Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Merge pull request #475 from IshanG97/download-data-bat-script #509

Open
wants to merge 1 commit into
base: master
Choose a base branch
from
Open

Merge pull request #475 from IshanG97/download-data-bat-script #509

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
97 changes: 97 additions & 0 deletions new_unet/net.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,97 @@
import torch
from torch import nn
from torch.nn import functional as F


# 卷积类
class Conv_Block(nn.Module):

def __init__(self, in_channels, out_channels):
super(Conv_Block, self).__init__()
self.layer = nn.Sequential(
nn.Conv2d(in_channels, out_channels, kernel_size=3,stride=1, padding=1,padding_mode='reflect',bias=False),
nn.BatchNorm2d(out_channels),
nn.Dropout(0.3),
nn.LeakyReLU(),
# 第一个卷积
nn.Conv2d(out_channels, out_channels, kernel_size=3, stride=1, padding=1, padding_mode='reflect',
bias=False),
nn.BatchNorm2d(out_channels),
nn.Dropout(0.3),
nn.LeakyReLU(),
# 第二个卷积同理
)
def forward(self, x):
return self.layer(x)


#下采样类
class DownSample(nn.Module):
def __init__(self, channel):
super(DownSample, self).__init__()
# 序列构造器
self.layer = nn.Sequential(
nn.Conv2d(channel, channel, kernel_size=3, stride=2, padding=1, padding_mode='reflect', bias=False),
nn.BatchNorm2d(channel),#可以用也可以不用
nn.LeakyReLU()
)

def forward(self, x):
return self.layer(x)


#上采样 得到特征图，和同层的下采样图进行拼接，然后再进行卷积
class UpSample(nn.Module):
def __init__(self,channel):
super(UpSample, self).__init__()
#转置卷积与插值法
#用1+1的卷积降通道
self.layer = nn.Conv2d(channel, channel//2, kernel_size=1, stride=1)

def forward(self, x,feature_map): #feature_map 是同层之前下采样的特征图
up = F.interpolate(x,scale_factor=2,mode='nearest')#scale_factor=2 变成原来的2倍 插值法
out = self.layer(up)
return torch.cat([out,feature_map],dim=1) #n c h w 0 1 2 3


class UNet(nn.Module):
def __init__(self):
super(UNet, self).__init__()
self.c1=Conv_Block(3, 64)
self.d1=DownSample(64)
self.c2=Conv_Block(64, 128)
self.d2=DownSample(128)
self.c3=Conv_Block(128, 256)
self.d3=DownSample(256)
self.c4=Conv_Block(256, 512)
self.d4=DownSample(512)
self.c5=Conv_Block(512, 1024)
self.u1=UpSample(1024)
self.c6=Conv_Block(1024, 512)
self.u2=UpSample(512)
self.c7=Conv_Block(512, 256)
self.u3=UpSample(256)
self.c8=Conv_Block(256, 128)
self.u4=UpSample(128)
self.c9=Conv_Block(128, 64)
self.out=nn.Conv2d(64, 3,kernel_size=1, stride=1, padding=1)
self.Th=nn.Sigmoid()#激活函数，虽然是彩色图像，只需要对图像进行二分类即可，也就是讲一个像素点分为黑色或白色

def forward(self, x):
R1=self.c1(x)
R2=self.c2(self.d1(R1))#先对R1进行下采样，然后再进行第二次的一个卷积
R3=self.c3(self.d2(R2))
R4=self.c4(self.d3(R3))
R5=self.c5(self.d4(R4))
O1=self.c6(self.u1(R5,R4)) #先将R5上采样，并且和R4进行拼接，然后再进行卷积
O2=self.c7(self.u2(O1,R3))
O3=self.c8(self.u3(O2,R2))
O4=self.c9(self.u4(O3,R1))

return self.Th(self.out(O4))

#测试，输出模型的形状，看看和我们设计的样子是否一样
if __name__ == '__main__':
x = torch.randn(2, 3, 256, 256)
net = UNet()
print(net(x).shape)
28 changes: 28 additions & 0 deletions scripts/download_data.bat
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,28 @@
@echo off
setlocal enabledelayedexpansion

if not exist "%userprofile%\.kaggle\kaggle.json" (
set /p USERNAME=Kaggle username:
echo.
set /p APIKEY=Kaggle API key:

mkdir "%userprofile%\.kaggle"
echo {"username":"!USERNAME!","key":"!APIKEY!"} > "%userprofile%\.kaggle\kaggle.json"
attrib +R "%userprofile%\.kaggle\kaggle.json"
)

pip install kaggle --upgrade

kaggle competitions download -c carvana-image-masking-challenge -f train_hq.zip
powershell Expand-Archive train_hq.zip -DestinationPath data\imgs
move data\imgs\train_hq\* data\imgs\
rmdir /s /q data\imgs\train_hq
del /q train_hq.zip

