, ' + str(1/tact_time) + 'FPS, @batch_size 1')
elif mode == "dir_predict":
import os
from tqdm import tqdm
img_names = os.listdir(dir_origin_path)
for img_name in tqdm(img_names):
if img_name.lower().endswith(('.bmp', '.dib', '.png', '.jpg', '.jpeg', '.pbm', '.pgm', '.ppm', '.tif', '.tiff')):
image_path = os.path.join(dir_origin_path, img_name)
image = Image.open(image_path)
r_image = yolo.detect_image(image)
if not os.path.exists(dir_save_path):
os.makedirs(dir_save_path)
r_image.save(os.path.join(dir_save_path, img_name))
else:
raise AssertionError("Please specify the correct mode: 'predict', 'video' or 'fps'.")
raise AssertionError("Please specify the correct mode: 'predict', 'video', 'fps' or 'dir_predict'.")
summary.py 0 → 100644
浏览文件 @ 34d2e3e1
#--------------------------------------------#
# 该部分代码用于看网络结构
#--------------------------------------------#
import torch
from torchsummary import summary
from nets.yolo import YoloBody
if __name__ == "__main__":
# 需要使用device来指定网络在GPU还是CPU运行
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
m = YoloBody([[6, 7, 8], [3, 4, 5], [0, 1, 2]], 80).to(device)
summary(m, input_size=(3, 416, 416))
train.py
浏览文件 @ 34d2e3e1
此差异已折叠。
utils/__init__.py 0 → 100644
浏览文件 @ 34d2e3e1
#
\ No newline at end of file
utils/callbacks.py 0 → 100644
浏览文件 @ 34d2e3e1
import os
import scipy.signal
from matplotlib import pyplot as plt
class LossHistory():
def __init__(self, log_dir):
import datetime
curr_time = datetime.datetime.now()
time_str = datetime.datetime.strftime(curr_time,'%Y_%m_%d_%H_%M_%S')
self.log_dir = log_dir
self.time_str = time_str
self.save_path = os.path.join(self.log_dir, "loss_" + str(self.time_str))
self.losses = []
self.val_loss = []
os.makedirs(self.save_path)
def append_loss(self, loss, val_loss):
self.losses.append(loss)
self.val_loss.append(val_loss)
with open(os.path.join(self.save_path, "epoch_loss_" + str(self.time_str) + ".txt"), 'a') as f:
f.write(str(loss))
f.write("\n")
with open(os.path.join(self.save_path, "epoch_val_loss_" + str(self.time_str) + ".txt"), 'a') as f:
f.write(str(val_loss))
f.write("\n")
self.loss_plot()
def loss_plot(self):
iters = range(len(self.losses))
plt.figure()
plt.plot(iters, self.losses, 'red', linewidth = 2, label='train loss')
plt.plot(iters, self.val_loss, 'coral', linewidth = 2, label='val loss')
try:
if len(self.losses) < 25:
num = 5
else:
num = 15
plt.plot(iters, scipy.signal.savgol_filter(self.losses, num, 3), 'green', linestyle = '--', linewidth = 2, label='smooth train loss')
plt.plot(iters, scipy.signal.savgol_filter(self.val_loss, num, 3), '#8B4513', linestyle = '--', linewidth = 2, label='smooth val loss')
except:
pass
plt.grid(True)
plt.xlabel('Epoch')
plt.ylabel('Loss')
plt.legend(loc="upper right")
plt.savefig(os.path.join(self.save_path, "epoch_loss_" + str(self.time_str) + ".png"))
plt.cla()
plt.close("all")
utils/dataloader.py
浏览文件 @ 34d2e3e1
from random import sample, shuffle
import cv2
import numpy as np
from PIL import Image
from torch.utils.data.dataset import Dataset
from utils.utils import merge_bboxes
from utils.utils import cvtColor, preprocess_input
class YoloDataset(Dataset):
def __init__(self, train_lines, image_size, mosaic=True, is_train=True):
def __init__(self, annotation_lines, input_shape, num_classes, mosaic, train):
super(YoloDataset, self).__init__()
self.train_lines = train_lines
self.train_batches = len(train_lines)
self.image_size = image_size
self.mosaic = mosaic
self.flag = True
self.is_train = is_train
self.annotation_lines = annotation_lines
self.input_shape = input_shape
self.num_classes = num_classes
self.length = len(self.annotation_lines)
self.mosaic = mosaic
self.train = train
def __len__(self):
return self.train_batches
return self.length
def __getitem__(self, index):
index = index % self.length
#---------------------------------------------------#
# 训练时进行数据的随机增强
# 验证时不进行数据的随机增强
#---------------------------------------------------#
if self.mosaic:
if self.rand() < 0.5:
lines = sample(self.annotation_lines, 3)
lines.append(self.annotation_lines[index])
shuffle(lines)
image, box = self.get_random_data_with_Mosaic(lines, self.input_shape)
else:
image, box = self.get_random_data(self.annotation_lines[index], self.input_shape, random = self.train)
else:
image, box = self.get_random_data(self.annotation_lines[index], self.input_shape, random = self.train)
image = np.transpose(preprocess_input(np.array(image, dtype=np.float32)), (2, 0, 1))
box = np.array(box, dtype=np.float32)
if len(box) != 0:
box[:, [0, 2]] = box[:, [0, 2]] / self.input_shape[1]
box[:, [1, 3]] = box[:, [1, 3]] / self.input_shape[0]
box[:, 2:4] = box[:, 2:4] - box[:, 0:2]
box[:, 0:2] = box[:, 0:2] + box[:, 2:4] / 2
return image, box
def rand(self, a=0, b=1):
return np.random.rand() * (b - a) + a
return np.random.rand()*(b-a) + a
def get_random_data(self, annotation_line, input_shape, jitter=.3, hue=.1, sat=1.5, val=1.5, random=True):
"""实时数据增强的随机预处理"""
line = annotation_line.split()
image = Image.open(line[0])
iw, ih = image.size
h, w = input_shape
box = np.array([np.array(list(map(int, box.split(',')))) for box in line[1:]])
line = annotation_line.split()
#------------------------------#
# 读取图像并转换成RGB图像
#------------------------------#
image = Image.open(line[0])
image = cvtColor(image)
#------------------------------#
# 获得图像的高宽与目标高宽
#------------------------------#
iw, ih = image.size
h, w = input_shape
#------------------------------#
# 获得预测框
#------------------------------#
box = np.array([np.array(list(map(int,box.split(',')))) for box in line[1:]])
if not random:
scale = min(w/iw, h/ih)
......@@ -38,56 +74,64 @@ class YoloDataset(Dataset):
dx = (w-nw)//2
dy = (h-nh)//2
image = image.resize((nw,nh), Image.BICUBIC)
new_image = Image.new('RGB', (w,h), (128,128,128))
#---------------------------------#
# 将图像多余的部分加上灰条
#---------------------------------#
image = image.resize((nw,nh), Image.BICUBIC)
new_image = Image.new('RGB', (w,h), (128,128,128))
