unet | deep learning framework -- Unet , using caffe | Machine Learning library

by warden3344 Python Version: Current License: No License

X-Ray Key Features Code Snippets Community Discussions(10)Vulnerabilities Install Support

kandi X-RAY | unet Summary

unet is a Python library typically used in Artificial Intelligence, Machine Learning, Deep Learning, Pytorch, Tensorflow applications. unet has no bugs, it has no vulnerabilities and it has high support. However unet build file is not available. You can download it from GitHub.

Implementation of deep learning framework -- Unet, using caffe. The architecture was inspired by U-Net: Convolutional Networks for Biomedical Image Segmentation.and the repository:which is impelement the unet by Keras. Data The original dataset is from isbi challenge, and the dataset on this repository is the same as the data in repository:How to train: 1.change the directory in the imglist.txt and the masklist.txt 2.change the directory and the path in the mydatalayer.py 3.change the path in the solver.prototxt 4.change the path in the train.sh 5.run the train.sh after serveral epochs the loss will be lower the 0.01.

Support

Quality

Security

License

Reuse

Support

unet has a highly active ecosystem.

It has 26 star(s) with 49 fork(s). There are 2 watchers for this library.

It had no major release in the last 6 months.

There are 3 open issues and 7 have been closed. On average issues are closed in 117 days. There are no pull requests.

It has a negative sentiment in the developer community.

The latest version of unet is current.

Quality

unet has 0 bugs and 0 code smells.

Security

unet has no vulnerabilities reported, and its dependent libraries have no vulnerabilities reported.

unet code analysis shows 0 unresolved vulnerabilities.

There are 0 security hotspots that need review.

License

unet does not have a standard license declared.

Check the repository for any license declaration and review the terms closely.

Without a license, all rights are reserved, and you cannot use the library in your applications.

Reuse

unet releases are not available. You will need to build from source code and install.

unet has no build file. You will be need to create the build yourself to build the component from source.

unet saves you 22 person hours of effort in developing the same functionality from scratch.

It has 62 lines of code, 6 functions and 3 files.

It has medium code complexity. Code complexity directly impacts maintainability of the code.

Top functions reviewed by kandi - BETA

kandi has reviewed unet and discovered the below as its top functions. This is intended to give you an instant insight into unet implemented functionality, and help decide if they suit your requirements.

Sets up the image
load an image
Load image mask at given index .
Generate the next input .
Reshape image to fit .

Get all kandi verified functions for this library.

unet Key Features

No Key Features are available at this moment for unet.

unet Examples and Code Snippets

No Code Snippets are available at this moment for unet.

Community Discussions

Trending Discussions on unet

How to read this modified unet?

Why does unet have classes?

Keras logits and labels must have the same first dimension, got logits shape [10240,151] and labels shape [1], sparse_categorical_crossentropy

How to plot accuracy with a trained model

Error creating model "segmentation_models" in Keras

InvalidArgumentError: required broadcastable shapes at loc(unknown)

Computer Vision: Improving Region of Interests segmentation

How to convert all images in one folder to numpy files?

Training a model on GPU is very slow

Merge multiple .npy files into single .npy file

QUESTION

How to read this modified unet?

Asked 2021-Jun-11 at 17:50

import numpy as np
import torch
import torch.nn as nn
import torch.nn.functional as F
import torchvision
from PIL import Image
import matplotlib.pyplot as plt

class Model_Down(nn.Module):
    """
    Convolutional (Downsampling) Blocks.

    nd = Number of Filters
    kd = Kernel size

    """
    def __init__(self,in_channels, nd = 128, kd = 3, padding = 1, stride = 2):
        super(Model_Down,self).__init__()
        self.padder = nn.ReflectionPad2d(padding)
        self.conv1 = nn.Conv2d(in_channels = in_channels, out_channels = nd, kernel_size = kd, stride = stride)
        self.bn1 = nn.BatchNorm2d(nd)

        self.conv2 = nn.Conv2d(in_channels = nd, out_channels = nd, kernel_size = kd, stride = 1)
        self.bn2 = nn.BatchNorm2d(nd)

        self.relu = nn.LeakyReLU()

    def forward(self, x):
        x = self.padder(x)
        x = self.conv1(x)
        x = self.bn1(x)
        x = self.relu(x)
        x = self.padder(x)
        x = self.conv2(x)
        x = self.bn2(x)
        x = self.relu(x)
        return x

...

