image-segmentation

问题 I am doing an image segmentation task. There are 7 classes in total so the final outout is a tensor like [batch, 7, height, width] which is a softmax output. Now intuitively I wanted to use CrossEntropy loss but the pytorch implementation doesn't work on channel wise one-hot encoded vector So I was planning to make a function on my own. With a help from some stackoverflow, My code so far looks like this from torch.autograd import Variable import torch import torch.nn.functional as F def cross

问题 I am doing an image segmentation task. There are 7 classes in total so the final outout is a tensor like [batch, 7, height, width] which is a softmax output. Now intuitively I wanted to use CrossEntropy loss but the pytorch implementation doesn't work on channel wise one-hot encoded vector So I was planning to make a function on my own. With a help from some stackoverflow, My code so far looks like this from torch.autograd import Variable import torch import torch.nn.functional as F def cross

问题 I am working on an image-segmentation application where the loss function is Dice loss. The issue is the the loss function becomes NAN after some epochs. I am doing 5-fold cross validation and checking validation and training losses for each fold. For some folds, the loss quickly becomes NAN and for some folds, it takes a while to reach it to NAN. I have inserted a constant in loss function formulation to avoid over/under-flow but still it the same problem occurs. My inputs are scaled within

问题 Iam using runtime data augmentation using generators in keras for segmentation problem.. Here is my data generator data_gen_args = dict( width_shift_range=0.1, height_shift_range=0.1, zoom_range=0.2, horizontal_flip=True, validation_split=0.2 ) image_datagen = ImageDataGenerator(**data_gen_args) def generate_data_generator(generator, Xi, Yi): genXi = generator.flow(Xi, seed=7, batch_size=32) genYi = generator.flow(Yi, seed=7,batch_size=32) while True: Xi = genXi.next() Yi = genYi.next() print

问题 I downloaded the BraTS dataset for my summer project. The dataset consisted of nii.gz files which I was able to open using nibabel library in Python. I used the following code: import os import numpy as np import nibabel as nib import matplotlib.pyplot as plat examplefile=os.path.join("mydatapath","BraTS19_2013_5_1_flair.nii.gz") img=nib.load(examplefile) print(img) this gave me the following output: <class 'nibabel.nifti1.Nifti1Image'> data shape (240, 240, 155) affine: [[ -1. 0. 0. -0.] [ 0

问题 I'm working on multi-class segmentation using Keras and U-net. I have as output of my NN 12 classes using soft max Activation function. the shape of my output is (N,288,288,12). to fit my model I use sparse_categorical_crossentropy. I want to initialize weights of my model for my unbalanced dataset. The right answer to my question can be found here : How to initialize sample weights for multi-class segmentation? I tried to implement it on my code and replace y by my training mask Y_train

问题 I'm working on multi-class segmentation using Keras and U-net. I have as output of my NN 12 classes using soft max Activation function. the shape of my output is (N,288,288,12). to fit my model I use sparse_categorical_crossentropy. I want to initialize weights of my model for my unbalanced dataset. The right answer to my question can be found here : How to initialize sample weights for multi-class segmentation? I tried to implement it on my code and replace y by my training mask Y_train

问题 Im using aerial images to segment road and centerline using multi label u-net, my test generator is look like this def testGenerator(test_path= "data\\membrane\\test\\image",num_image = 1584,target_size = (224,224),flag_multi_class = False,as_gray = False): for i in range(num_image): img = io.imread(os.path.join(test_path,"%d.jpg"%i),as_gray = as_gray) img = img / 255. img = trans.resize(img,target_size) img = np.reshape(img,img.shape) if (not flag_multi_class) else img img = np.reshape(img,

问题 Im using aerial images to segment road and centerline using multi label u-net, my test generator is look like this def testGenerator(test_path= "data\\membrane\\test\\image",num_image = 1584,target_size = (224,224),flag_multi_class = False,as_gray = False): for i in range(num_image): img = io.imread(os.path.join(test_path,"%d.jpg"%i),as_gray = as_gray) img = img / 255. img = trans.resize(img,target_size) img = np.reshape(img,img.shape) if (not flag_multi_class) else img img = np.reshape(img,

问题 I've been trying to clear images for OCR: (the lines) I need to remove these lines to sometimes further process the image and I'm getting pretty close but a lot of the time the threshold takes away too much from the text: copy = img.copy() blur = cv2.GaussianBlur(copy, (9,9), 0) thresh = cv2.adaptiveThreshold(blur,255,cv2.ADAPTIVE_THRESH_GAUSSIAN_C, cv2.THRESH_BINARY_INV,11,30) kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (9,9)) dilate = cv2.dilate(thresh, kernel, iterations=2) cnts =