Wickkiey
  • Member for 3 years, 1 month
  • Last seen more than a month ago
Faster RCNN-RPN NETWORK
2 votes

Is that, we have to crop all the objects in every image and do binary classification as object vs background for classifying the anchor has object or not The RPN gets the input from backbone network(...

View answer
kMean clustering for recommendation
1 votes

Since your data is sequential, you could try with sequential models (LSTM, RNN, GRU) etc. With which you can you predict what the user will select after the set of books as recommendation. In this way ...

View answer
When to use Multinomial Naive Bayes?
1 votes

For Text classification Multinomial Naive bayes is a good choice to start with. We can start with MNB, when 1. There is no dependence between the predictors 2. Good if class is not unblanced (...

View answer
Clause type classification
0 votes

Since all the sentences length are not highly varying, you can use sentence embeddings and do the clustering on top of that. For example, Text => USE => vector[1024] => KMeans USE - ...

View answer
Search for implementation of Faster RCNN
0 votes

If you familiar with Tensorflow, you can refer Tensorflow Object Detection API` you can find the architecture and implementation in the below codes, https://github.com/tensorflow/models/blob/master/...

View answer
Why is XGBClassifier in Python outputting different feature importance values with the same data across different repetitions?
0 votes

According to the XGBClassifier parameters (link) some operations will be happens on top of randomness, like subsample feature_selector etc. If we didn't set seed for random value everything different ...

View answer
Why does my random forest classifier predicts one class more often?
0 votes

While prediction, If you have more date relevant to class 0 obviously this is the expected one. But if your observation is like, the model predicts more data with class 0 as incorrect, then you model ...

View answer
Large dataset - ANN
0 votes

To avoid overfit, While model building with MLPClassifier, Use early_stopping = True. This stops the training when there is no improvement with validation data. Using default node size is fine for ...

View answer
Get Label Statistics of Image Dataset
0 votes

From this SO answer https://stackoverflow.com/a/53832130/1727543 import xml.etree.ElementTree as ET import os def read_content(xml_file: str): tree = ET.parse(xml_file) root = tree.getroot(...

View answer
gradient descent in n dimensions
0 votes

Image courtesy : https://lh6.ggpht.com/-5RFMcz2bzWI/VA9NuUkB_vI/AAAAAAAAAdM/_DqqYO0nbX4/im2_thumb%25255B1%25255D.png?imgmax=800 My question is, does the slope go down a multi-dimensional curve when ...

View answer
Intent Classification in Question Answering
0 votes

You can use Spacy's named entity recognition. Since I feels it is good in accuracy as well as multi-processing approach is also possible. https://spacy.io/usage/linguistic-features#named-entities ...

View answer