Skip to main content

Questions tagged [deep-learning]

a new area of Machine Learning research concerned with the technologies used for learning hierarchical representations of data, mainly done with deep neural networks (i.e. networks with two or more hidden layers), but also with some sort of Probabilistic Graphical Models.

Filter by
Sorted by
Tagged with
0 votes
0 answers
21 views

Input 0 of layer "sequential_2" is incompatible with the layer: expected shape=(None, 3, 3), found shape=(1, 3, 11)

I am trying to predict stock closing price using news sentiment analysis with the help LSTM neural network but after I do model.fit(). I am encountered with the error message: ValueError: Input 0 of ...
1 vote
1 answer
117 views

Lung segmentation by Kmeans contains white border

I'm new to image processing, I'm trying to segment lung CT images by Kmeans by the following: ...
1 vote
1 answer
89 views

Using sensor data and a know reference point infer the position of a moving robot

Say, the robot is starting at a known position and I've data coming off of the robot as it traverses the grid layout. Exploiting the nuances captured in the data - like the implication of unequal rpm ...
1 vote
1 answer
67 views

General practices for building an incremental learning model which never forgets?

I'm new to datascience and appreciate your sage advice! I need to build an incremental learning model, and I know there's a lot that goes into something like that, but I'd like to highlight the most ...
0 votes
1 answer
73 views

How does the trainable projection layer used in PRADO and pQRNN work?

Trainable projection layers are said to be a very powerful thing but after reading: https://www.aclweb.org/anthology/D19-1506.pdf https://arxiv.org/pdf/2101.08890.pdf I don't understand how it works....
0 votes
0 answers
10 views

Why is resnet regression model (on a skewed data with small interval) not converging?

Using resnet50 (torchvision.models pretrained=False) with an input of [15, 224,224] which includes 14 heatmaps and a level set ...
0 votes
2 answers
107 views

feature normalisation problem

I am very new to ML and have limited knowledge about it. I am having issue in feature normalization process. I have understood from the post that we need to normalize the training features and scale ...
0 votes
1 answer
19 views

Accuracy and test_accuracy gives a result =1

I've developed a code for classifying hyperspectral images using three different convolutional neural network (CNN) architectures: 1D, 2D, and 3D. The code has two main parts: Preprocessing and data ...
1 vote
1 answer
1k views

Using a combination of gradient boosting with LSTM for classification?

I am presently using an LSTM model to classify high dimensional tabular data which is not text/images (dimensions 21392x1970). I also tried XGBoost (Gradient boosting) in Python separately for the ...
1 vote
1 answer
1k views

How to resize image along with their mask?

I have original images of the size 1935x1481. I am using labelme to annotate the images. I am creating polygons on the original image. Is there a way to resize the image along with their mask? I am ...
0 votes
0 answers
44 views

Is it possible to train a neural network to feed into a Random Forest Classifier or any other type of classifier like XGBoost or Decision Tree?

I want to create a model architecture to predict future stock price movement as such: The Goal of this model is to predict if the price will go UP or DOWN within the next 3 months. I have tried a few ...
3 votes
1 answer
98 views

What Models should i try for this problem?

I need some advice for a problem i'm working on with automobile data. The vehicles provide a series of codes at every second which are bieng stored, though it can vary how many. For example , at time ...
2 votes
1 answer
2k views

Advantages and disadvantages of using softmax/sigmoid and categorical_crossentropy/binary crossentropy for a binary classification with a CNN

I'm doing a deep learning model using tensorflow and keras. I have a question about the output architecture. I want to classify between two classes, images with defects and images without defects, I'...
0 votes
1 answer
57 views

Encoder Decoder model for parameter extraction from text input

I have an input as text from which I want to extract parameters as given in example below. Input: ...
1 vote
0 answers
21 views

Training VAE in Latent Diffusion Models

When working with Latent Diffusion Models (LDMs), is it common practice to only train the U-Net component while leaving the VAE untrained? Additionally, does this approach apply when fine-tuning an ...
1 vote
1 answer
54 views

PyTorch ResNet implementation's Training Loss increasing with every Epochs

I'm implementing a ResNet network from scratch using PyTorch. This network is unique to my requirements, since I need to perform Image Classification for Satellite Imagery with 14 different channels ...
0 votes
2 answers
208 views

How to improve the evaluation score for highly imbalanced dataset?

