Skip to main content
Deshwal's user avatar
Deshwal's user avatar
Deshwal's user avatar
Deshwal
  • Member for 4 years, 7 months
  • Last seen more than a month ago
5 votes
1 answer
4k views

Which is the "BEST" deep learning model for "Custom" object detection for images & real time. YOLO v3, v4, v5, EfficientDet?

2 votes
0 answers
227 views

Practical example and working of Laplace Smoothing or Linear Interpolation in Natural Language Processing (NLP) [closed]

2 votes
1 answer
144 views

"Change the features of a CNN into a grid to fed into RNN Encoder?" What is meant by that?

2 votes
0 answers
27 views

Statistical method to find the value which preserves the most information inside "most" of data points. (resize images to a common height)

1 vote
2 answers
2k views

What are the steps and correct order of the operations in Machine Learning? [from Getting data to optimising models]

1 vote
1 answer
778 views

How does the equation "dW = - (2 * (X^T ).dot(Y - Y_hat)) / m" comes in Linear Regression (using Matrix + Gradient Descent)?

1 vote
2 answers
222 views

How to choose products based on Number of good, bad and total reviews?

1 vote
0 answers
18 views

What can be the approaches to merge (ensemble) a NON-Probabilistic model with RandomForest?

1 vote
0 answers
12 views

Generalise a CNN model for Question vs Spam . Techniques to generalise the model apart from more data

1 vote
0 answers
31 views

How exactly the hidden state works in an RNN ? How to decide on how many past instances to consider?

1 vote
1 answer
242 views

Training loss stuck in the starting epochs but then starts decreasing. What could be the reason for it?

1 vote
1 answer
119 views

Working Behavior of BERT vs Transformers vs Self-Attention+LSTM vs Attention+LSTM on the scientific STEM data classification task?

1 vote
0 answers
117 views

What should be the best CNN model for Feature extraction of images for Image-Image search engine using LSH?

1 vote
2 answers
416 views

How gradients are flown back to Network in siamese architecture? How weights of all CNN models are same even when using different models

0 votes
1 answer
52 views

How to manage memory constraint and increase speed for 1 vs rest image similarity comparison for over 100k images for computer vision?

0 votes
0 answers
86 views

Is it possible (if yes, then how) to provide the semantic segmentation results on the Original Size of the input image?

0 votes
1 answer
36 views

What what will happen if all the layers of a MLP or any DL architecture are set as same in the beginning?

0 votes
2 answers
101 views

How a Random forest "learns" or How loss (objective function value) is propagated back so that a random forest can "Improve"?

0 votes
0 answers
46 views

What are some good techniques to decrease the size of Image Embeddings returned by CNN model?