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.
4,834
questions
6
votes
1
answer
2k
views
What is the minimum number of times a word needs to appear in word2vec training corpus for quality results?
When training a word2vec model with, eg, gensim, you can specify the minimum times a word needs to be seen (with the parameter min_count). The default value for this seems to be 5.
Are there any ...
CommunityBot
- 1
1
vote
1
answer
773
views
Error on custom RNN/LSTM with multiple inputs
I want to implement a custom RNN/LSTM model similar to this. The model should take two separate vectors as input and process them. I was following keras tutorial to implement a custom keras layer and ...
CommunityBot
- 1
0
votes
1
answer
136
views
Number of capsules in the Primary Capsule Layer of Capsule networks
What is the Number of capsules in the Primary Capsule Layer of Capsule networks?
In many articles, it is written that the number of Capsules is 32 but in the paper, by Hinton - Dynamic Routing ...
CommunityBot
- 1
1
vote
1
answer
272
views
LSTM model bad forecasts
I tried to implement LSTM model for time-series prediction. Below is my trial code. This code runs without error.
...
CommunityBot
- 1
1
vote
1
answer
177
views
Trained CNN individually on multiple images to classify them, how can I now classify a related "set" of these images that correspond to one object?
I have a N object classification examples, each example consisting of a set M individual images of the object at different angles. I've trained M CNNs with the dataset of one particular image angle ...
CommunityBot
- 1
0
votes
1
answer
90
views
Difference between class_weight and loss_weights arguments in TensorFlow/Keras
I am creating a neural network using TensorFlow (v2.9.2) for an imbalanced image dataset. While doing so, I noticed that model.compile() method has an argument <...
CommunityBot
- 1
0
votes
1
answer
78
views
Incorporating structural information in a Transformer?
For a Neural Machine Translation (NMT) task, my input data has relational information. This relation could be modelled using a graphical structure.
So one approach could be to use Graph Neural Network ...
CommunityBot
- 1
0
votes
1
answer
16
views
How to add multiple embeddings (layers) to LSTM layer
The similar question was asked before here https://stackoverflow.com/questions/52627739/how-to-merge-numerical-and-embedding-sequential-models-to-treat-categories-in-rn/52629902#...
- 426
0
votes
1
answer
22
views
more insights about Word2Vec implementation
As we know Word2Vec is non-contextual embedding (at word level). As per my knowledge, BOW is statistical embedding technique (word level).
we can perform Word2Vec embedding in two approaches: 1. CBOW. ...
- 11
0
votes
1
answer
17
views
Appropriate input size for nn.Embedding
I’m quite new to using Pytorch and deep learning. What size of unique categories of a categorical variable is appropriate for applying the nn.Embedding ideally (best practices)? for example, if a ...
- 11
0
votes
2
answers
7k
views
No gradients provided for any variable
I have composed a customized loss function (kl_loss):
...
CommunityBot
- 1
1
vote
2
answers
91
views
What is the typical things in Data that i have to look for, when implementing Survival Models using Machine Learning?
Problem Scenario
I am working on an industry specific problem focussed on predicting the failure of a seal/gasket in the given time interval(T) in a high-pressure-compression environment. Whenever ...
CommunityBot
- 1
0
votes
0
answers
6
views
RecSys model performance stalling at 47% AUC and F1-Score. Is the problem due to ratio of users to items in my dataset?
I'm having trouble with making my validation metrics go down for the binary_crossentropy and go up for the F1-score and AUC. I've tried tuning my hyper parameters such as the number of latent features ...
1
vote
2
answers
114
views
approach for predicting machine failure using maintenance history
I have been struggling with this problem for a while now and I finally decided to post a question here to get some help. The problem i'm trying to solve is about predictive maintenance.
Specifically, ...
CommunityBot
- 1
1
vote
2
answers
403
views
how to label 3d model for segmentation task
I'm working on 3d meshes dataset, i have to label it to train my deep learning model for a segmentation task like the picture shows.
I spent days looking for a tool to label my 3d data but ...
0
votes
1
answer
978
views
CNN image to image translation: multiple image inputs to one image output
I am interested in training a CNN to take in inputs where each input is a set of low-resolution images and each ground truth is a single high-resolution image. The ground truth high-resolution image ...
CommunityBot
- 1
1
vote
1
answer
843
views
Deep learning based Resume Parser and Scoring
I want to know if Deep learning can be used for Resume Parsing and scoring of the resume.
