1,338 questions
1
vote
1
answer
64
views
My neural network for MNIST digit recognition learns for one epoch and then stops learning
I am coding an MNIST digit recognition neural network. I thought I was finished but when I run the program to train the MNIST the accurcacy after each epoch is stable. I use MSE as my cost function ...
Best practices
1
vote
11
replies
6k
views
Reading data more efficiently from a csv file in python
I am programming an neural network to recognise digits trained on the MNIST dataset. At the moment I am reading each line separately using the following code:
file = np.loadtxt(dataLocation, delimiter=...
1
vote
2
answers
94
views
MNIST multi digit prediction [closed]
I tried to train a model on mnist dataset. It's working fine for single digit prediction and I got 96.92% accuracy on test data too but I have everything but it's not working for multidigit.
even ...
- 19
0
votes
0
answers
70
views
Keras SKLearnClassifier wrapper can't fit MNIST data
I'm trying to use the SKLearnClassifier Keras wrapper to do some grid searching and cross validation using the sklearn library but I'm unable to get the model to work properly.
def build_model(X, y, ...
0
votes
1
answer
105
views
Problems downloading a dataset for Torch for R
I'm trying to load the MNIST dataset in Torch for R, following https://skeydan.github.io/Deep-Learning-and-Scientific-Computing-with-R-torch/overfitting.html#classic-data-augmentation:
library(torch)
...
- 35
1
vote
1
answer
74
views
Use subset of dataset in c++ frontend
I am using MNIST in the c++ frontend, and I want to use a reduced version of it. However, the c++ frontend does not appear to have torch.utils.data.Subset or RandomizedSubsetSampler to use a subset of ...
- 21
0
votes
0
answers
90
views
Error when importing to_categorical from tensorflow.keras.utils
Whenever I use
from tensorflow.keras.utils import to_categorical
or
from tensorflow.keras.datasets import mnist
I receive the error "could not be resolved". Did anything change over the ...
0
votes
0
answers
130
views
Gradient descent 3D visualization Python
I've recently implemented a neural network from scratch and am now focusing on visualizing the optimization process. Specifically, I'm interested in creating a 3D visualization of the loss landscape ...
- 59
1
vote
0
answers
103
views
How can I apply data augmentation to MNIST images in R's keras package?
I'm fluent in R but a total beginner with deep learning. I'm trying to splice together two bits of code from the Chollet et al. Deep Learning with R book (2d ed), namely one for a CNN model for the ...
- 35
1
vote
1
answer
83
views
Numpy grayscale image to black and white
I use the MNIST dataset that contains 28x28 grayscale images represented as numpy arrays with 0-255 values. I'd like to convert images to black and white only (0 and 1) so that pixels with a value ...
- 309
1
vote
1
answer
130
views
Not reaching optimal parameter values for my neural network
I am trying to create a classification neural network using only the NumPY library for it. I have completely made the network and worked through the logic of it, and it seems perfectly fine to me. I ...
- 19
0
votes
0
answers
187
views
options for loading mnist dataset in python
I am confused about the options for loading data into python. Using the mnist dataset, I have found numerous options for loading the test and trainsets. Since these options are tethered to the ...
0
votes
0
answers
66
views
The DataLoader in PyTorch modifies my data
I am trying to train my deep network on the MNIST dataset. When I try to upload the dataset to the dataloader and get the batched data through the iterator, I get modified data that differs from the ...
- 1
0
votes
1
answer
81
views
Generator is not learning in One to Many CGANs
I am still new to GANs and trying to implement the One to Many CGAN, on the MNIST Dataset, to generate a sequence of images (with the number of output images equal to the number of generators) from a ...
0
votes
0
answers
106
views
Fixing the train-test resolution discrepancy in a YOLO model
I have trained a yolov8 model in order to detect handwritten digits on paper with MNIST dataset. The problem is that the images on the dataset are 416x416 and once the model is trained it gets really ...
