Questions tagged [cgan]
13 questions
1
vote
0 answers
Implementation of the discriminator in CGAN
I am trying to implement CGAN with convolutions. I have written a discriminator. The code is running but I am not sure if it is correct or not. Below is my code
import torch
import torch.nn as nn
import torch.optim as optim
from torchvision.utils…
odbhut.shei.chhele
- 5,834
- 16
- 69
- 109
1
vote
0 answers
I want to optimize the conditon gan model (generator),error: shape '[64, 3, 64, 64]' is invalid for input of size 2952192 ，
This is original github source:
https://github.com/otepencelik/GAN-Artwork-Generation
I want to rerun this model and use it another area (CGAN).
I want to change the network to generate multiple label and increase the performance but it didn't work…
Jackie J
- 11
- 2
1
vote
0 answers
best way of using float as the conditional input for cGAN? one-hot encoder?
I'm trying to make a model for outputing an image based on speed (a float input). This can for example range from 1.0 to 6.0. so basically it is an cGAN, with a latent noise and a float as combined input.
I wonder what's the best way to encode my…
icarus.z
- 45
- 4
0
votes
0 answers
Data cardinality is ambiguous: x sizes: 15, 15 y sizes: 30 Make sure all arrays contain the same number of samples
def train_gan(self, epochs, batch_size=30, save_interval=50):
print('Train')
self.img_rows = 256
self.img_cols = 256
# Load and preprocess the dataset
print('start train_gan')
# Define the…
0
votes
0 answers
Can I call a generator model created with functional api into this Model subclass of a cGAN (tensorflow , keras)?
Currently, this is what I have for a cGAN model using model subclassing (ignore that the discriminator model is missing).
# Create the generator.
generator = keras.Sequential(
[
keras.layers.InputLayer((generator_in_channels,)),
…
srv_77
- 547
- 1
- 8
- 20
0
votes
0 answers
Problems with the network architecture for a conditional GAN that works with 64x64x3 images
I am trying to create a cGAN that generates new anime faces. The data I am using is given in the link: https://www.kaggle.com/datasets/splcher/animefacedataset.
As is evident, there is no class label associated with the dataset. Hence, I have used…
Skywalker
- 582
- 1
- 5
- 16
0
votes
1 answer
ValueError: Input 0 of layer “Discriminator” is incompatible with the layer: expected shape=(None, 3), found shape=(100, 2)
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
from sklearn import preprocessing
from sklearn.preprocessing import StandardScaler
from sklearn.metrics import precision_score, recall_score, f1_score,\
…
Shrija Sheth
- 1
- 2
0
votes
0 answers
Why is my cDCGAN model behaving like this?
Training a cDCGAN model using PyTorch to generate Covid X-ray images at a resolution of 128x128. Currently limited to 2 classes over 500 epochs while developing.
Actual Losses Why does it behave like this?
Results
Class 0 - 6012 samples
Class 1 -…
patryk
- 1
- 1
0
votes
0 answers
cGAN: RuntimeError: The size of tensor a (100) must match the size of tensor b (7) at non-singleton dimension 0
I am new to cGAN architectures and I was trying out on the MNIST which worked out quite fine but not my own data set. The data set has 7 classes and an Input size of each image (64, 64, 3). I am using Pytorch with Python 3.10:
class…
soku
- 1
0
votes
0 answers
Input 0 of layer "conv2d" is incompatible with the layer: expected axis -1 of input shape to have value 1
I am trying to make a Cgan and I want to do an interpolation between the categories, but I get the following error
"Input 0 of layer "conv2d" is incompatible with the layer: expected axis -1 of input shape to have value 1, but received input with…
0
votes
0 answers
Conditional GAN loss
I'm a little confused, I applied an existing code to the cgan and then plotted a plot diagram for the loss. It showed me three vector values of loss for the generator while the discriminant took only one loss vector. Why?
Lolo
- 1
- 1
0
votes
1 answer
In layers.append(nn.BatchNorm1d(out_feat, 0.8)) and layers.append(nn.LeakyReLU(0.2, inplace=True)) What is meant by 0.8 and 0.2?
class Generator(nn.Module):
def init(self): # defines an init function which is used to initialize all the required variables
super(Generator, self).init()
self.label_emb = nn.Embedding(opt.n_classes, opt.n_classes)
def block(in_feat,…
0
votes
0 answers
Getting Error in tf.cast while implementing CGAN
Question
HI, I am implementing CGAN in TensorFlow.
Please help me understand the cause of the error and how to resolve it.
Code
def train(dataset, epochs): for epoch in range(epochs):
start = time.time()
for image_batch in dataset:
…
Sumera Rounaq
- 11
- 1