Comments (4)
""" Full assembly of the parts to form the complete network """
import torch.nn.functional as F
# from model.unet_parts import *
from unet_parts import *
class UNet(nn.Module):
def __init__(self, n_channels, n_classes, bilinear=True):
super(UNet, self).__init__()
self.n_channels = n_channels
self.n_classes = n_classes
self.bilinear = bilinear
self.inc = DoubleConv(n_channels, 64)
self.down1 = Down(64, 128)
self.down2 = Down(128, 256)
self.down3 = Down(256, 512)
factor = 2 if bilinear else 1
self.down4 = Down(512, 1024 // factor)
self.up1 = Up(1024, 512 // factor, bilinear)
self.up2 = Up(512, 256 // factor, bilinear)
self.up3 = Up(256, 128 // factor, bilinear)
self.up4 = Up(128, 64, bilinear)
self.outc = OutConv(64, n_classes)
def forward(self, x):
x1 = self.inc(x)
x2 = self.down1(x1)
x3 = self.down2(x2)
x4 = self.down3(x3)
x5 = self.down4(x4)
x = self.up1(x5, x4)
x = self.up2(x, x3)
x = self.up3(x, x2)
x = self.up4(x, x1)
logits = self.outc(x)
# logits = torch.sigmoid(logits)
return logits
if __name__ == '__main__':
net = UNet(3,2,True)
net = net.cuda()
image = torch.Tensor(32,3,32,128).cuda()
result = net(image)
print(result.shape)
'''
from fudanocr.
""" Parts of the U-Net model """
import torch
import torch.nn as nn
import torch.nn.functional as F
class DoubleConv(nn.Module):
"""(convolution => [BN] => ReLU) * 2"""
def __init__(self, in_channels, out_channels, mid_channels=None):
super().__init__()
if not mid_channels:
mid_channels = out_channels
self.double_conv = nn.Sequential(
nn.Conv2d(in_channels, mid_channels, kernel_size=3, padding=1),
nn.BatchNorm2d(mid_channels),
nn.ReLU(inplace=True),
nn.Conv2d(mid_channels, out_channels, kernel_size=3, padding=1),
nn.BatchNorm2d(out_channels),
nn.ReLU(inplace=True)
)
def forward(self, x):
return self.double_conv(x)
class Down(nn.Module):
"""Downscaling with maxpool then double conv"""
def __init__(self, in_channels, out_channels):
super().__init__()
self.maxpool_conv = nn.Sequential(
nn.MaxPool2d(2),
DoubleConv(in_channels, out_channels)
)
def forward(self, x):
return self.maxpool_conv(x)
class Up(nn.Module):
"""Upscaling then double conv"""
def __init__(self, in_channels, out_channels, bilinear=True):
super().__init__()
# if bilinear, use the normal convolutions to reduce the number of channels
if bilinear:
self.up = nn.Upsample(scale_factor=2, mode='bilinear', align_corners=True)
self.conv = DoubleConv(in_channels, out_channels, in_channels // 2)
else:
self.up = nn.ConvTranspose2d(in_channels , in_channels // 2, kernel_size=2, stride=2)
self.conv = DoubleConv(in_channels, out_channels)
def forward(self, x1, x2):
x1 = self.up(x1)
# input is CHW
diffY = x2.size()[2] - x1.size()[2]
diffX = x2.size()[3] - x1.size()[3]
x1 = F.pad(x1, [diffX // 2, diffX - diffX // 2,
diffY // 2, diffY - diffY // 2])
x = torch.cat([x2, x1], dim=1)
return self.conv(x)
class OutConv(nn.Module):
def __init__(self, in_channels, out_channels):
super(OutConv, self).__init__()
self.conv = nn.Conv2d(in_channels, out_channels, kernel_size=1)
def forward(self, x):
return self.conv(x)
'''
from fudanocr.
sorry for the late update.
hope this code could help you :D
from fudanocr.
抱歉更新晚了。 希望这段代码可以帮助你 :D
请问能够提供这段代码的训练集或者是已经训练完成的网络吗,我想通过这个网络来实现文字在小区域内的精准定位,看到这个论文中你们用来计算loss的方法刚好合适,如果可以不胜感激
from fudanocr.
Related Issues (20)
- Question about CLIP-like pre-training in image-ids-CTR HOT 1
- train.py在计算loss有个小错误 HOT 1
- 关于CCR-CLIP HOT 1
- 数据集请求 HOT 2
- 请问text-focused-Transformers model和datasets如何下载 HOT 1
- VCTR dataset read error
- 请问在竖直文本识别那篇论文中,有没有提供预训练模型呢 HOT 2
- How to download VCTR dataset? HOT 2
- How to extract only image after super resolution?
- CCR-CLIP pretraining HOT 2
- About CCR-CLIP pretrained HOT 1
- inference of orientation-independent-CTR ?
- CCR-CLIP使用印刷字体进行增强 HOT 1
- Fix link for Baidu download in text-focused-Transformers/
- train.py的坑:容易误删已训练模型 HOT 2
- lmdb can not find my file. HOT 2
- 关于Chinese-CLIP复现中的几点疑惑,期待答复!
- Question about CCR-CLIP experiment and code HOT 4
- 字典里面的字符是不是不够啊?除了没有逗号,有时候会出现字典里没有这个汉字。 HOT 4
- 是否有HWDB 1.0-1.2 的lmdb数据集 HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from fudanocr.