new_image.paste(image, (dx, dy))
image_data = np.array(new_image, np.float32)
image_data = np.array(new_image, np.float32)
# 调整目标框坐标
box_data = np.zeros((len(box), 5))
if len(box) > 0:
#---------------------------------#
# 对真实框进行调整
#---------------------------------#
if len(box)>0:
np.random.shuffle(box)
box[:, [0, 2]] = box[:, [0, 2]] * nw / iw + dx
box[:, [1, 3]] = box[:, [1, 3]] * nh / ih + dy
box[:, 0:2][box[:, 0:2] < 0] = 0
box[:, 2][box[:, 2] > w] = w
box[:, 3][box[:, 3] > h] = h
box[:, [0,2]] = box[:, [0,2]]*nw/iw + dx
box[:, [1,3]] = box[:, [1,3]]*nh/ih + dy
box[:, 0:2][box[:, 0:2]<0] = 0
box[:, 2][box[:, 2]>w] = w
box[:, 3][box[:, 3]>h] = h
box_w = box[:, 2] - box[:, 0]
box_h = box[:, 3] - box[:, 1]
box = box[np.logical_and(box_w > 1, box_h > 1)] # 保留有效框
box_data = np.zeros((len(box), 5))
box_data[:len(box)] = box
return image_data, box_data
# 调整图片大小
new_ar = w / h * self.rand(1 - jitter, 1 + jitter) / self.rand(1 - jitter, 1 + jitter)
box = box[np.logical_and(box_w>1, box_h>1)] # discard invalid box
return image_data, box
#------------------------------------------#
# 对图像进行缩放并且进行长和宽的扭曲
#------------------------------------------#
new_ar = w/h * self.rand(1-jitter,1+jitter) / self.rand(1-jitter,1+jitter)
scale = self.rand(.25, 2)
if new_ar < 1:
nh = int(scale * h)
nw = int(nh * new_ar)
nh = int(scale*h)
nw = int(nh*new_ar)
else:
nw = int(scale * w)
nh = int(nw / new_ar)
image = image.resize((nw, nh), Image.BICUBIC)
# 放置图片
dx = int(self.rand(0, w - nw))
dy = int(self.rand(0, h - nh))
new_image = Image.new('RGB', (w, h),
(np.random.randint(0, 255), np.random.randint(0, 255), np.random.randint(0, 255)))
nw = int(scale*w)
nh = int(nw/new_ar)
image = image.resize((nw,nh), Image.BICUBIC)
#------------------------------------------#
# 将图像多余的部分加上灰条
#------------------------------------------#
dx = int(self.rand(0, w-nw))
dy = int(self.rand(0, h-nh))
new_image = Image.new('RGB', (w,h), (128,128,128))
new_image.paste(image, (dx, dy))
image = new_image
# 是否翻转图片
flip = self.rand() < .5
if flip:
image = image.transpose(Image.FLIP_LEFT_RIGHT)
#------------------------------------------#
# 翻转图像
#------------------------------------------#
flip = self.rand()<.5
if flip: image = image.transpose(Image.FLIP_LEFT_RIGHT)
# 色域变换
#------------------------------------------#
# 色域扭曲
#------------------------------------------#
hue = self.rand(-hue, hue)
sat = self.rand(1, sat) if self.rand() < .5 else 1 / self.rand(1, sat)
val = self.rand(1, val) if self.rand() < .5 else 1 / self.rand(1, val)
sat = self.rand(1, sat) if self.rand()<.5 else 1/self.rand(1, sat)
val = self.rand(1, val) if self.rand()<.5 else 1/self.rand(1, val)
x = cv2.cvtColor(np.array(image,np.float32)/255, cv2.COLOR_RGB2HSV)
x[..., 0] += hue*360
x[..., 0][x[..., 0]>1] -= 1
......@@ -99,112 +143,134 @@ class YoloDataset(Dataset):
x[x<0] = 0
image_data = cv2.cvtColor(x, cv2.COLOR_HSV2RGB)*255
# 调整目标框坐标
box_data = np.zeros((len(box), 5))
if len(box) > 0:
#---------------------------------#
# 对真实框进行调整
#---------------------------------#
if len(box)>0:
np.random.shuffle(box)
box[:, [0, 2]] = box[:, [0, 2]] * nw / iw + dx
box[:, [1, 3]] = box[:, [1, 3]] * nh / ih + dy
if flip:
box[:, [0, 2]] = w - box[:, [2, 0]]
box[:, 0:2][box[:, 0:2] < 0] = 0
box[:, 2][box[:, 2] > w] = w
box[:, 3][box[:, 3] > h] = h
box[:, [0,2]] = box[:, [0,2]]*nw/iw + dx
box[:, [1,3]] = box[:, [1,3]]*nh/ih + dy
if flip: box[:, [0,2]] = w - box[:, [2,0]]
box[:, 0:2][box[:, 0:2]<0] = 0
box[:, 2][box[:, 2]>w] = w
box[:, 3][box[:, 3]>h] = h
box_w = box[:, 2] - box[:, 0]
box_h = box[:, 3] - box[:, 1]
box = box[np.logical_and(box_w > 1, box_h > 1)] # 保留有效框
box_data = np.zeros((len(box), 5))
box_data[:len(box)] = box
return image_data, box_data
def get_random_data_with_Mosaic(self, annotation_line, input_shape, hue=.1, sat=1.5, val=1.5):
box = box[np.logical_and(box_w>1, box_h>1)]
return image_data, box
def merge_bboxes(self, bboxes, cutx, cuty):
merge_bbox = []
for i in range(len(bboxes)):
for box in bboxes[i]:
tmp_box = []
x1, y1, x2, y2 = box[0], box[1], box[2], box[3]
if i == 0:
if y1 > cuty or x1 > cutx:
continue
if y2 >= cuty and y1 <= cuty:
y2 = cuty
if x2 >= cutx and x1 <= cutx:
x2 = cutx
if i == 1:
if y2 < cuty or x1 > cutx:
continue
if y2 >= cuty and y1 <= cuty:
y1 = cuty
if x2 >= cutx and x1 <= cutx:
x2 = cutx
if i == 2:
if y2 < cuty or x2 < cutx:
continue
if y2 >= cuty and y1 <= cuty:
y1 = cuty
if x2 >= cutx and x1 <= cutx:
x1 = cutx
if i == 3:
if y1 > cuty or x2 < cutx:
continue
if y2 >= cuty and y1 <= cuty:
y2 = cuty
if x2 >= cutx and x1 <= cutx:
x1 = cutx
tmp_box.append(x1)
tmp_box.append(y1)
tmp_box.append(x2)
tmp_box.append(y2)
tmp_box.append(box[-1])
merge_bbox.append(tmp_box)
return merge_bbox
def get_random_data_with_Mosaic(self, annotation_line, input_shape, max_boxes=100, hue=.1, sat=1.5, val=1.5):
h, w = input_shape
min_offset_x = 0.3
min_offset_y = 0.3
scale_low = 1 - min(min_offset_x, min_offset_y)
scale_high = scale_low + 0.2
image_datas = []
box_datas = []
index = 0
place_x = [0, 0, int(w * min_offset_x), int(w * min_offset_x)]
place_y = [0, int(h * min_offset_y), int(h * min_offset_y), 0]
min_offset_x = self.rand(0.25, 0.75)
min_offset_y = self.rand(0.25, 0.75)
nws = [ int(w * self.rand(0.4, 1)), int(w * self.rand(0.4, 1)), int(w * self.rand(0.4, 1)), int(w * self.rand(0.4, 1))]
nhs = [ int(h * self.rand(0.4, 1)), int(h * self.rand(0.4, 1)), int(h * self.rand(0.4, 1)), int(h * self.rand(0.4, 1))]
place_x = [int(w*min_offset_x) - nws[0], int(w*min_offset_x) - nws[1], int(w*min_offset_x), int(w*min_offset_x)]
place_y = [int(h*min_offset_y) - nhs[0], int(h*min_offset_y), int(h*min_offset_y), int(h*min_offset_y) - nhs[3]]
image_datas = []
box_datas = []
index = 0
for line in annotation_line:
# 每一行进行分割
line_content = line.split()
# 打开图片
image = Image.open(line_content[0])
image = image.convert("RGB")
image = cvtColor(image)
# 图片的大小
iw, ih = image.size