Currently what I am doing is extracting the text from pdf or image using OCR/tesseract and finding the ...
CommunityBot
- 1
1
vote
1
answer
194
views
Calculate importance of input data bands for CNN image classification?
I constructed and trained a convolutional neural network using Keras in R with the TensorFlow backend. I feed the network with multispectral images for a simple image classification.
Is there some way ...
CommunityBot
- 1
1
vote
2
answers
212
views
Designing a pretrained DNN for image similarity
I am pretty new to deep learning and really hope that you can help me.
I want to write a python program that lets me choose an area in a reference image. This subimage of variable size should then be ...
CommunityBot
- 1
0
votes
0
answers
7
views
How to Use Multiple Adapters with a Pretrained Model in Hugging Face Transformers for Inference?
I have a pretrained Llama-2 model in the models_hf directory and two fine-tuned adapters: a summarization adapter in ...
- 23
2
votes
2
answers
320
views
How to get same accuracy with identical models in Keras and Tensorflow?
As we all know Keras backend uses Tensorflow and so it should give out some kind of results when we provide the same parameters, hyper-parameters, weights, and biases initialization at each layer, but ...
CommunityBot
- 1
1
vote
1
answer
669
views
Train a deep learning model in chunks/sequentially to avoid memory error
How do I train/fit a model in chunks so as to escape the dreaded memory error?
...
CommunityBot
- 1
2
votes
1
answer
74
views
What should I do to test the confidence of my deep learning model?
I've recently fine-tuned a deep learning framework/model BERT for a sentiment classification task. I had a 80/10/10 train/validation and test set. After running several experiments, I've gotten a ...
CommunityBot
- 1
1
vote
1
answer
2k
views
keep_dims is deprecated, use keepdims instead
I downloaded:
!git clone https://www.github.com/matterport/Mask_RCNN.git
os.chdir('Mask_RCNN')
And I've got an error:
which version I should have of Keras?
<...
CommunityBot
- 1
4
votes
2
answers
954
views
How propagate the error delta in backpropagation in convolutional neural networks (CNN)?
My CNN has the following structure:
Output neurons: 10
Input matrix (I): 28x28
Convolutional layer (C): 3
feature maps with a 5x5 kernel (output dimension is 3x24x24)
Max pooling layer (MP): size 2x2 ...
CommunityBot
- 1
0
votes
0
answers
9
views
Generating synthetic labeled data (sampling from p(x,y))
I'm working on a toy problem. Consider a dataset that consists of 1-D vectors (waveforms) that contain noise, except for one prominent spike. Denote the waveform by $\vec{x}$, and let the coordinate ...
- 1
0
votes
1
answer
68
views
Input standartization for Deep Learning - Proper Scaling
Typically the input to neural network (NN) is transformed to have zero mean and 1 std.
I wonder why std scale should be 1? What about other scales? 10? 100?
Doesn't it make sense to provide NN with ...
CommunityBot
- 1
1
vote
1
answer
173
views
Deep Q-learning, how to set q-value of non-selected actions?
I am learning Deep Q-learning by applying it to a real world problem. I have been through some tutorials and papers available online but I counldn't figure out the solution for the following problem ...
CommunityBot
- 1
0
votes
1
answer
87
views
Feature extraction in machine learning
I am a bit confused by reading A survey on object detection in remote sensing. They state that machine learning-based object detection consists of three essential parts - feature extraction, feature ...
CommunityBot
- 1
2
votes
1
answer
2k
views
Using LSTM for multi label classification
I am trying to use LSTMs to train and predict authors using reviews data and metadata
...
CommunityBot
- 1
1
vote
2
answers
93
views
computer science student - asking for some machine learning guiding (voice cloning)
I have chosen my synopsis topic for my second last semester.
I want to make a text-to-speech program, that speaks with the voice of a game character.
I have worked with machine learning in my class, ...
CommunityBot
- 1
1
vote
1
answer
255
views
How is ResNet different from FPN?
I'm learning more about different variations of deep CNNs. Based from my understanding, ResNet makes use of skip connections that's also somehow shaped like a pyramid or triangle? How is this ...
CommunityBot
- 1
3
votes
1
answer
151
views
VQ-GAN understanding
I tried to understand how VQ-GAN works, but unfortunately I have not understood it. I tried to read some articles about it and watch a video. I believe a good and simple article will help me. You ...
