Skip to main content
Filter by
Sorted by
Tagged with
0 votes
0 answers
42 views

I'm using CustomTkinter to build a GUI for medical image segmentation. I have a button to load the images, and I’ve previously saved my trained model as "unet_model.h5". I want to display ...
user31385194's user avatar
0 votes
1 answer
58 views

I have model Pix-to-Pix. Not segmentation. Transfer from texture to texture. Loss = 'mse'. And it works properly with GPU. But if i try to use TPU i get loss = 'nan' I simplified the model by cutting ...
Pavel No's user avatar
0 votes
0 answers
70 views

I’m running a TensorFlow UNet model on geospatial imagery. I split the image into overlapping 500×500 pixel tiles using a custom function (get_tiles) and use a stride of 460 (i.e. 500 – 2×padding) so ...
icyroots's user avatar
0 votes
0 answers
16 views

I am trying to get a custom version of the EelSpecNet model working, which is based on the Unet architecture. The original large version can be found here: text The model ist used to reconstruct an ...
twelle's user avatar
  • 21
1 vote
1 answer
75 views

I got the following U-net architecture causing problems: class UNet(nn.Module): def __init__(self, in_channels, out_channels): super(UNet, self).__init__() self.encoder1 = self....
greenbow's user avatar
2 votes
1 answer
94 views

I need to implement a U-Net in Julia using Flux.jl. The ultimate goal is to train a neural network for a scientific problem. As a first step, I decided to experiment with the KITTI benchmark dataset. ...
Baird's user avatar
  • 23
1 vote
1 answer
160 views

I have been reading about Unets and Stable diffusion and want to train one. I understand the original architecture for unets and how its channels, height and width evolve over down blocks and up ...
Krishna Dave's user avatar
0 votes
1 answer
74 views

I am studying Deep learning and have an assignment for training a DDPM with UNet on the MNIST handwritten digits dataset. Three ipynb files (model, unet and train_mnist) and one pdf for unet diagram ...
Daniel's user avatar
  • 1
0 votes
1 answer
115 views

I’m working on a deep learning model using Keras where I’m trying to combine three inputs: images, masks, and CSV data. The goal of my model is to predict the presence and type of brain hemorrhage ...
Mohammadreza Heidary's user avatar
0 votes
1 answer
73 views

I have trained a model fish.pth with 2 channels (fish and background). I want to add a layer so that I train a new model spine.pth which segments 3 classes fish, spine and background. Yes, I can do it ...
Erlend's user avatar
  • 1
0 votes
0 answers
49 views

I want to train a machine learning model for fine masked details in 2D DICOM images. I have 500 images ready for labeling/annotating. Can I use this technique or have I misunderstood? Annotation of ...
Erlend's user avatar
  • 1
1 vote
1 answer
159 views

I am training a model for brain extraction on MR images. I use 2D U-Net architecture and pretrained EfficientNetV2B3. def dice_coefficients(y_true, y_pred, smooth=0): intersection = K.sum(y_true *...
EfeK0's user avatar
  • 13
0 votes
1 answer
154 views

I've been assigned a task in my company to try to hydrate a model that was trained for a previous project, and while I can load it again, I'm failing to try it and I don't know why. The model follows ...
J. Maria's user avatar
  • 436
-1 votes
1 answer
56 views

when i try to use the UNet3+ i get an error: RuntimeError: one of the variables needed for gradient computation has been modified by an inplace operation: [torch.cuda.FloatTensor [1, 1024, 64, 64]], ...
Big-Yellow-J's user avatar
0 votes
0 answers
30 views

I've tried to implement a U-Net model to classify audio, and after preprocessing, I've converted the data into a dataset of float values. These are the shapes of my X and Y X_train shape: (3806, 2809) ...
Sunflower_Poet's user avatar
0 votes
1 answer
58 views

How can I pass an ImageDataGenerator to segmentation_model's U-net, data_generator = ImageDataGenerator( rescale = 1./255. ) train_dataset_images = data_generator....
Unknown_ _'s user avatar
0 votes
1 answer
102 views