# 保存框的位置
box = np.array([np.array(list(map(int, box.split(',')))) for box in line_content[1:]])
box = np.array([np.array(list(map(int,box.split(',')))) for box in line_content[1:]])
# 是否翻转图片
flip = self.rand() < .5
if flip and len(box) > 0:
flip = self.rand()<.5
if flip and len(box)>0:
image = image.transpose(Image.FLIP_LEFT_RIGHT)
box[:, [0, 2]] = iw - box[:, [2, 0]]
# 对输入进来的图片进行缩放
new_ar = w / h
scale = self.rand(scale_low, scale_high)
if new_ar < 1:
nh = int(scale * h)
nw = int(nh * new_ar)
else:
nw = int(scale * w)
nh = int(nw / new_ar)
image = image.resize((nw, nh), Image.BICUBIC)
# 进行色域变换
hue = self.rand(-hue, hue)
sat = self.rand(1, sat) if self.rand() < .5 else 1 / self.rand(1, sat)
val = self.rand(1, val) if self.rand() < .5 else 1 / self.rand(1, val)
x = cv2.cvtColor(np.array(image,np.float32)/255, cv2.COLOR_RGB2HSV)
x[..., 0] += hue*360
x[..., 0][x[..., 0]>1] -= 1
x[..., 0][x[..., 0]<0] += 1
x[..., 1] *= sat
x[..., 2] *= val
x[x[:,:, 0]>360, 0] = 360
x[:, :, 1:][x[:, :, 1:]>1] = 1
x[x<0] = 0
image = cv2.cvtColor(x, cv2.COLOR_HSV2RGB) # numpy array, 0 to 1
image = Image.fromarray((image * 255).astype(np.uint8))
box[:, [0,2]] = iw - box[:, [2,0]]
nw = nws[index]
nh = nhs[index]
image = image.resize((nw,nh), Image.BICUBIC)
# 将图片进行放置，分别对应四张分割图片的位置
dx = place_x[index]
dy = place_y[index]
new_image = Image.new('RGB', (w, h),
(np.random.randint(0, 255), np.random.randint(0, 255), np.random.randint(0, 255)))
new_image = Image.new('RGB', (w,h), (128,128,128))
new_image.paste(image, (dx, dy))
image_data = np.array(new_image)
index = index + 1
box_data = []
# 对box进行重新处理
if len(box) > 0:
if len(box)>0:
np.random.shuffle(box)
box[:, [0, 2]] = box[:, [0, 2]] * nw / iw + dx
box[:, [1, 3]] = box[:, [1, 3]] * nh / ih + dy
box[:, 0:2][box[:, 0:2] < 0] = 0
box[:, 2][box[:, 2] > w] = w
box[:, 3][box[:, 3] > h] = h
box[:, [0,2]] = box[:, [0,2]]*nw/iw + dx
box[:, [1,3]] = box[:, [1,3]]*nh/ih + dy
box[:, 0:2][box[:, 0:2]<0] = 0
box[:, 2][box[:, 2]>w] = w
box[:, 3][box[:, 3]>h] = h
box_w = box[:, 2] - box[:, 0]
box_h = box[:, 3] - box[:, 1]
box = box[np.logical_and(box_w > 1, box_h > 1)]
box_data = np.zeros((len(box), 5))
box = box[np.logical_and(box_w>1, box_h>1)]
box_data = np.zeros((len(box),5))
box_data[:len(box)] = box
image_datas.append(image_data)
box_datas.append(box_data)
# 将图片分割，放在一起
cutx = np.random.randint(int(w * min_offset_x), int(w * (1 - min_offset_x)))
cuty = np.random.randint(int(h * min_offset_y), int(h * (1 - min_offset_y)))
cutx = int(w * min_offset_x)
cuty = int(h * min_offset_y)
new_image = np.zeros([h, w, 3])
new_image[:cuty, :cutx, :] = image_datas[0][:cuty, :cutx, :]
......@@ -212,47 +278,26 @@ class YoloDataset(Dataset):
new_image[cuty:, cutx:, :] = image_datas[2][cuty:, cutx:, :]
new_image[:cuty, cutx:, :] = image_datas[3][:cuty, cutx:, :]
# 进行色域变换
hue = self.rand(-hue, hue)
sat = self.rand(1, sat) if self.rand()<.5 else 1/self.rand(1, sat)
val = self.rand(1, val) if self.rand()<.5 else 1/self.rand(1, val)
x = cv2.cvtColor(np.array(new_image/255,np.float32), cv2.COLOR_RGB2HSV)
x[..., 0] += hue*360
x[..., 0][x[..., 0]>1] -= 1
x[..., 0][x[..., 0]<0] += 1
x[..., 1] *= sat
x[..., 2] *= val
x[x[:, :, 0]>360, 0] = 360
x[:, :, 1:][x[:, :, 1:]>1] = 1
x[x<0] = 0
new_image = cv2.cvtColor(x, cv2.COLOR_HSV2RGB)*255
# 对框进行进一步的处理
new_boxes = np.array(merge_bboxes(box_datas, cutx, cuty))
new_boxes = self.merge_bboxes(box_datas, cutx, cuty)
return new_image, new_boxes
def __getitem__(self, index):
lines = self.train_lines
n = self.train_batches
index = index % n
if self.mosaic:
if self.flag and (index + 4) < n:
img, y = self.get_random_data_with_Mosaic(lines[index:index + 4], self.image_size[0:2])
else:
img, y = self.get_random_data(lines[index], self.image_size[0:2], random=self.is_train)
self.flag = bool(1-self.flag)
else:
img, y = self.get_random_data(lines[index], self.image_size[0:2], random=self.is_train)
if len(y) != 0:
# 从坐标转换成0~1的百分比
boxes = np.array(y[:, :4], dtype=np.float32)
boxes[:, 0] = boxes[:, 0] / self.image_size[1]
boxes[:, 1] = boxes[:, 1] / self.image_size[0]
boxes[:, 2] = boxes[:, 2] / self.image_size[1]
boxes[:, 3] = boxes[:, 3] / self.image_size[0]
boxes = np.maximum(np.minimum(boxes, 1), 0)
boxes[:, 2] = boxes[:, 2] - boxes[:, 0]
boxes[:, 3] = boxes[:, 3] - boxes[:, 1]
boxes[:, 0] = boxes[:, 0] + boxes[:, 2] / 2
boxes[:, 1] = boxes[:, 1] + boxes[:, 3] / 2
y = np.concatenate([boxes, y[:, -1:]], axis=-1)
img = np.array(img, dtype=np.float32)
tmp_inp = np.transpose(img / 255.0, (2, 0, 1))
tmp_targets = np.array(y, dtype=np.float32)
return tmp_inp, tmp_targets
# DataLoader中collate_fn使用
def yolo_dataset_collate(batch):
images = []
......@@ -261,5 +306,4 @@ def yolo_dataset_collate(batch):
images.append(img)
bboxes.append(box)
images = np.array(images)
return images, bboxes
return images, bboxes
\ No newline at end of file
utils/utils.py
浏览文件 @ 34d2e3e1
from __future__ import division
import numpy as np
import torch
import torch.nn as nn
from PIL import Image
from torchvision.ops import nms
class DecodeBox(nn.Module):
def __init__(self, anchors, num_classes, img_size):
super(DecodeBox, self).__init__()
#-----------------------------------------------------------#
# 13x13的特征层对应的anchor是[142, 110], [192, 243], [459, 401]
# 26x26的特征层对应的anchor是[36, 75], [76, 55], [72, 146]
# 52x52的特征层对应的anchor是[12, 16], [19, 36], [40, 28]
#-----------------------------------------------------------#
self.anchors = anchors
self.num_anchors = len(anchors)
self.num_classes = num_classes
self.bbox_attrs = 5 + num_classes
self.img_size = img_size
def forward(self, input):
#-----------------------------------------------#
# 输入的input一共有三个，他们的shape分别是
# batch_size, 255, 13, 13
# batch_size, 255, 26, 26
# batch_size, 255, 52, 52
#-----------------------------------------------#
batch_size = input.size(0)
input_height = input.size(2)
input_width = input.size(3)
#-----------------------------------------------#
# 输入为416x416时
# stride_h = stride_w = 32、16、8
#-----------------------------------------------#
