27,179 questions
1
vote
3
answers
2k
views
TF-IDF vs XGBoost vs CNN
I have a Natural Language Dataset where I am performing classification.
The tf-idf model always performs better than a Convolutional Neural Network model.
I have performed a lot of hyperparameter ...
Advice
0
votes
0
replies
30
views
Does random shifted artificial border harms network training?
Hello everyone I would like to request some information on best practices for training a neural network for image segmentation.
I am conflicted between two approaches lets assume i have patches of ...
- 27
Advice
0
votes
8
replies
87
views
Variational Autoencoders Visualisation
I am unable to visualise how variational autoencoders work graphically. I have understood the equations but am unable to figure out how this would all translate visually, like what is the purpose of P(...
- 2,080
Advice
0
votes
0
replies
36
views
Regarding's MONAI WarmupCosineSchedule with AdamW, should scheduler.step() be called per batch, and does optimizer lr define the peak lr?
I am training a PyTorch segmentation model and using:
torch.optim.AdamW
monai.optimizers.WarmupCosineSchedule
My optimizer:
optimizer = torch.optim.AdamW(
model.parameters(),
lr=1e-4,
...
- 163
4
votes
1
answer
8k
views
Multi-Head attention layers - what is a warpper multi-head layer in Keras?
I am new to attention mechanisms and I want to learn more about it by doing some practical examples. I came across a Keras implementation for multi-head attention found it in this website Pypi keras ...
CommunityBot
- 1
Tooling
0
votes
0
replies
50
views
What are the best methods or libraries to extract Arabic text from images or PDFs without using Surya OCR?
I am working on a project where I need to extract Arabic text from images and PDF documents. Currently, I am using Surya OCR, but I would like to explore other alternatives that might provide better ...
- 1
3
votes
1
answer
1k
views
LSTM/GRU and the use of overlapping sliding windows
Context
I am currently running some experiments with LSTMs / GRUs in Keras. Anyhow, the following questions also relate to the general functionality of these networks, which means an answer does not ...
Advice
0
votes
2
replies
70
views
Do you use raw pytorch or some wrapper or such?
I recently started a course about machine-learning as a part of my master that is apparently essentially a course in PyTorch, since starting the course i have learned that PyTorch is actually used a ...
- 15
3
votes
0
answers
401
views
Training Tesseract to decode the Epstein Files
The Department of Justice has recently released Volumes 09 and 10 of the Epstein files. Among them is a PDF: https://www.justice.gov/epstein/files/DataSet%209/EFTA01012650.pdf
This PDF contains ...
- 761k
Advice
1
vote
6
replies
145
views
Ai Neural Network | C++ | Project Guidance --- Matrix Part
I’m an undergraduate CS student working on a final project due in about a month, and I’m trying to design and implement a C++-based AI Neural Network Simulator integrated into a small game environment....
Advice
2
votes
1
replies
145
views
Need Guide for AI/ML
I am looking to grow my career in the AI/ML field, but I am currently feeling a bit confused about the right direction. At the moment, I am learning Python, NumPy, and Pandas.
Could someone please ...
2
votes
2
answers
854
views
What is the alternative for keras.layers.DenseFeatures in TensorFlow 2.16.+
I am using feature-column dataset in my code, in newer version of TensorFlow 2.16.1 and later there is no keras.layers.DenseFeatures class in order to ready the input layer for the DNN. what is the ...
Tooling
2
votes
0
replies
52
views
What are a good books to read in Bayesian Learning
Seems like Bayesian learning is the go to method now for reducing over fitting in ML models, I've read Manning's NLP in action, Deep Learning with python, O'Reilly Deep Learning foundations, Hands on ...
-1
votes
1
answer
42
views
Why does my LSTM time series prediction show periodic sharp downward spikes on test data?
I am trying to predict google stock price using LSTM model from PyTorch.
However after training my model and plotting the predicted results vs the real value, I see periodic sharp downward spikes.
...
- 111k
Best practices
0
votes
0
replies
39
views
FID score computation while training WGAN-GP
I am training WGAN-GP on Eurosat dataset, splitted into train/val/test sets in counts 18900/4050/4050. Since FID scores are widely used in GANs in image generation, I based my hyperparameter search on ...
