Stack Overflow
Stack Overflow

Questions tagged [vgg-net]

A kind of convolutional neural network consisting of 16 or 19 layers, often used with weights pre-trained on ImageNet dataset. Whereas the the model was originally created for image classification, its convolutional part can be used for a variety of purposes. Use this tag for questions, specific for this CNN architecture.

The name VGG stands for Visual Geometry Group (Oxford University), authors of the original paper.

The model consists of a convolutional part (several convolution and max- or avegare-pooling layers) and several fully-connected layers atop of it. Small (3x3) convolution filters are used.

See visual representation below (taken from this answer):

enter image description here

Model applications

  1. Image classifier (Tensorflow).
  2. Image segmentation (Keras).
  3. Image style transfer (Keras).
471 questions
0
votes
1 answer

VGG: order of categories?

I'm using VGG-16 network trained on ILSVRC with Fast-RCNN. You can get a 1000-dimensional matrix for probability of each of 1,000 classes in ILSVRC. However, I can't find out which column in the matrix corresponds to which class. For example, I'd…
ytrewq
  • 3,670
  • 9
  • 42
  • 71
-1
votes
0 answers

Keras utils function Progbar.update throwing TypeError: unsupported operand type(s) for /: 'tuple' and 'int'

I am trying to train a neural network to recognize faces by using Tensorflow object-detection API. The code is mostly borrowed from Nicolas Renotte (https://www.youtube.com/@NicholasRenotte). i am however running into an error while trying to train…
Bharath Reddy
  • 1
-1
votes
1 answer

My model isn't improving.VGG16 with cifar10

I am trying to train a model by transfer learning with VGG16, but the accuracy isn't increasing even as the learning epoch progresses. Could there be something wrong with the input? def build_model(): input_tensor = layers.Input(shape=(32, 32,…
kogle
  • 1
  • 1
-1
votes
1 answer

image segmentation with vgg16 and randomforest

according to the below link, the writer has implemented the image segmentation with vgg16 as the encoder and the random forest as the…
ali ali
  • 1
  • 1
-1
votes
1 answer

Problem Regarding Input Shape Conversion of vgg16 CNN Model in the OpenVINO 2022.1 Version

I am using the Intel OpenVINO 2022.1 on Windows OS for my project. I am trying to convert the input data shape of the vgg16 CNN model from [1,3,224,224] to [2,3,300,300]. I tried to use the following command: mo --input_model…
Md Maksud-Ul-Kabir Rico
  • 1
  • 1
-1
votes
2 answers

Training Deep Neural Network Using Tensorflow

I am trying to immplement the VGG16 network using Tensorflow. to test the model, i want to classify a dataset of images. i sarted by creating a train_data with tensorflow.data.Dataset:
anam
  • 9
  • 3
-1
votes
1 answer

Vgg16 and Resnet50 overfits despite including 100k images - Tensorflow

I am training a classifier using vgg16 and Resnet50. The data I have collected contains 100k RGB images belonging to four classes, each containing ~25k (the unbalanced issue was minor and compensated by augmentations). The dimension of each image is…
SH_Clarity
  • 63
  • 2
  • 7
-1
votes
1 answer

Why VGG16 model cannot be trained with its FC Layers

I am trying to train the VGG16 model code, but the loss is not optimized and seems that model's parameters are not updated. here is the model : import torch import torch.nn as nn import math import torch.nn.functional as F from utils import…
Musheer Abdullah
  • 9
  • 3
-1
votes
1 answer

Facing ValueError: Shapes (None, None) and (None, 256, 256, 12) are incompatible

İ am working on transfer learning for multiclass classification of image datasets that consists of 12 classes. As a result, İ am using VGG19. However, I am facing an error i.e. Facing ValueError: Shapes (None, None) and (None, 256, 256, 12) are…
Turjoy Ahmed
  • 29
  • 9
-1
votes
1 answer

Validation loss less than training loss (vald accuracy higher than training accuracy) without using dropout

I have been working on Multitask model, using VGG16 with no dropout layers. I find out that the validation accuracy is higher than the training accuracy and validation loss is lesser than the training loss. I cant seem to findout the reason to why…
Obiii
  • 698
  • 1
  • 6
  • 26
-1
votes
1 answer

How can i predict images(outside dataset) using VGG16 with keras after training?

I have trained the VGG16 net using keras with my own dataset, which has 10 classes. so i modified the activation layer with 10 classes. Here is the code TRAIN_DIR = "D:\\Dataset\\training" VALIDATION_DIR = "D:\\Dataset\\validation" part 2 …
sayem
  • 1
  • 1
  • 1
-1
votes
1 answer

VGG16 fine tuning

I'm trying to fine tune VGG16. But sometimes I got a validation accuracy that is constant, sometimes it is fixed to 0.0 and sometimes it is fixed to 1.0 and it is the same also on the test accuracy. It also happened that the training is…
Vincenzo Longobardi
  • 1
-1
votes
1 answer

Is there anyway to omit VGG16 target classes?

I have a bunch of medical images and I want to do some feature extraction on them. To do that, I intend to use pretrained CNN VGG16. It has a list of target classes which is consists of name of the ordinary objects. How can I change it to do feature…
Elessar
  • 93
  • 2
  • 11
-1
votes
1 answer

How to Fit my model using transfer learning Vgg

I'm new to Machine learning i got 1 example of Cat vs Dog image classification and here is the link to it https://pythonprogramming.net/convolutional-neural-network-kats-vs-dogs-machine-learning-tutorial/ It worked perfectly , but now when i want…
N.A
  • 11
  • 4
-1
votes
1 answer

How to use mid-level fine tuning in Keras?

My task is to adapt a pre-trained network from Keras for classification of aerial images (we have a database of 30 categories of aerial images, each containing 200-400 images). Now, what I don't really understand is this next part. We must use…
xmisd
  • 390
  • 6
  • 17
1 2 3
…
31
32