stride_h = self.img_size[1] / input_height
stride_w = self.img_size[0] / input_width
#-------------------------------------------------#
# 此时获得的scaled_anchors大小是相对于特征层的
#-------------------------------------------------#
scaled_anchors = [(anchor_width / stride_w, anchor_height / stride_h) for anchor_width, anchor_height in self.anchors]
#-----------------------------------------------#
# 输入的input一共有三个，他们的shape分别是
# batch_size, 3, 13, 13, 85
# batch_size, 3, 26, 26, 85
# batch_size, 3, 52, 52, 85
#-----------------------------------------------#
prediction = input.view(batch_size, self.num_anchors,
self.bbox_attrs, input_height, input_width).permute(0, 1, 3, 4, 2).contiguous()
# 先验框的中心位置的调整参数
x = torch.sigmoid(prediction[..., 0])
y = torch.sigmoid(prediction[..., 1])
# 先验框的宽高调整参数
w = prediction[..., 2]
h = prediction[..., 3]
# 获得置信度，是否有物体
conf = torch.sigmoid(prediction[..., 4])
# 种类置信度
pred_cls = torch.sigmoid(prediction[..., 5:])
FloatTensor = torch.cuda.FloatTensor if x.is_cuda else torch.FloatTensor
LongTensor = torch.cuda.LongTensor if x.is_cuda else torch.LongTensor
#----------------------------------------------------------#
# 生成网格，先验框中心，网格左上角
# batch_size,3,13,13
#----------------------------------------------------------#
grid_x = torch.linspace(0, input_width - 1, input_width).repeat(input_height, 1).repeat(
batch_size * self.num_anchors, 1, 1).view(x.shape).type(FloatTensor)
grid_y = torch.linspace(0, input_height - 1, input_height).repeat(input_width, 1).t().repeat(
batch_size * self.num_anchors, 1, 1).view(y.shape).type(FloatTensor)
#----------------------------------------------------------#
# 按照网格格式生成先验框的宽高
# batch_size,3,13,13
#----------------------------------------------------------#
anchor_w = FloatTensor(scaled_anchors).index_select(1, LongTensor([0]))
anchor_h = FloatTensor(scaled_anchors).index_select(1, LongTensor([1]))
anchor_w = anchor_w.repeat(batch_size, 1).repeat(1, 1, input_height * input_width).view(w.shape)
anchor_h = anchor_h.repeat(batch_size, 1).repeat(1, 1, input_height * input_width).view(h.shape)
#----------------------------------------------------------#
# 利用预测结果对先验框进行调整
# 首先调整先验框的中心，从先验框中心向右下角偏移
# 再调整先验框的宽高。
#----------------------------------------------------------#
pred_boxes = FloatTensor(prediction[..., :4].shape)
pred_boxes[..., 0] = x.data + grid_x
pred_boxes[..., 1] = y.data + grid_y
pred_boxes[..., 2] = torch.exp(w.data) * anchor_w
pred_boxes[..., 3] = torch.exp(h.data) * anchor_h
# fig = plt.figure()
# ax = fig.add_subplot(121)
# if input_height==13:
# plt.ylim(0,13)
# plt.xlim(0,13)
# elif input_height==26:
# plt.ylim(0,26)
# plt.xlim(0,26)
# elif input_height==52:
# plt.ylim(0,52)
# plt.xlim(0,52)
# plt.scatter(grid_x.cpu(),grid_y.cpu())
# anchor_left = grid_x - anchor_w/2
# anchor_top = grid_y - anchor_h/2
# rect1 = plt.Rectangle([anchor_left[0,0,5,5],anchor_top[0,0,5,5]],anchor_w[0,0,5,5],anchor_h[0,0,5,5],color="r",fill=False)
# rect2 = plt.Rectangle([anchor_left[0,1,5,5],anchor_top[0,1,5,5]],anchor_w[0,1,5,5],anchor_h[0,1,5,5],color="r",fill=False)
# rect3 = plt.Rectangle([anchor_left[0,2,5,5],anchor_top[0,2,5,5]],anchor_w[0,2,5,5],anchor_h[0,2,5,5],color="r",fill=False)
# ax.add_patch(rect1)
# ax.add_patch(rect2)
# ax.add_patch(rect3)
# ax = fig.add_subplot(122)
# if input_height==13:
# plt.ylim(0,13)
# plt.xlim(0,13)
# elif input_height==26:
# plt.ylim(0,26)
# plt.xlim(0,26)
# elif input_height==52:
# plt.ylim(0,52)
# plt.xlim(0,52)
# plt.scatter(grid_x.cpu(),grid_y.cpu())
# plt.scatter(pred_boxes[0,:,5,5,0].cpu(),pred_boxes[0,:,5,5,1].cpu(),c='r')
# pre_left = pred_boxes[...,0] - pred_boxes[...,2]/2
# pre_top = pred_boxes[...,1] - pred_boxes[...,3]/2
# rect1 = plt.Rectangle([pre_left[0,0,5,5],pre_top[0,0,5,5]],pred_boxes[0,0,5,5,2],pred_boxes[0,0,5,5,3],color="r",fill=False)
# rect2 = plt.Rectangle([pre_left[0,1,5,5],pre_top[0,1,5,5]],pred_boxes[0,1,5,5,2],pred_boxes[0,1,5,5,3],color="r",fill=False)
# rect3 = plt.Rectangle([pre_left[0,2,5,5],pre_top[0,2,5,5]],pred_boxes[0,2,5,5,2],pred_boxes[0,2,5,5,3],color="r",fill=False)
# ax.add_patch(rect1)
# ax.add_patch(rect2)
# ax.add_patch(rect3)
# plt.show()
#----------------------------------------------------------#
# 将输出结果调整成相对于输入图像大小
#----------------------------------------------------------#
_scale = torch.Tensor([stride_w, stride_h] * 2).type(FloatTensor)
output = torch.cat((pred_boxes.view(batch_size, -1, 4) * _scale,
conf.view(batch_size, -1, 1), pred_cls.view(batch_size, -1, self.num_classes)), -1)
return output.data
def letterbox_image(image, size):
iw, ih = image.size
w, h = size
scale = min(w/iw, h/ih)
nw = int(iw*scale)
nh = int(ih*scale)
image = image.resize((nw,nh), Image.BICUBIC)
new_image = Image.new('RGB', size, (128,128,128))
new_image.paste(image, ((w-nw)//2, (h-nh)//2))
return new_image
def yolo_correct_boxes(top, left, bottom, right, input_shape, image_shape):
new_shape = image_shape*np.min(input_shape/image_shape)
offset = (input_shape-new_shape)/2./input_shape
scale = input_shape/new_shape
box_yx = np.concatenate(((top+bottom)/2,(left+right)/2),axis=-1)/input_shape
box_hw = np.concatenate((bottom-top,right-left),axis=-1)/input_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 = np.concatenate([
box_mins[:, 0:1],
box_mins[:, 1:2],
box_maxes[:, 0:1],
box_maxes[:, 1:2]
],axis=-1)
boxes *= np.concatenate([image_shape, image_shape],axis=-1)
return boxes
def bbox_iou(box1, box2, x1y1x2y2=True):
"""
计算IOU
"""
if not x1y1x2y2:
b1_x1, b1_x2 = box1[:, 0] - box1[:, 2] / 2, box1[:, 0] + box1[:, 2] / 2
b1_y1, b1_y2 = box1[:, 1] - box1[:, 3] / 2, box1[:, 1] + box1[:, 3] / 2
b2_x1, b2_x2 = box2[:, 0] - box2[:, 2] / 2, box2[:, 0] + box2[:, 2] / 2
b2_y1, b2_y2 = box2[:, 1] - box2[:, 3] / 2, box2[:, 1] + box2[:, 3] / 2
#---------------------------------------------------------#
# 将图像转换成RGB图像，防止灰度图在预测时报错。
# 代码仅仅支持RGB图像的预测，所有其它类型的图像都会转化成RGB
#---------------------------------------------------------#