kaggle competitions download -c carvana-image-masking-challenge -f train_masks.zip
powershell Expand-Archive train_masks.zip -DestinationPath data\masks
move data\masks\train_masks\* data\masks\
rmdir /s /q data\masks\train_masks
del /q train_masks.zip

exit /b 0
9 changes: 6 additions & 3 deletions train.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -19,8 +19,11 @@
from utils.data_loading import BasicDataset, CarvanaDataset
from utils.dice_score import dice_loss

dir_img = Path('./data/imgs/')
dir_mask = Path('./data/masks/')
# dir_img = Path('./data/imgs/')
# dir_mask = Path('./data/masks/')
#注释掉原来的地址
dir_img = Path('../Dataset/TrainDataset/Image/')
dir_mask = Path('../Dataset/TrainDataset/GT/')
dir_checkpoint = Path('./checkpoints/')


Expand All @@ -33,7 +36,7 @@ def train_model(
val_percent: float = 0.1,
save_checkpoint: bool = True,
img_scale: float = 0.5,
amp: bool = False,
amp: bool = True,
weight_decay: float = 1e-8,
momentum: float = 0.999,
gradient_clipping: float = 1.0,
Expand Down
117 changes: 112 additions & 5 deletions utils/data_loading.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -12,9 +12,20 @@
from torch.utils.data import Dataset
from tqdm import tqdm

def keep_image_size_open(path, size=(256, 256)):
img = Image.open(path)
temp = max(img.size)
mask = Image.new('RGB',(temp, temp), (0, 0, 0))
mask.paste(img, (0, 0))
mask = mask.resize(size)
return mask


def load_image(filename):
ext = splitext(filename)[1]

# splitext(filename)是os.path模块中的函数，用于将文件名分离成文件名和扩展名两个部分。
# splitext(filename)[1]提取扩展名部分，比如.jpg、.png、.npy等。这里的ext变量将保存这个扩展名。
if ext == '.npy':
return Image.fromarray(np.load(filename))
elif ext in ['.pt', '.pth']:
Expand All @@ -24,14 +35,47 @@ def load_image(filename):


def unique_mask_values(idx, mask_dir, mask_suffix):
mask_file = list(mask_dir.glob(idx + mask_suffix + '.*'))[0]
mask_file = list(mask_dir.glob(idx + mask_suffix + '.png'))[0]
# print(f"找到遮罩文件: {mask_file}")
# 得到mask_dir目录下 idx.png 格式的名字
#----------------修改 开始------------
# try:
# # 获取第一个匹配文件
# print(f"找到遮罩文件: {mask_file}")
# except IndexError:
# print("没有找到与模式匹配的遮罩文件。")
# ----------------修改 结束------------
mask = np.asarray(load_image(mask_file))
a = np.unique(mask)
# print(f'idx: {idx} a {a}')
# if a == [ 0 255] :
# print(f'idx: {idx} a {a}')
# else:
# print(f'-------------------idx: {idx} a {a}--------------------')

# print(f"{mask_file} np.unique(mask): {np.unique(mask)}")
# 得到像素中的不同数
if mask.ndim == 2:
# print("ndim == 2") cod10k是这个

# a = np.unique(mask)
# print(f"{mask_file} a.ndim: {a.ndim} ")
# print(f"{mask_file} np.unique(mask): {np.unique(mask)}")
# if a.ndim == 2:
# print(f'a.ndim=2*****************')
# # print(f"{mask_file} np.unique(mask): {np.unique(mask)}")
# if a.ndim>2 :
# print(f'a.ndim>2*****************')
# print(f"{mask_file} np.unique(mask): {np.unique(mask)}")
return np.unique(mask)
# return mask
elif mask.ndim == 3:
mask = mask.reshape(-1, mask.shape[-1])
print(f"{mask_file} np.unique(mask): {np.unique(mask)}")
# print("ndim == 3")
return np.unique(mask, axis=0)
else:
print(f"{mask_file} np.unique(mask): {np.unique(mask)}")
raise ValueError(f'Loaded masks should have 2 or 3 dimensions, found {mask.ndim}')


Expand All @@ -44,6 +88,7 @@ def __init__(self, images_dir: str, mask_dir: str, scale: float = 1.0, mask_suff
self.mask_suffix = mask_suffix

self.ids = [splitext(file)[0] for file in listdir(images_dir) if isfile(join(images_dir, file)) and not file.startswith('.')]
# self.ids 是照片的名称，不带文件格式的文件名。
if not self.ids:
raise RuntimeError(f'No input file found in {images_dir}, make sure you put your images there')

Expand All @@ -55,21 +100,61 @@ def __init__(self, images_dir: str, mask_dir: str, scale: float = 1.0, mask_suff
total=len(self.ids)
))


