All Questions
Tagged with deep-learning conv-neural-network
3,321
questions
-1
votes
0
answers
12
views
Variable size input for CNN
I would like to create an AI that could guess the next image in a sequence of images and I have the idea to feed a CNN with 1,2,3,...,n-1 images as input running it through an LSTM and the output is ...
-3
votes
0
answers
14
views
Gray wolf algorithm and CNN in Kai text [closed]
I used the gray wolf optimization algorithm to optimize CNN's hyperparameters, but instead of getting more, the accuracy is about 95, the accuracy is 35, and I can't find the problem. Can someone help ...
-1
votes
0
answers
20
views
Deep learning and Tracking objects across cameras
I am using YOLOV10 to detect and Deep sort to tack objects it is working fine while we are in the first CCTV camera when we get to the next CCTV camera there the object is from a different point of ...
0
votes
0
answers
14
views
Which deep learning model: CNN or VGG16 based on metrics and accuracy plots?
I trained two models using for image classification: one with a CNN (dataset 1 was significantly cropped to separate shaded and non-shaded images, 100 epochs) and the other with VGG16 transfer ...
-1
votes
0
answers
17
views
How to use the Vgg16 optimally
I read some code on the Vgg16 and I have some questions please. In some code I notice that they use the outputs like this :
vgg = VGG19(weights="imagenet",include_top=False, input_shape=...
0
votes
0
answers
20
views
CRNN OCR, issue with dynamic width of images. How to tackle and resolve this? Need to train on images with different width
I am creating a ocr for urdu. I bucket my data into n number of buckets based on their widths. means all images whose widths are less than 400px are all reshaped to have width of 400px and are stored ...
-2
votes
0
answers
11
views
CNN Predicting Random Images
I have Trained the model with CNN. The MODEl i have Trained for Binary classification with chest - X - Ray images. Even after training the model. Model is predicting Random images like cars, animals ...
1
vote
1
answer
48
views
How do I define/change the accuracy for a non-classification convolutional neural network?
I'm using Keras to make a prediction model. It takes in two time series and outputs a number between 0 and 1. Currently, I am getting very low accuracy as the model is only considered "correct&...
-1
votes
0
answers
22
views
My ConvLSTM model for predicting sign language gestures trained on WLASL video dataset is not improving accuracy during training phase for 10 epochs
Link for the dataset - https://www.kaggle.com/datasets/risangbaskoro/wlasl-processed
This is preprocess dataset code.
# IMPORTS
import os
import sys
import pandas as pd
import torch
from torch.utils....
0
votes
1
answer
37
views
Loss function not decreasing on a CNN model?
I am a creating a CNN model in order to detect emotions (I am very new to creating neural networks). The dataset I used had this structure:
DatasetName ->
train ->
0
1
2
3
4
5
6
7
where each ...
0
votes
0
answers
23
views
GPU in Neural Net slow
I am trying to run the following code in Colab via GPU:
import torch
import torch.nn as nn
import torch.optim as optim
import pandas as pd
import numpy as np
from sklearn.model_selection import ...
0
votes
0
answers
17
views
input_shape error while converting tensorflow model to tensorflow.js model
I want to use my deep learning CNN algorithm in a web application and I converted my tensorflow model, emotion_model.h5 to a tensorflow.js model using this command in the terminal
...
-1
votes
0
answers
22
views
Degradation after scaling of coded images
I'm working on a problem of predicting the next image from a past image sequence. My starting images are of the form (50, 101, 128, 128, 3), To prepare them for training with an auto-encoder ...
-1
votes
0
answers
18
views
CNN for RadioNuclide Identification: How to normalize data, using CategoricalCrossentropy for loss, and metric for performace test?
Currently I have made a CNN model for RadioNuclide identification using gamma spectrum after reading through some of the papers related this type of work. This model is supposed to be for multilabel ...
0
votes
0
answers
26
views
gettting dl/dx shape from conv(padded dl/dz, rot180 kernels) in convolution neural networks
I am implementing cnn from scratch and I am stucked in dl/dx during backward propagation
Architecture:
28 x 28 input image
Layer 1
conv layer 1 kernels = 32 x 3 x 3
output shape = 32 x 26 x 26
max ...