def cvtColor(image):
if len(np.shape(image)) == 3 and np.shape(image)[-2] == 3:
return image
else:
b1_x1, b1_y1, b1_x2, b1_y2 = box1[:, 0], box1[:, 1], box1[:, 2], box1[:, 3]
b2_x1, b2_y1, b2_x2, b2_y2 = box2[:, 0], box2[:, 1], box2[:, 2], box2[:, 3]
inter_rect_x1 = torch.max(b1_x1, b2_x1)
inter_rect_y1 = torch.max(b1_y1, b2_y1)
inter_rect_x2 = torch.min(b1_x2, b2_x2)
inter_rect_y2 = torch.min(b1_y2, b2_y2)
inter_area = torch.clamp(inter_rect_x2 - inter_rect_x1 + 1, min=0) * \
torch.clamp(inter_rect_y2 - inter_rect_y1 + 1, min=0)
b1_area = (b1_x2 - b1_x1 + 1) * (b1_y2 - b1_y1 + 1)
b2_area = (b2_x2 - b2_x1 + 1) * (b2_y2 - b2_y1 + 1)
iou = inter_area / (b1_area + b2_area - inter_area + 1e-16)
return iou
def non_max_suppression(prediction, num_classes, conf_thres=0.5, nms_thres=0.4):
#----------------------------------------------------------#
# 将预测结果的格式转换成左上角右下角的格式。
# prediction [batch_size, num_anchors, 85]
#----------------------------------------------------------#
box_corner = prediction.new(prediction.shape)
box_corner[:, :, 0] = prediction[:, :, 0] - prediction[:, :, 2] / 2
box_corner[:, :, 1] = prediction[:, :, 1] - prediction[:, :, 3] / 2
box_corner[:, :, 2] = prediction[:, :, 0] + prediction[:, :, 2] / 2
box_corner[:, :, 3] = prediction[:, :, 1] + prediction[:, :, 3] / 2
prediction[:, :, :4] = box_corner[:, :, :4]
output = [None for _ in range(len(prediction))]
for image_i, image_pred in enumerate(prediction):
#----------------------------------------------------------#
# 对种类预测部分取max。
# class_conf [num_anchors, 1] 种类置信度
# class_pred [num_anchors, 1] 种类
#----------------------------------------------------------#
class_conf, class_pred = torch.max(image_pred[:, 5:5 + num_classes], 1, keepdim=True)
#----------------------------------------------------------#
# 利用置信度进行第一轮筛选
#----------------------------------------------------------#
conf_mask = (image_pred[:, 4] * class_conf[:, 0] >= conf_thres).squeeze()
#----------------------------------------------------------#
# 根据置信度进行预测结果的筛选
#----------------------------------------------------------#
image_pred = image_pred[conf_mask]
class_conf = class_conf[conf_mask]
class_pred = class_pred[conf_mask]
if not image_pred.size(0):
continue
#-------------------------------------------------------------------------#
# detections [num_anchors, 7]
# 7的内容为：x1, y1, x2, y2, obj_conf, class_conf, class_pred
#-------------------------------------------------------------------------#
detections = torch.cat((image_pred[:, :5], class_conf.float(), class_pred.float()), 1)
#------------------------------------------#
# 获得预测结果中包含的所有种类
#------------------------------------------#
unique_labels = detections[:, -1].cpu().unique()
if prediction.is_cuda:
unique_labels = unique_labels.cuda()
detections = detections.cuda()
for c in unique_labels:
#------------------------------------------#
# 获得某一类得分筛选后全部的预测结果
#------------------------------------------#
detections_class = detections[detections[:, -1] == c]
#------------------------------------------#
# 使用官方自带的非极大抑制会速度更快一些！
#------------------------------------------#
keep = nms(
detections_class[:, :4],
detections_class[:, 4] * detections_class[:, 5],
nms_thres
)
max_detections = detections_class[keep]
# # 按照存在物体的置信度排序
# _, conf_sort_index = torch.sort(detections_class[:, 4]*detections_class[:, 5], descending=True)
# detections_class = detections_class[conf_sort_index]
# # 进行非极大抑制
# max_detections = []
# while detections_class.size(0):
# # 取出这一类置信度最高的，一步一步往下判断，判断重合程度是否大于nms_thres，如果是则去除掉
# max_detections.append(detections_class[0].unsqueeze(0))
# if len(detections_class) == 1:
# break
# ious = bbox_iou(max_detections[-1], detections_class[1:])
# detections_class = detections_class[1:][ious < nms_thres]
# # 堆叠
# max_detections = torch.cat(max_detections).data
# Add max detections to outputs
output[image_i] = max_detections if output[image_i] is None else torch.cat(
(output[image_i], max_detections))
return output
def merge_bboxes(bboxes, cutx, cuty):
merge_bbox = []
for i in range(len(bboxes)):
for box in bboxes[i]:
tmp_box = []
x1,y1,x2,y2 = box[0], box[1], box[2], box[3]
if i == 0:
if y1 > cuty or x1 > cutx:
continue
if y2 >= cuty and y1 <= cuty:
y2 = cuty
if y2-y1 < 5:
continue
if x2 >= cutx and x1 <= cutx:
x2 = cutx
if x2-x1 < 5:
continue
if i == 1:
if y2 < cuty or x1 > cutx:
continue
if y2 >= cuty and y1 <= cuty:
y1 = cuty
if y2-y1 < 5:
continue
if x2 >= cutx and x1 <= cutx:
x2 = cutx
if x2-x1 < 5:
continue
if i == 2:
if y2 < cuty or x2 < cutx:
continue
if y2 >= cuty and y1 <= cuty:
y1 = cuty
if y2-y1 < 5:
continue
if x2 >= cutx and x1 <= cutx:
x1 = cutx
if x2-x1 < 5:
continue
if i == 3:
if y1 > cuty or x2 < cutx:
continue
if y2 >= cuty and y1 <= cuty:
y2 = cuty
if y2-y1 < 5:
continue
if x2 >= cutx and x1 <= cutx:
x1 = cutx
if x2-x1 < 5:
continue
image = image.convert('RGB')
return image
#---------------------------------------------------#
# 对输入图像进行resize
#---------------------------------------------------#
def resize_image(image, size, letterbox_image):
iw, ih = image.size
w, h = size
if letterbox_image:
scale = min(w/iw, h/ih)
nw = int(iw*scale)
nh = int(ih*scale)
image = image.resize((nw,nh), Image.BICUBIC)
new_image = Image.new('RGB', size, (128,128,128))
new_image.paste(image, ((w-nw)//2, (h-nh)//2))
else:
new_image = image.resize((w, h), Image.BICUBIC)
return new_image
tmp_box.append(x1)
tmp_box.append(y1)
tmp_box.append(x2)
tmp_box.append(y2)
tmp_box.append(box[-1])
merge_bbox.append(tmp_box)
return merge_bbox
#---------------------------------------------------#
# 获得类
#---------------------------------------------------#
def get_classes(classes_path):
with open(classes_path, encoding='utf-8') as f:
class_names = f.readlines()
class_names = [c.strip() for c in class_names]
return class_names, len(class_names)
#---------------------------------------------------#
# 获得先验框
#---------------------------------------------------#