I want mask my images with json formats as data for training model of u net. I use this below code to mask them: import json import numpy as np import cv2 import os # Path to the folder containing ...
user avatar
0 votes
0 answers
212 views

I am trying to adapt Tensorflow's example UNet for my purposes. The main difference is this UNet takes 128x128 images and masks and my images are 512x512 and my masks are 100x100. I am getting this ...
Ruby Midford's user avatar
0 votes
1 answer
210 views

I have used this code below to train an unet model. My dataset at first consisted of 10000 images, shape=(256,256,3), what was working fine. However, ofter enlargening it to 14000 images i encountered ...
Dennis's user avatar
  • 9
1 vote
0 answers
158 views

I try to use Mean-Teacher architecture with two U-Net in a semi-supervised setup but I have a strange behaviour with the loss during the training. I have a supervised loss and a consistency loss ...
MARCO CALABRESE's user avatar
0 votes
2 answers
114 views

As i try to run my y prediction to my model of x batch , it shows me a mismatch. This is the error I get: RuntimeError: Given groups=1, weight of size [512, 1024, 3, 3], expected input[16, 1536, 16, ...
James's user avatar
  • 17
0 votes
0 answers
103 views

I have implemented a U-Net model to perform self supervised learning on images (spectrograms; dim=(376, 128)) to learn background/foreground masks. I am very new to self supervised learning but after ...
Shamayl's user avatar
  • 81
0 votes
1 answer
500 views

I am using the keras_unet_collection python library's U-Net model to perform self supervised learning on images (spectrograms; dim=(376, 128)) to learn background/foreground masks. I am very new to ...
Shamayl's user avatar
  • 81
1 vote
1 answer
167 views

there are 704 graphs in our dataset when we use command nnUnetV2_plan_and_preprocess -d 201 --verify__integrity The program is stuck in enter image description here immobility.but when we reduce ...
xitong moren's user avatar
0 votes
2 answers
149 views

I'm trying to perform leaf disease image segmentation using Github code. Here is the code, i am facing this issue "The size of tensor a (524288) must match the size of tensor b (131072) at non-...
Urwa Shanza's user avatar
0 votes
1 answer
58 views

So I am currently using the Kaggle notebook environment. I am trying to build a U-Net model for image segmentation. When I build the model, it shows that the mode size is 2.17mb, but this takes model ...
distopia's user avatar
0 votes
1 answer
32 views

I'm building my first u-net, and having a bit of trouble matching the output to the labels. My code is as follows: import tensorflow as tf from keras import layers, models from keras.preprocessing....
Dylan Ndengu's user avatar
0 votes
1 answer
246 views

In the decoder part of UNet architecture, Upsampling layer is often followed by a Conv2d. Here is an example: class UpConv(nn.Module): def __init__(self, in_chans, out_chans): super()....
Alena's user avatar
  • 27
0 votes
1 answer
122 views

I am doing a Unet to make segmentation, in this file https://github.com/erickfmm/ML-experiments/blob/master/test/butterfly.py The shape of xtrain and ytrain are x_train shape (557, 100, 100, 3) ...
vincegeratorix's user avatar
0 votes
0 answers
93 views

I have several questions concerning a multi class image segmentation model pipeline. 1 - Influence of images masks I have created masks for each image according to this template : (0,0,0) is the ...
user avatar
0 votes
1 answer
178 views

net = UNet2DModel(sample_size=28, in_channels=1, out_channels=1, layers_per_block=2, block_out_channels=(32, 64, 64), ...
张佳伟's user avatar
0 votes
1 answer
668 views

First and foremost, I want to precise that I am a begginer in torch. I am struggling with the following code (found on github), I want to know what should be the input size of a such UNet. ""...
NancyBoy's user avatar
  • 113
0 votes
0 answers
233 views

Today i try to use Unet2DConditionModel and CLIPTextModel from Transformer Library with my text to image dataset, but i have error "RuntimeError: mat1 and mat2 shapes cannot be multiplied (...
Artsem Holub's user avatar
1 vote
0 answers
490 views

