Questions tagged [convolutional-neural-network]
A convolutional neural network is a form of neural network with an additional convolutional layer, typically used in image & audio analysis. The convolutional layer is essentially a filtering stage defined by the kernel which is used. For example, a convolutional layer could have a kernel which extracts edges from an image towards the goal of learning which objects are in a scene.
710 questions
0 votes
0 answers
12 views
does object Aspect-ratio affect our resize policy?
Is object aspect ratio truly important for resize robustness, or is this suggestion based on a misunderstanding — e.g., treating a very wide object as if it is “bigger” or “pixel-richer” than a square ...
2 votes
0 answers
39 views
Convolution Kernels - Understanding dilation
I have a fairly good understanding of the basic convolution operation and how padding & stride affect its output, but dilation is something new to me. So I am going to make some broad statements ...
4 votes
1 answer
35 views
Possible to Improve Reconstruction Quality and Accuracy with VAE?
I am training a VAE architecture on microscopy images. Dataset of 1000 training images, 253 testing images. Images are resized to 128x128 input or 256x256 input from original resolution which is ...
7 votes
2 answers
221 views
Combining image and tabular data for a binary classification task
I'm working on a binary classification task where the goal is to determine whether a tissue contains malignant cells Each instance in my dataset consists of a microscope image of the cell a small set ...
0 votes
0 answers
27 views
How to use graph convolutional neural network (GCNN) to predict the appropriate patterns to solve an scheduling problem
I am working on a scheduling problem where I am willing to solve that by Graph Convolutional Neural Network (GCNN). The problem is stated as follows: There is an assembly product graph with $\text{G(V,...
3 votes
0 answers
44 views
Loss while fine tuning a transformer based pose estimation model not reducing
I am trying to fine-tune a transformer/encoder based pose estimation model available here at: https://huggingface.co/docs/transformers/en/model_doc/vitpose When passing "labels" attribute to ...
2 votes
0 answers
77 views
Overfitting problem of convolutional neural network; how to fix?
So I've been working on this convolutional neural network but my accuracy is stuck at 62% without improving and I'm afraid I'm in rather severe situation with the overfitting issue. I've been trying ...
0 votes
0 answers
36 views
Inference time Batch Normalization's Unbiased Variance Estimate in Convolutional Neural Network
I do see a lot of answers on the same topic. However, I have a part that still confuses me so I ask this question. https://stackoverflow.com/questions/38553927/batch-normalization-in-convolutional-...
0 votes
0 answers
22 views
Q-Learning TicTacToe Bot
I want to teach a neural network to play TicTacToe using Q-learning. I've seen this method implemented with the basic cartpole environment, and wanted to give TicTacToe a try. My question is how I ...
1 vote
2 answers
180 views
Please help with 1d Convolutional Neural Network with two channels in Tensorflow
I've been trying effortlessly (to no avail) for the past month to run a CNN. I previously tried PyTorch without success, and am trying Tensorflow as it appears simpler. I have simulated data from a ...
1 vote
1 answer
52 views
What program/function should I use to run a Convolutional NN to train simulated movement data against parameters that generated them?
I am overwhelmed by the literature and every example problem I see that uses Pytorch or TensorFlow differ from mine. I have N simulations of data on a grid- they are matrices of latitudes and ...
0 votes
0 answers
38 views
Deconvolution, NN-resize convolution
I was reading following paper: Deconvolution and Checkerboard Artifacts. The text says that Both deconvolution and the different resize-convolution approaches are linear operations, and can be ...
0 votes
0 answers
31 views
Are group convolutions still used?
Group convolutions theoretically should reduce the number of parameters and hence improve the speed of inference, without significantly affecting the performance of the model. However, I don't notice ...
1 vote
0 answers
140 views
Efficient Net V2 M ONNX model infers significantly slower on small input
When I convert an Efficient net v2 m model from Pytorch to Onnx on differently sized inputs, I notice a strange and unexplained behavior. I was hoping to find an explanation to my observations from ...
0 votes
1 answer
154 views
Conv2d with time series
I have a question about how a CONV2D layer handles time series data. How with filters that scroll through time, our model can extract features and capture and model our target value? Thank you in ...