def get_anchors(anchors_path):
'''loads the anchors from a file'''
with open(anchors_path, encoding='utf-8') as f:
anchors = f.readline()
anchors = [float(x) for x in anchors.split(',')]
anchors = np.array(anchors).reshape(-1, 2)
return anchors, len(anchors)
#---------------------------------------------------#
# 获得学习率
#---------------------------------------------------#
def get_lr(optimizer):
for param_group in optimizer.param_groups:
return param_group['lr']
def preprocess_input(image):
image /= 255.0
return image
\ No newline at end of file
utils/utils_bbox.py 0 → 100644
浏览文件 @ 34d2e3e1
import torch
import torch.nn as nn
from torchvision.ops import nms
import numpy as np
class DecodeBox():
def __init__(self, anchors, num_classes, input_shape, anchors_mask = [[6,7,8], [3,4,5], [0,1,2]]):
super(DecodeBox, self).__init__()
self.anchors = anchors
self.num_classes = num_classes
self.bbox_attrs = 5 + num_classes
self.input_shape = input_shape
#-----------------------------------------------------------#
# 13x13的特征层对应的anchor是[142, 110],[192, 243],[459, 401]
# 26x26的特征层对应的anchor是[36, 75],[76, 55],[72, 146]
# 52x52的特征层对应的anchor是[12, 16],[19, 36],[40, 28]
#-----------------------------------------------------------#
self.anchors_mask = anchors_mask
def decode_box(self, inputs):
outputs = []
for i, input in enumerate(inputs):
#-----------------------------------------------#
# 输入的input一共有三个，他们的shape分别是
# batch_size, 255, 13, 13
# batch_size, 255, 26, 26
# batch_size, 255, 52, 52
#-----------------------------------------------#
batch_size = input.size(0)
input_height = input.size(2)
input_width = input.size(3)
#-----------------------------------------------#
# 输入为416x416时
# stride_h = stride_w = 32、16、8
#-----------------------------------------------#
stride_h = self.input_shape[0] / input_height
stride_w = self.input_shape[1] / input_width
#-------------------------------------------------#
# 此时获得的scaled_anchors大小是相对于特征层的
#-------------------------------------------------#
scaled_anchors = [(anchor_width / stride_w, anchor_height / stride_h) for anchor_width, anchor_height in self.anchors[self.anchors_mask[i]]]
#-----------------------------------------------#
# 输入的input一共有三个，他们的shape分别是
# batch_size, 3, 13, 13, 85
# batch_size, 3, 26, 26, 85
# batch_size, 3, 52, 52, 85
#-----------------------------------------------#
prediction = input.view(batch_size, len(self.anchors_mask[i]),
self.bbox_attrs, input_height, input_width).permute(0, 1, 3, 4, 2).contiguous()
#-----------------------------------------------#
# 先验框的中心位置的调整参数
#-----------------------------------------------#
x = torch.sigmoid(prediction[..., 0])
y = torch.sigmoid(prediction[..., 1])
#-----------------------------------------------#
# 先验框的宽高调整参数
#-----------------------------------------------#
w = prediction[..., 2]
h = prediction[..., 3]
#-----------------------------------------------#
# 获得置信度，是否有物体
#-----------------------------------------------#
conf = torch.sigmoid(prediction[..., 4])
#-----------------------------------------------#
# 种类置信度
#-----------------------------------------------#
pred_cls = torch.sigmoid(prediction[..., 5:])
FloatTensor = torch.cuda.FloatTensor if x.is_cuda else torch.FloatTensor
LongTensor = torch.cuda.LongTensor if x.is_cuda else torch.LongTensor
#----------------------------------------------------------#
# 生成网格，先验框中心，网格左上角
# batch_size,3,13,13
#----------------------------------------------------------#
grid_x = torch.linspace(0, input_width - 1, input_width).repeat(input_height, 1).repeat(
batch_size * len(self.anchors_mask[i]), 1, 1).view(x.shape).type(FloatTensor)
grid_y = torch.linspace(0, input_height - 1, input_height).repeat(input_width, 1).t().repeat(
batch_size * len(self.anchors_mask[i]), 1, 1).view(y.shape).type(FloatTensor)
#----------------------------------------------------------#
# 按照网格格式生成先验框的宽高
# batch_size,3,13,13
#----------------------------------------------------------#
anchor_w = FloatTensor(scaled_anchors).index_select(1, LongTensor([0]))
anchor_h = FloatTensor(scaled_anchors).index_select(1, LongTensor([1]))
anchor_w = anchor_w.repeat(batch_size, 1).repeat(1, 1, input_height * input_width).view(w.shape)
anchor_h = anchor_h.repeat(batch_size, 1).repeat(1, 1, input_height * input_width).view(h.shape)
#----------------------------------------------------------#
# 利用预测结果对先验框进行调整
# 首先调整先验框的中心，从先验框中心向右下角偏移
# 再调整先验框的宽高。
#----------------------------------------------------------#
pred_boxes = FloatTensor(prediction[..., :4].shape)
pred_boxes[..., 0] = x.data + grid_x
pred_boxes[..., 1] = y.data + grid_y
pred_boxes[..., 2] = torch.exp(w.data) * anchor_w
pred_boxes[..., 3] = torch.exp(h.data) * anchor_h
#----------------------------------------------------------#
# 将输出结果归一化成小数的形式
#----------------------------------------------------------#
_scale = torch.Tensor([input_width, input_height, input_width, input_height]).type(FloatTensor)
output = torch.cat((pred_boxes.view(batch_size, -1, 4) / _scale,
conf.view(batch_size, -1, 1), pred_cls.view(batch_size, -1, self.num_classes)), -1)
outputs.append(output.data)
return outputs
def yolo_correct_boxes(self, box_xy, box_wh, input_shape, image_shape, letterbox_image):
#-----------------------------------------------------------------#
# 把y轴放前面是因为方便预测框和图像的宽高进行相乘
#-----------------------------------------------------------------#
box_yx = box_xy[..., ::-1]
box_hw = box_wh[..., ::-1]
input_shape = np.array(input_shape)
image_shape = np.array(image_shape)
if letterbox_image:
#-----------------------------------------------------------------#
# 这里求出来的offset是图像有效区域相对于图像左上角的偏移情况
# new_shape指的是宽高缩放情况
#-----------------------------------------------------------------#
new_shape = np.round(image_shape * np.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 = np.concatenate([box_mins[..., 0:1], box_mins[..., 1:2], box_maxes[..., 0:1], box_maxes[..., 1:2]], axis=-1)