Does anyone know how sample size work in SD's VAE and UNet? All I know is the SD v1.5 was trained with 512*512, so it can generate 512*512 more properly. But when I set the pipeline like 384*384 or ...
MAPLE LEAF's user avatar
0 votes
1 answer
568 views

Newbee here:) I am trying to copying the course code from How Diffusion Models Work provided by DeepLearning.AI. The source code works on RGB images (if i remember correctly, size [3,28,28]) while I ...
JIAZHENG HU's user avatar
0 votes
0 answers
155 views

I am trying to implement Unet based segmentation for Medical Histopathology classification for single class problem. I get the loss and accuracy of the model but predicted masks are not getting ...
Rama's user avatar
  • 1
1 vote
1 answer
17k views

I have this code: import logging import os import sys import tempfile from glob import glob import torch from torch.cuda.amp import autocast, GradScaler from PIL import Image from torch.utils....
Aytekin Yenilmez's user avatar
0 votes
0 answers
721 views

I am a beginner for machine learning, and currently trying the retina-unet. There's a couple errors when processing model.fit model.fit(patches_imgs_train, patches_masks_train, epochs=20, batch_size=...
Ashley's user avatar
  • 21
0 votes
1 answer
1k views

I've been recently working on segmentation task on certain CT scans. I decided to use Python as the language, ResidualUNet model architecture implemented in MONAI, evaluated by DiceLoss. Everything ...
dkrolicki's user avatar
2 votes
1 answer
225 views

I'm currently learning U net and i am trying to run the example code from: https://colab.research.google.com/github/keras-team/keras-io/blob/master/examples/vision/ipynb/oxford_pets_image_segmentation....
Ashley's user avatar
  • 21
0 votes
0 answers
49 views

I want to train an UNET Network and my data is already normalized in an Array, I saved it in my disk in bin format, it's about 12GB of data. My memory is limited so I need to load a batch of the data ...
Lud Dias's user avatar
0 votes
1 answer
158 views

I am training U-net with 3 channels, input data 40x40x40 set of voxels and using CELoss followed by ReLU activation. Also, there is only one convolution layer unlike the original U-net. For many ...
Pranjali Singh's user avatar
0 votes
1 answer
193 views

I am segmenting microscopy images using a model I built with a UNet architecture. I get reasonable results after training my model, so I know it's working. As outputs, I obtain arrays with predicted ...
Linda Smith's user avatar
0 votes
1 answer
2k views

Hey together, i wrote a code with pytorch to segment satellite-images with a unet. If I test every block seperatly (unet, dataloader, train()), it works perfectly and it gives me the correct sizes ...
Felix's user avatar
  • 7
1 vote
1 answer
840 views

I'm trying use multi-channel file to training unet classify. My dataset is 5 * 1-channel & 1 * 3-channel image, and I expected it can be 8-channel .npy file. I use np.concatenate to merge, but it ...
Syuuuu's user avatar
  • 99
1 vote
1 answer
1k views

if you have a standard Unet encoder such as resnet50, then it's easy to add pertaining to it. for example: ENCODER = 'resnet50' ENCODER_WEIGHTS = 'imagenet' CLASSES = class_names ACTIVATION = 'sigmoid'...
user836026's user avatar
  • 11.5k
-1 votes
1 answer
796 views

Hello l am creating my Unet model. However l got weird issues they are a size missing on my third decoder line. l don't understand why. l am using a padding method in my UpBlock Class to get the same ...
jeremy's user avatar
  • 1
-1 votes
1 answer
284 views

according to the below link, the writer has implemented the image segmentation with vgg16 as the encoder and the random forest as the classifier. https://github.com/bnsreenu/python_for_microscopists/...
ali ali's user avatar
0 votes
0 answers
43 views

Classification Report: precision recall f1-score support discbulge 1.00 0.96 0.98 5898240 herniation 0.00 0.00 0.00 0 normal 0.00 0.00 0....
m paul's user avatar
  • 1
1 vote
1 answer
649 views

In order to train an autoencoder model using audio data as a first step, I need to understand the different representations of audio found in the literature, such as STFT(not spectrogram i mean by ...
chaima rebah's user avatar