CommunityBot
- 1
0
votes
1
answer
594
views
Custom loss for low false positive rate (higher precision)
I am working with a scenario where I need to minimize the false positive rate for the minority class. Additionally my dataset is imbalanced. (10% minority class, 90% majority class). I am using the ...
CommunityBot
- 1
0
votes
0
answers
6
views
Can we use the pretrained WavLM on Portuguese?
I wan to try WavLM for 2 tasks:
Speaker Verification
Speech embeddings
If I understand it correctly, the WavLM pre-trained model was trained on English.
so if I want to use it for my missions, do I ...
- 363
1
vote
3
answers
2k
views
Detect blur image using ssdmobilenet and tensorflowlite
I have clear images of cards vs blurry images of card. My task is to capture photo when the image is not blurry, as you can see from the description I need this code to run in real time on android ...
CommunityBot
- 1
0
votes
1
answer
75
views
Why apply min-max normalization to each individual mel spectrogram for a training set?
I am watching a tutorial on using mel spectrograms to classify the audio's genre via CNN. My question is why apply local min-max normalization to each individual mel spectrogram? What I mean by local ...
CommunityBot
- 1
0
votes
1
answer
79
views
How to use LSTM for time series data?
I've an ECG data spread over time. The duration for each data is around 3 minutes (approx 180 seconds).
Each second around 200 recordings were taken. So total length for each sample is approx 36000.
...
CommunityBot
- 1
2
votes
1
answer
345
views
Comparison between approaches for timeseries anomaly detection
After various days of research, I could take a global picture of the existing methods to perform anomaly detection on time series, namely:
Forecasting with Deep Learning. Eg. RADM or LSTM model
...
CommunityBot
- 1
0
votes
0
answers
18
views
Different generated patches from original image using vision transformer (ViT)
I am using ViT for image classification, I scaled images in range of [-1,1], and I also padded images. Then, I used the following code to see the original image and generated patches, but the output ...
- 1
0
votes
1
answer
66
views
About the Evaluation method of the Market 1501 ReID dataset
The market 1501 dataset has train, query and gallery folders, each containing multiple views of people from multiple cameras. I would like to understand how to evaluate a model (trained with triplet ...
CommunityBot
- 1
0
votes
0
answers
13
views
Why I am getting error in dataloader in defining a NN?
I am trying to write a NN. However I am getting error.
Here is my Code:
...
- 1
1
vote
1
answer
88
views
Error when checking target: dimensions error in CNN-LSTM model for multivariate time series forecasting
I'm making a CNN-LSTM model to forecast multivariate time series:
...
CommunityBot
- 1
2
votes
1
answer
329
views
Policy gradient/REINFORCE algorithm with RNN: why does this converge with SGM but not Adam?
I am working on training RNN model on caption generation with REINFORCE algorithm. I adopt self-critic strategy (see paper Self-critical Sequence Training for Image Captioning) to reduce the variance. ...
CommunityBot
- 1
0
votes
1
answer
1k
views
Does YOLO give preference to color over shape or vice-versa while detecting an object?
If you train your YOLO model only on grayscale images to detect car, then would it able to recognise a car in a colored image also. If so, then can I assume that YOLO consider only object shape not ...
CommunityBot
- 1
4
votes
2
answers
235
views
Benefits of using Deep Learning-specific hyperparameter optimization tools vs. sklearn?
There are quite a few library for hyperparameter optimization that are specific to Keras or other Deep Learning libraries, like Hyperas or Talos.
My question is, what's the main benefit of using ...
CommunityBot
- 1
2
votes
2
answers
144
views
Extract Information from PDF using DL
We are having this requirement of extracting information from a credit history document. Usually it is a PDF and a computer generated document.
Because these PDFs are generated by different sources, ...
CommunityBot
- 1
0
votes
1
answer
332
views
What are the theoretical differences of multitask learning vs fine tuning based transfer learning?
Suppose, I have the following scenarios:
I have a bunch of fruits, i.e., apple, orange, and banana. I simply made a multitask model, where my network first tell me which fruit it is, and then telling ...
CommunityBot
- 1
0
votes
0
answers
14
views
Why use sliding window input features in deep learning?
I was reading through the DNABERT paper and found that their input features were k-mers. This is equivalent to using rolling/sliding window features in the other common family of sequential problem, ...
- 131
1
vote
1
answer
4k
views
How to load all images using image_dataset_from_directory function?
I am working on a multi-label classification problem and faced some memory issues so I would to use the Keras image_dataset_from_directory method to load all the ...
CommunityBot
- 1