boxes *= np.concatenate([image_shape, image_shape], axis=-1)
return boxes
def non_max_suppression(self, prediction, num_classes, input_shape, image_shape, letterbox_image, conf_thres=0.5, nms_thres=0.4):
#----------------------------------------------------------#
# 将预测结果的格式转换成左上角右下角的格式。
# prediction [batch_size, num_anchors, 85]
#----------------------------------------------------------#
box_corner = prediction.new(prediction.shape)
box_corner[:, :, 0] = prediction[:, :, 0] - prediction[:, :, 2] / 2
box_corner[:, :, 1] = prediction[:, :, 1] - prediction[:, :, 3] / 2
box_corner[:, :, 2] = prediction[:, :, 0] + prediction[:, :, 2] / 2
box_corner[:, :, 3] = prediction[:, :, 1] + prediction[:, :, 3] / 2
prediction[:, :, :4] = box_corner[:, :, :4]
output = [None for _ in range(len(prediction))]
for i, image_pred in enumerate(prediction):
#----------------------------------------------------------#
# 对种类预测部分取max。
# class_conf [num_anchors, 1] 种类置信度
# class_pred [num_anchors, 1] 种类
#----------------------------------------------------------#
class_conf, class_pred = torch.max(image_pred[:, 5:5 + num_classes], 1, keepdim=True)
#----------------------------------------------------------#
# 利用置信度进行第一轮筛选
#----------------------------------------------------------#
conf_mask = (image_pred[:, 4] * class_conf[:, 0] >= conf_thres).squeeze()
#----------------------------------------------------------#
# 根据置信度进行预测结果的筛选
#----------------------------------------------------------#
image_pred = image_pred[conf_mask]
class_conf = class_conf[conf_mask]
class_pred = class_pred[conf_mask]
if not image_pred.size(0):
continue
#-------------------------------------------------------------------------#
# detections [num_anchors, 7]
# 7的内容为：x1, y1, x2, y2, obj_conf, class_conf, class_pred
#-------------------------------------------------------------------------#
detections = torch.cat((image_pred[:, :5], class_conf.float(), class_pred.float()), 1)
#------------------------------------------#
# 获得预测结果中包含的所有种类
#------------------------------------------#
unique_labels = detections[:, -1].cpu().unique()
if prediction.is_cuda:
unique_labels = unique_labels.cuda()
detections = detections.cuda()
for c in unique_labels:
#------------------------------------------#
# 获得某一类得分筛选后全部的预测结果
#------------------------------------------#
detections_class = detections[detections[:, -1] == c]
#------------------------------------------#
# 使用官方自带的非极大抑制会速度更快一些！
#------------------------------------------#
keep = nms(
detections_class[:, :4],
detections_class[:, 4] * detections_class[:, 5],
nms_thres
)
max_detections = detections_class[keep]
# # 按照存在物体的置信度排序
# _, conf_sort_index = torch.sort(detections_class[:, 4]*detections_class[:, 5], descending=True)
# detections_class = detections_class[conf_sort_index]
# # 进行非极大抑制
# max_detections = []
# while detections_class.size(0):
# # 取出这一类置信度最高的，一步一步往下判断，判断重合程度是否大于nms_thres，如果是则去除掉
# max_detections.append(detections_class[0].unsqueeze(0))
# if len(detections_class) == 1:
# break
# ious = bbox_iou(max_detections[-1], detections_class[1:])
# detections_class = detections_class[1:][ious < nms_thres]
# # 堆叠
# max_detections = torch.cat(max_detections).data
# Add max detections to outputs
output[i] = max_detections if output[i] is None else torch.cat((output[i], max_detections))
if output[i] is not None:
output[i] = output[i].cpu().numpy()
box_xy, box_wh = (output[i][:, 0:2] + output[i][:, 2:4])/2, output[i][:, 2:4] - output[i][:, 0:2]
output[i][:, :4] = self.yolo_correct_boxes(box_xy, box_wh, input_shape, image_shape, letterbox_image)
return output
utils/utils_fit.py 0 → 100644
浏览文件 @ 34d2e3e1
import torch
from tqdm import tqdm
from utils.utils import get_lr
def fit_one_epoch(model_train, model, yolo_loss, loss_history, optimizer, epoch, epoch_step, epoch_step_val, gen, gen_val, Epoch, cuda):
loss = 0
val_loss = 0
model_train.train()
print('Start Train')
with tqdm(total=epoch_step,desc=f'Epoch {epoch + 1}/{Epoch}',postfix=dict,mininterval=0.3) as pbar:
for iteration, batch in enumerate(gen):
if iteration >= epoch_step:
break
images, targets = batch[0], batch[1]
with torch.no_grad():
if cuda:
images = torch.from_numpy(images).type(torch.FloatTensor).cuda()
targets = [torch.from_numpy(ann).type(torch.FloatTensor).cuda() for ann in targets]
else:
images = torch.from_numpy(images).type(torch.FloatTensor)
targets = [torch.from_numpy(ann).type(torch.FloatTensor) for ann in targets]
#----------------------#
# 清零梯度
#----------------------#
optimizer.zero_grad()
#----------------------#
# 前向传播
#----------------------#
outputs = model_train(images)
loss_value_all = 0
num_pos_all = 0
#----------------------#
# 计算损失
#----------------------#
for l in range(len(outputs)):
loss_item, num_pos = yolo_loss(l, outputs[l], targets)
loss_value_all += loss_item
num_pos_all += num_pos
loss_value = loss_value_all / num_pos_all
#----------------------#
# 反向传播
#----------------------#
loss_value.backward()
optimizer.step()
loss += loss_value.item()
pbar.set_postfix(**{'loss' : loss / (iteration + 1),
'lr' : get_lr(optimizer)})
pbar.update(1)
print('Finish Train')
model_train.eval()
print('Start Validation')
with tqdm(total=epoch_step_val, desc=f'Epoch {epoch + 1}/{Epoch}',postfix=dict,mininterval=0.3) as pbar:
for iteration, batch in enumerate(gen_val):
if iteration >= epoch_step_val:
break
images, targets = batch[0], batch[1]
with torch.no_grad():
if cuda:
images = torch.from_numpy(images).type(torch.FloatTensor).cuda()
targets = [torch.from_numpy(ann).type(torch.FloatTensor).cuda() for ann in targets]
else:
images = torch.from_numpy(images).type(torch.FloatTensor)
targets = [torch.from_numpy(ann).type(torch.FloatTensor) for ann in targets]
#----------------------#
# 清零梯度
#----------------------#
optimizer.zero_grad()
#----------------------#
# 前向传播
#----------------------#
outputs = model_train(images)
loss_value_all = 0
num_pos_all = 0
#----------------------#
# 计算损失
#----------------------#