ANSWER

Answered 2021-Jun-11 at 17:50

Here is a functional equivalent of the main Model forward(x) method. It is much more verbose, but it is "unravelling" the flow of operations, making it more easily understandable.

I assumed that the length of the list-arguments are always 5 (i is in the [0, 4] range, inclusive) so I could unpack properly (and it follows the default set of parameters).

Source https://stackoverflow.com/questions/67936380

QUESTION

Why does unet have classes?

Asked 2021-Jun-11 at 09:42

import torch
import torch.nn as nn
import torch.nn.functional as F


class double_conv(nn.Module):
    '''(conv => BN => ReLU) * 2'''
    def __init__(self, in_ch, out_ch):
        super(double_conv, self).__init__()
        self.conv = nn.Sequential(
            nn.Conv2d(in_ch, out_ch, 3, padding=1),
            nn.BatchNorm2d(out_ch),
            nn.ReLU(inplace=True),
            nn.Conv2d(out_ch, out_ch, 3, padding=1),
            nn.BatchNorm2d(out_ch),
            nn.ReLU(inplace=True)
        )

    def forward(self, x):
        x = self.conv(x)
        return x


class inconv(nn.Module):
    def __init__(self, in_ch, out_ch):
        super(inconv, self).__init__()
        self.conv = double_conv(in_ch, out_ch)

    def forward(self, x):
        x = self.conv(x)
        return x


class down(nn.Module):
    def __init__(self, in_ch, out_ch):
        super(down, self).__init__()
        self.mpconv = nn.Sequential(
            nn.MaxPool2d(2),
            double_conv(in_ch, out_ch)
        )

    def forward(self, x):
        x = self.mpconv(x)
        return x


class up(nn.Module):
    def __init__(self, in_ch, out_ch, bilinear=True):
        super(up, self).__init__()

        #  would be a nice idea if the upsampling could be learned too,
        #  but my machine do not have enough memory to handle all those weights
        if bilinear:
            self.up = nn.Upsample(scale_factor=2, mode='bilinear', align_corners=True)
        else:
            self.up = nn.ConvTranspose2d(in_ch//2, in_ch//2, 2, stride=2)

        self.conv = double_conv(in_ch, out_ch)

    def forward(self, x1, x2):
        x1 = self.up(x1)
        diffX = x1.size()[2] - x2.size()[2]
        diffY = x1.size()[3] - x2.size()[3]
        x2 = F.pad(x2, (diffX // 2, int(diffX / 2),
                        diffY // 2, int(diffY / 2)))
        x = torch.cat([x2, x1], dim=1)
        x = self.conv(x)
        return x


class outconv(nn.Module):
    def __init__(self, in_ch, out_ch):
        super(outconv, self).__init__()
        self.conv = nn.Conv2d(in_ch, out_ch, 1)

    def forward(self, x):
        x = self.conv(x)
        return x


class UNet(nn.Module):
    def __init__(self, n_channels, n_classes):
        super(UNet, self).__init__()
        self.inc = inconv(n_channels, 64)
        self.down1 = down(64, 128)
        self.down2 = down(128, 256)
        self.down3 = down(256, 512)
        self.down4 = down(512, 512)
        self.up1 = up(1024, 256)
        self.up2 = up(512, 128)
        self.up3 = up(256, 64)
        self.up4 = up(128, 64)
        self.outc = outconv(64, n_classes)

    def forward(self, x):
        self.x1 = self.inc(x)
        self.x2 = self.down1(self.x1)
        self.x3 = self.down2(self.x2)
        self.x4 = self.down3(self.x3)
        self.x5 = self.down4(self.x4)
        self.x6 = self.up1(self.x5, self.x4)
        self.x7 = self.up2(self.x6, self.x3)
        self.x8 = self.up3(self.x7, self.x2)
        self.x9 = self.up4(self.x8, self.x1)
        self.y = self.outc(self.x9)
        return self.y

...