I have trained my BERT model(bert-base-cased) to detect toxic comments. I used the Toxic Comment Classification Challenge dataset from the Kaggle. My accuracy is 98% and the AUROC for various sub-...
0 votes
2 answers
269 views

Using DNN as the objective function for a multi-objective optimization algorithm

When creating a multi-objective optimisation/MCDM algorithm such as NSGA-ii, does it make sense to use a deep neural network trained on a supervised tabular regression prediction task, in place of a ...
0 votes
1 answer
68 views

How to automate the restarting of training of deep learning model in TensorFlow

I am trying to automate the (recursively) restart of a finished deep-learning training session in TensorFlow. Currently, to restart I am manually restarting my kernel and re-running the training code. ...
1 vote
1 answer
34 views

Choosing the right Deep Learning Model for Image Segmentation

How do you choose the appropriate Deep Learning Algorithm if you wanted to do image segmentation with an image datset which consist of hispathology images of almost 10000? I'am new to deep learning ...
0 votes
1 answer
1k views

Which is best FaceNet or dlib_face_recognition_resnet_model_v1?

I am newbie in face recognition related things... As far i observed dlib's frontal_face_detectoris widely used to find the faces in an image and after that, to ...
1 vote
1 answer
354 views

Bounding box regression without a classification task

I am using PyTorch to create a model that detects certain objects in an image. I framed my problem as a regression on bounding boxes, without any classification task whatsoever. The reasoning behind ...
0 votes
1 answer
79 views

Is it ok to use MC-dropout technique to estimate uncertainty without putting dropout after every weight layer?

In the paper by Kendall and Gal (What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?), dropout is being set after every convolutional layer. However, is it still legit to ...
0 votes
2 answers
99 views

How to deal with over confident model?

I have an LSTM model for action recognition. During inference, any random actions that are not labelled or the model has not learned at all are also predicted with very high confidence score. I ...
1 vote
1 answer
693 views

SSD based on ResNet-101 doesn't improve over SSD-VGGNet

I am training a SSD model for detecting mobile cranes. The training dataset contains 1,000 images and test set over 400 images. About 200 epochs gave mAP 83%, but my target is 90%. So I trained SSD-...
2 votes
1 answer
216 views

What is the output of multivariate LSTM model?

I am currently trying to build an LSTM model by using multivariate inputs, but I don't understand what exact output I am predicting. I am currently using 5 features in the data as input data: ...
1 vote
1 answer
198 views

Classification problem using features with unequal sizes

I am relatively new to Machine Learning/ Deep Learning and currently I am working on a classification problem. I have many 2D images and each of them is a cross section of a specimen showing the ...
0 votes
3 answers
55 views

Why do we use similarity/cosine between Query and Key in attention?

Let's take an example sentence for translation: I am going to my home and play with toy house. For translating 'home', as per my understanding, Query will be 'house'...
0 votes
1 answer
925 views

How to increase accuracy of model from tensorflow model zoo?

Situation: My dataset is 70k images of people wearing clothes. Images are labelled: bbox position and class. There are 10 classes. I did 80:20 split. Categories are ...
0 votes
1 answer
68 views

What actually is model size scaling and how do i globally apply to every model?

I read this article on the EfficientNet paper and have seen a lot of this kind of scaling. For example, there's Tiny-YOLO, YOLO (the base),.. Some model like SVTR, people did scale it to Tiny, Small, ...
-1 votes
1 answer
35 views

I need suggestion for a project

I want to make a forecasting system which will forecast how much quantity will be sold next year based on the previous 5 years' data from 2019 to 2023 and want to predict for future years. Now the ...
1 vote
1 answer
266 views

Online vs minibatch training for speed

If I do online learning in a setting where I have a HUGE amount of data, is that faster than doing minibatch learning (even if I optimize my batch size for GPU use, that is, use a multiple of 32 ...
1 vote
1 answer
851 views

How does BERT work for Aspect-Based sentiment analysis?