for l in range(len(outputs)):
loss_item, num_pos = yolo_loss(l, outputs[l], targets)
loss_value_all += loss_item
num_pos_all += num_pos
loss_value = loss_value_all / num_pos_all
val_loss += loss_value.item()
pbar.set_postfix(**{'val_loss': val_loss / (iteration + 1)})
pbar.update(1)
print('Finish Validation')
loss_history.append_loss(loss / epoch_step, val_loss / epoch_step_val)
print('Epoch:'+ str(epoch+1) + '/' + str(Epoch))
print('Total Loss: %.3f || Val Loss: %.3f ' % (loss / epoch_step, val_loss / epoch_step_val))
torch.save(model.state_dict(), 'logs/ep%03d-loss%.3f-val_loss%.3f.pth' % (epoch + 1, loss / epoch_step, val_loss / epoch_step_val))
utils/utils_map.py 0 → 100644
浏览文件 @ 34d2e3e1
此差异已折叠。
voc_annotation.py
浏览文件 @ 34d2e3e1
#---------------------------------------------#
# 运行前一定要修改classes
import os
import random
import xml.etree.ElementTree as ET
from utils.utils import get_classes
#--------------------------------------------------------------------------------------------------------------------------------#
# annotation_mode用于指定该文件运行时计算的内容
# annotation_mode为0代表整个标签处理过程，包括获得VOCdevkit/VOC2007/ImageSets里面的txt以及训练用的2007_train.txt、2007_val.txt
# annotation_mode为1代表获得VOCdevkit/VOC2007/ImageSets里面的txt
# annotation_mode为2代表获得训练用的2007_train.txt、2007_val.txt
#--------------------------------------------------------------------------------------------------------------------------------#
annotation_mode = 0
#-------------------------------------------------------------------#
# 必须要修改，用于生成2007_train.txt、2007_val.txt的目标信息
# 与训练和预测所用的classes_path一致即可
# 如果生成的2007_train.txt里面没有目标信息
# 那么就是因为classes没有设定正确
#---------------------------------------------#
import xml.etree.ElementTree as ET
from os import getcwd
# 仅在annotation_mode为0和2的时候有效
#-------------------------------------------------------------------#
classes_path = 'model_data/voc_classes.txt'
#--------------------------------------------------------------------------------------------------------------------------------#
# trainval_percent用于指定(训练集+验证集)与测试集的比例，默认情况下 (训练集+验证集):测试集 = 9:1
# train_percent用于指定(训练集+验证集)中训练集与验证集的比例，默认情况下 训练集:验证集 = 9:1
# 仅在annotation_mode为0和1的时候有效
#--------------------------------------------------------------------------------------------------------------------------------#
trainval_percent = 0.9
train_percent = 0.9
#-------------------------------------------------------#
# 指向VOC数据集所在的文件夹
# 默认指向根目录下的VOC数据集
#-------------------------------------------------------#
VOCdevkit_path = 'VOCdevkit'
sets=[('2007', 'train'), ('2007', 'val'), ('2007', 'test')]
#-----------------------------------------------------#
# 这里设定的classes顺序要和model_data里的txt一样
#-----------------------------------------------------#
classes = ["aeroplane", "bicycle", "bird", "boat", "bottle", "bus", "car", "cat", "chair", "cow", "diningtable", "dog", "horse", "motorbike", "person", "pottedplant", "sheep", "sofa", "train", "tvmonitor"]
VOCdevkit_sets = [('2007', 'train'), ('2007', 'val')]
classes, _ = get_classes(classes_path)
def convert_annotation(year, image_id, list_file):
in_file = open('VOCdevkit/VOC%s/Annotations/%s.xml'%(year, image_id), encoding='utf-8')
in_file = open(os.path.join(VOCdevkit_path, 'VOC%s/Annotations/%s.xml'%(year, image_id)), encoding='utf-8')
tree=ET.parse(in_file)
root = tree.getroot()
......@@ -28,14 +51,59 @@ def convert_annotation(year, image_id, list_file):
xmlbox = obj.find('bndbox')
b = (int(float(xmlbox.find('xmin').text)), int(float(xmlbox.find('ymin').text)), int(float(xmlbox.find('xmax').text)), int(float(xmlbox.find('ymax').text)))
list_file.write(" " + ",".join([str(a) for a in b]) + ',' + str(cls_id))
if __name__ == "__main__":
random.seed(0)
if annotation_mode == 0 or annotation_mode == 1:
print("Generate txt in ImageSets.")
xmlfilepath = os.path.join(VOCdevkit_path, 'VOC2007/Annotations')
saveBasePath = os.path.join(VOCdevkit_path, 'VOC2007/ImageSets/Main')
temp_xml = os.listdir(xmlfilepath)
total_xml = []
for xml in temp_xml:
if xml.endswith(".xml"):
total_xml.append(xml)
num = len(total_xml)
list = range(num)
tv = int(num*trainval_percent)
tr = int(tv*train_percent)
trainval= random.sample(list,tv)
train = random.sample(trainval,tr)
print("train and val size",tv)
print("train size",tr)
ftrainval = open(os.path.join(saveBasePath,'trainval.txt'), 'w')
ftest = open(os.path.join(saveBasePath,'test.txt'), 'w')
ftrain = open(os.path.join(saveBasePath,'train.txt'), 'w')
fval = open(os.path.join(saveBasePath,'val.txt'), 'w')
for i in list:
name=total_xml[i][:-4]+'\n'
if i in trainval:
ftrainval.write(name)
if i in train:
ftrain.write(name)
else:
fval.write(name)
else:
ftest.write(name)
ftrainval.close()
ftrain.close()
fval.close()
ftest.close()
print("Generate txt in ImageSets done.")
wd = getcwd()
if annotation_mode == 0 or annotation_mode == 2:
print("Generate 2007_train.txt and 2007_val.txt for train.")
for year, image_set in VOCdevkit_sets:
image_ids = open(os.path.join(VOCdevkit_path, 'VOC%s/ImageSets/Main/%s.txt'%(year, image_set)), encoding='utf-8').read().strip().split()
list_file = open('%s_%s.txt'%(year, image_set), 'w', encoding='utf-8')
for image_id in image_ids:
list_file.write('%s/VOC%s/JPEGImages/%s.jpg'%(os.path.abspath(VOCdevkit_path), year, image_id))
for year, image_set in sets:
image_ids = open('VOCdevkit/VOC%s/ImageSets/Main/%s.txt'%(year, image_set), encoding='utf-8').read().strip().split()
list_file = open('%s_%s.txt'%(year, image_set), 'w', encoding='utf-8')
for image_id in image_ids:
list_file.write('%s/VOCdevkit/VOC%s/JPEGImages/%s.jpg'%(wd, year, image_id))
convert_annotation(year, image_id, list_file)
list_file.write('\n')
list_file.close()
convert_annotation(year, image_id, list_file)
list_file.write('\n')
list_file.close()
print("Generate 2007_train.txt and 2007_val.txt for train done.")
yolo.py
浏览文件 @ 34d2e3e1
此差异已折叠。
Markdown is supported
0% 或 .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑！
想要评论请 注册 或