ANSWER

Answered 2021-Jun-11 at 09:42

Answer

Does n_classes signify multiclass segmentation?

Yes, if you specify n_classes=4 it will output a (batch, 4, width, height) shaped tensor, where each pixel can be segmented as one of 4 classes. Also one should use torch.nn.CrossEntropyLoss for training.

If so, what is the output of binary UNet segmentation?

If you want to use binary segmentation you'd specify n_classes=1 (either 0 for black or 1 for white) and use torch.nn.BCEWithLogitsLoss

I am trying to use this code for image denoising and I couldn't figure out what will should the n_classes parameter be

It should be equal to n_channels, usually 3 for RGB or 1 for grayscale. If you want to teach this model to denoise an image you should:

Add some noise to the image (e.g. using torchvision.transforms)
Use sigmoid activation at the end as the pixels will have value between 0 and 1 (unless normalized)
Use torch.nn.MSELoss for training

Why sigmoid?

Because [0,255] pixel range is represented as [0, 1] pixel value (without normalization at least). sigmoid does exactly that - squashes value into [0, 1] range, hence linear outputs (logits) can have a range from -inf to +inf.

Why not a linear output and a clamp?

In order for the Linear layer to be in [0, 1] range after clamp possible output values from Linear would have to be greater than 0 (logits range to fit the target: [0, +inf])

Why not a linear output without a clamp?

Logits outputted would have to be within [0, 1] range

Why not some other method?

You could do that, but the idea of sigmoid is:

help neural network (any logit value can be outputted)
first derivative of sigmoid is gaussian standard normal, hence it models the probability of many real-life occurring phenomena (see also here for more)

Source https://stackoverflow.com/questions/67932624

QUESTION

Keras logits and labels must have the same first dimension, got logits shape [10240,151] and labels shape [1], sparse_categorical_crossentropy

Asked 2021-Jun-10 at 13:36

I'm trying to create a Unet for semantic segmentation.. I've been following this repo that has the code from this article. I'm using the scene parsing 150 dataset instead of the one used in the article. My data is not one-hot encoded so I'm trying to use sparse_categorical_crossentropy for loss.

This is the shape of my data. x is RGB images, y is 1 channel annotations of categories (151 categories). Yes, I'm using just 10 samples of each, just for testing, this will be changed when I can actually get it to start training.

...

ANSWER

Answered 2021-Jun-10 at 13:36

As per Dominik Ficek's comment

Source https://stackoverflow.com/questions/67919303

QUESTION

How to plot accuracy with a trained model

Asked 2021-May-31 at 18:59

I have a Tensorflow model already trained in my notebook, and I want to plot accuracy and loss after that.

Here is my code:

...

ANSWER

Answered 2021-May-31 at 18:58

Try this:

Source https://stackoverflow.com/questions/67773921

QUESTION

Error creating model "segmentation_models" in Keras

Asked 2021-May-29 at 23:13

A week ago, my Notebook in Google Colaboratory was working fine after installing the following libraries:

...

ANSWER

Answered 2021-May-29 at 23:13

You may need to install h5py of the following version, source.

Source https://stackoverflow.com/questions/67756332

QUESTION

InvalidArgumentError: required broadcastable shapes at loc(unknown)

Asked 2021-May-29 at 09:07

Background

I am totally new to Python and to machine learning. I just tried to set up a UNet from code I found on the internet and wanted to adapt it to the case I'm working on bit for bit. When trying to .fit the UNet to the training data, I received the following error:

...