# print(f'unique[0] {unique[0]} ')
#
# print(f'self.ids[0] {self.ids[0]}')
#
# mask_file = list(mask_dir.glob(self.ids[0] + mask_suffix + '.*'))[0]
# print(f'mask_file {mask_file}')
# mask = np.asarray(load_image(mask_file))
# print(f'mask {mask}')
# np_mask = np.unique(mask)
# print(f'np_mask {np_mask}')
# aa=unique_mask_values(self.ids[0], self.mask_dir, self.mask_suffix)
# print(f'unique_mask_values aa {aa}')
# tqdm(unique_mask_values(self.ids[0], self.mask_dir, self.mask_suffix),total=1)
# unique1 = list( (tqdm(unique_mask_values(self.ids[0], self.mask_dir, self.mask_suffix),total=1) ))
# print(f'unique1 {unique1}')
# unique2 = list(unique_mask_values(self.ids[0], self.mask_dir, self.mask_suffix))
# print(f'unique1 {unique2}')
#
print(f'unique[0] {unique[0]} ')
print(f'unique[1] {unique[1]} ')
# unique_mask_values(self.ids[1], self.mask_dir, self.mask_dir)
print(f'unique[2] {unique[2]} ')
print(f'unique[3] {unique[3]} ')
# unique_mask_values(self.ids[2], self.mask_dir, self.mask_dir)
print(f'unique[4] {unique[4]} ')
print(f'unique[5] {unique[5]} ')
print(f'unique[6] {unique[6]} ')
print(f'unique[7] {unique[7]} ')
print(f'unique[8] {unique[8]} ')
# unique_mask_values(self.ids[6], self.mask_dir, self.mask_dir)
c = np.concatenate(unique)
# a = np.unique(np.concatenate(unique), axis=0).tolist()
# self.mask_values = list(sorted(a))


self.mask_values = list(sorted(np.unique(np.concatenate(unique), axis=0).tolist()))
# self.mask_values = [0,255]

logging.info(f'Unique mask values: {self.mask_values}')

def __len__(self):
return len(self.ids)

@staticmethod
def preprocess(mask_values, pil_img, scale, is_mask):
#
w, h = pil_img.size
newW, newH = int(scale * w), int(scale * h)
assert newW > 0 and newH > 0, 'Scale is too small, resized images would have no pixel'
pil_img = pil_img.resize((newW, newH), resample=Image.NEAREST if is_mask else Image.BICUBIC)
img = np.asarray(pil_img)

if is_mask:
#如果是mask图片，就生成一张大小与图像相同的空遮挡
mask = np.zeros((newH, newW), dtype=np.int64)
for i, v in enumerate(mask_values):
if img.ndim == 2:
Expand All @@ -92,12 +177,19 @@ def preprocess(mask_values, pil_img, scale, is_mask):

def __getitem__(self, idx):
name = self.ids[idx]
mask_file = list(self.mask_dir.glob(name + self.mask_suffix + '.*'))
img_file = list(self.images_dir.glob(name + '.*'))
# mask_file = list(self.mask_dir.glob(name + self.mask_suffix + '.*'))
# img_file = list(self.images_dir.glob(name + '.*'))
#将数据集图片的格式改成自己的，这里都是.jpg
#images_dir - dir_img - '../Dataset/TrainDataset/Image/'
#mask_file - dir_mask - '../Dataset/TrainDataset/GT/'
mask_file = list(self.mask_dir.glob(name + self.mask_suffix + '.png'))
#将文件路径变成list存储
img_file = list(self.images_dir.glob(name + '.jpg'))
#

assert len(img_file) == 1, f'Either no image or multiple images found for the ID {name}: {img_file}'
assert len(mask_file) == 1, f'Either no mask or multiple masks found for the ID {name}: {mask_file}'
mask = load_image(mask_file[0])
mask = load_image(mask_file[0])#取第一个文件路径并加载
img = load_image(img_file[0])

assert img.size == mask.size, \
Expand All @@ -114,4 +206,19 @@ def __getitem__(self, idx):

class CarvanaDataset(BasicDataset):
def __init__(self, images_dir, mask_dir, scale=1):
super().__init__(images_dir, mask_dir, scale, mask_suffix='_mask')
super().__init__(images_dir, mask_dir, scale, mask_suffix='')

def unique_values(idx, mask_dir):
# imgs = os.listdir(root)
imgs = list(mask_dir.glob(idx + '.png'))[0]
concat_unique = np.empty(1)
for imgpath in imgs:
img = np.asarray(Image.open(imgs))
# 得到像素中的不同数
unique = np.unique(img)
# 对其进行拼接
concat_unique = np.concatenate([concat_unique, unique])
# 对拼接后的图片进行再次求不同像素，即全部文件中不同像素数，排序后返回
return list(sorted(np.unique(concat_unique)))
# if __name__ == '__main__':