I have recently used a package to perform Aspect-Based Sentiment Analysis (ABSA) through a BERT model. Briefly, the model takes two inputs: words that constitute the aspects a sentence on which we ...
1 vote
1 answer
680 views

Ground truth/label modification during training (with the data obtained from the

I'm working on an image segmentation algorithm with FCN (Long et al., 2015) as the backbone network. One idea I have is to use the argmax binary mask obtained from the final score layer (250x250x1) ...
2 votes
1 answer
339 views

How to use arctan2 function inside Keras model?

I'm trying to add arctan2 function to the end of Keras model, but it looks like it is not getting any near even local minimum. Here is my ridiculous but minimal ...
0 votes
1 answer
361 views

How to have a fixed no of features for input layer of a neural network when using TF-IDF

So basically my question is hypothetically lets say: I have a column containing 2000 rows of texts, and when I apply tf-idf, I get 27 features like shown below. Now once I do that, I could consider ...
2 votes
1 answer
29 views

Practical Experiments on Self-Attention Mechanisms: QQ^T vs. QK^T

I'm currently exploring the self-attention mechanism used in models like Transformers, and I have a question about the necessity of using a separate key matrix (K) instead of just using the query ...
0 votes
1 answer
26 views

CS undergrad query about DS

why is learning DS so ambigious .you dont truly know what should you learn to actually do DS .web dev say has a clear path learn html css js and you can make something .i am a cs undergrad just want ...
0 votes
0 answers
10 views

jar files downloading very slowly in jupyter notebook in Mac Book(M2 pro)

Required jar files are downloading from maven repository in Jupyter notebook are very slow in Mac book (M2 pro). how can i increase the speed of download?
0 votes
1 answer
100 views

Why does my mAP metric value start so high in the first epoch?

I am doing an object detecton task and I have an issue with my mean average precision metric (mAP). The problem is that the value is a perfect 1.0000 from the first epoch. My guess is that it has ...
0 votes
1 answer
55 views

Transpose Convolution feature extraction

Convolution extracts high-level features, but what about Transpose Convolution (or De/Up-Convolution)? Does it behave exactly the opposite? Does it generate lower-level features?
0 votes
0 answers
14 views

Whats a suitable feature selection method for Time series data across multiple files?

My problem is basically a higher dimensional regression, where my input is (100 levels, 300 timesteps, 23 features) My goal is to build a deep learning LSTM model that finds which level the data ...
0 votes
1 answer
81 views

Learning similarity of representations

I am interested in a framework for learning the similarity of different input representations based on some common context. I have looked into word2vec, SVD and other recommender systems, which does ...
0 votes
1 answer
57 views

How to train encoder in BiGAN?

I have some difficulties training a BiGAN. In particular, the encoder seems not learning the map between the images x and the latent space z. I have the following encoder: ...
1 vote
1 answer
2k views

sklearn MinMaxScaler: Inverse does not equal original

I am using MinMaxScaler on a large dataset (2201887, 3) to normalize features. Inversed values does not match originals. I tested with the target column, first (a), I applied the scaler on 10 values, ...
2 votes
1 answer
166 views

Reinforcement Learning on real time data over a web server

Question: is it possible to implement a reinforcement learning model over a NodeJS server? This server would be receiving binary forms of data (open /close; yes/no) in real time. The objective for ...
1 vote
2 answers
718 views

BERT classifier with Ktrain API is unable to predict new data

I have trained a classifier for sentiment analysis using BERT architecture. I am able to train the classifier and I am getting a validation accuracy of 87%. But whenever I feed in test data, or some ...
2 votes
1 answer
151 views

Time Series Generation - Multi Dimensional Time Series Data

Disclaimer: Mathematicians please don't be mad at me for the use of some of the terminologies in this post. I am an Engineer. :-) Background: So I am currently working on a problem where I have to ...
0 votes
0 answers
10 views

Can transfer learning on VGG better align with Across the Spider-Verse styles for improved style transfer?

Our project is working on implementing style transfer using styles from Across the Spider-verse. We've gotten some good outputs so far, but were wondering if we could better align the VGG model to the ...
2 votes
1 answer
135 views

What are the tradeoffs between Bayesian Deep Learning and Deep Gaussain Processes?

I understand the differences between Deep Gaussian Processes(DGPs) and Bayesian Deep Learning(BDL): DGPs are essentially feed-forward neural networks where each node is a Gaussian Processes, which BDL ...

1
3 4
5
6 7
98