ANSWER

Answered 2021-May-29 at 08:40

Try to check whether ks.layers.concatenate layers' inputs are of equal dimension. For example ks.layers.concatenate([u7, c3]), here check u7 and c3 tensors are of same shape to be concatenated except the axis input to the function ks.layers.concatenate. Axis = -1 default, that's the last dimension. To illustrate if you are giving ks.layers.concatenate([u7,c3],axis=0), then except the first axis of both u7 and c3 all other axes' dimension should match exactly, example, u7.shape = [3,4,5], c3.shape = [6,4,5].

Source https://stackoverflow.com/questions/67557515

QUESTION

Computer Vision: Improving Region of Interests segmentation

Asked 2021-May-14 at 23:42

I'm running a unet model on x-ray for lung region segmentation, the model seems to work well, but my dataset is not that good looking, I'm obtaining results with some missing parts as in here:

My question is: is there any cv operator I can preform to smoothen it a little more to obtain something like this:

Thanks.

...

ANSWER

Answered 2021-May-14 at 23:42

What you describe can be implemented via morphology. Morphological operations are a set of (logical) operations that affect the overall shape of the image. It can "expand" or "reduce" shape regions, among many other cool operations.

Let's use a dilation to expand your image's shape:

Source https://stackoverflow.com/questions/67541938

QUESTION

How to convert all images in one folder to numpy files?

Asked 2021-May-01 at 19:23

I need to do Semantic image segmentation based on Unet.

I have to work with Pascal VOC 2012 dataset, however I don't know how to do it, do I manually select images for the train & val and convert them into numpy and then load them into the model? Or is there another way?

If this is the first one I would like to know how to convert all the images present in a folder into .npy.

...

ANSWER

Answered 2021-May-01 at 00:09

if i understood correctly, you just need to go through all the files from the folder and add them to the numpy table?

Source https://stackoverflow.com/questions/67341689

QUESTION

Training a model on GPU is very slow

Asked 2021-May-01 at 17:35

I am using A100-SXM4-40GB Gpu but training is terribly slow. I tried two models, a simple classification on cifar and a Unet on Cityscapes. I tried my code on other GPUs and it worked totally fine, but I do not know why training on this high capacity GPU is super slow.

I would appreciate any help.

Here are some other properties of GPUs.

...

ANSWER

Answered 2021-May-01 at 13:39

Call .cuda() on the model during initialization.

As per your above comments, you have GPUs, as well as CUDA installed, so there's no point of checking the device availability with torch.cuda.is_available().

Additionally, you should wrap your model in nn.DataParallel to allow PyTorch use every GPU you expose it to. You also could do DistributedDataParallel, but DataParallel is easier to grasp initially.

Example initialization:

Source https://stackoverflow.com/questions/67346102

QUESTION

Merge multiple .npy files into single .npy file

Asked 2021-Apr-30 at 13:27

I have a folder in which I have 100+ .npy files. The path to this folder is '/content/drive/MyDrive/lung_cancer/subset0/trainImages'.

This folder has the .npy files as shown in the image the .npy files

The shape of each of these .npy files is (3,512,512)

I want to combine all of these files into one single file with the name trainImages.npy so that I can train my unet model with it.

My unet model takes input of the shape (1,512,512). I will load the above trainImages.npy file into imgs_train as below to pass it as input into unet model

imgs_train = np.load(working_path+"trainImages.npy").astype(np.float32)

Can someone please tell me how do i concatenate all those .npy files into one single .npy file?? Thanks.

...

ANSWER

Answered 2021-Apr-30 at 13:27

So I found the answer out by myself and I am attaching the code below if anyone needs it. Change it according to your needs..

Source https://stackoverflow.com/questions/65951501

Community Discussions, Code Snippets contain sources that include Stack Exchange Network

Vulnerabilities

No vulnerabilities reported

Install unet

You can download it from GitHub.
You can use unet like any standard Python library. You will need to make sure that you have a development environment consisting of a Python distribution including header files, a compiler, pip, and git installed. Make sure that your pip, setuptools, and wheel are up to date. When using pip it is generally recommended to install packages in a virtual environment to avoid changes to the system.

Support

For any new features, suggestions and bugs create an issue on GitHub. If you have any questions check and ask questions on community page Stack Overflow .

Find more information at: