Category "machine-learning"

DNN model with maxout activation in tensorflow

How can I make this DNN model in tensorflow? 31 neurons in the first, 10 in the second, 5 in the third hidden layer, and 2 neurons in the output layer. The acti

Dummy variables: must I scale* them if I scale all dataset or leave them apart? *(center, scale, normalize...)

When working with scaled data, dummy variables should also be scaled or should be left apart without scaling? Can ML algorithms produce different result and whi

ValueError: Input 0 of layer lstm_14 is incompatible with the layer: expected ndim=3, found ndim=4. Full shape received: [None, 12, 12, 64]

I am using CNN-LSTM network for image classification. My image size is (224, 224, 3) and batch size is 90. I m getting this error when i passing input to LSTM l

How to create an ensemble model by stacking different model?

I want to use ensemble model by stacking Multiple Linear Regression, SVR, Decision Tree Regression and ANN regression. How can I do that?

Feature importance in neural networks with multiple differently shaped inputs in pytorch and captum (classification)

I have developed a model with three inputs types. Image, categorical data and numerical data. For Image data I've used ResNet50 for the other two I develop my o

How do engineered features help when they are not present in the test data

I am trying to classify between drones and birds using machine learning. I have got a big number of samples of feature vectors from a radar which generally con

Wandb line plots only show bar charts after refresh

My weights and biases (wandb) panels (e.g. for loss) shortly show line plots (x: steps, y: loss), then refresh (showing a spinner for some time) and then only s

converting recurrent to bi recurrent

I want to convert this below RNN into bidirectional RNN, how can I do that? #Call the function and compile the model. model = RNN() model.summary() model.compil

Keras model with 2 inputs

I am dealing with a binary classification problem that feeds a network with two inputs (images), model_vgg16_conv = VGG16(weights='imagenet', include_top=False)

I created a TF-IDF code to analyze an annual report, I want to know the importance of specific keywords

import pandas as pd from sklearn.feature_extraction.text import TfidfTransformer from sklearn.feature_extraction.text import TfidfVectorizer import path import

Error in init() function during azure ML deployment due to model path definition [closed]

We are trying to deploy a model to Azure ML workspace containing a saved model & One Hot Encoded joblib file. We are facing issue in init(

Error in fine-tuning a pre-trained FasterRCNN instance segmentation model (Detectron2) on my custom dataset

from detectron2.engine import DefaultTrainer from detectron2.config import get_cfg import os cfg = get_cfg() cfg.merge_from_file(model_zoo.get_config_file("COC

Pytorch Dataloader for .nifti.img files

I am trying to load the OSASIS-2 dataset in order to try to predict the onset of dementia. However, there does not, to my knowledge, exist a dataloader for this

Which method should I use to sample from a normal distribution?

I'm trying to sample batch_size points from an N-dim standard Gaussian distribution. But I noticed there are two similar functions I can use, and I want to know

How to download pipeline code from Pycaret AutoML into .py files?

PyCaret seems like a great AutoML tool. It works, fast and simple and I would like to download the generated pipeline code into .py files to double check and i

How to create synthetic data based on dataset with mixed data types for classification problem?

I am trying to build a classification model, but I don't have enough data. What would be the most appropriate way to create synthetic data based on my existing

how can I modify Dataset class to make the mask RCNN work with multiple objects?

I am currently working on instance segmentation. I follow these two tutorials: https://haochen23.github.io/2020/06/fine-tune-mask-rcnn-pytorch.html https://col

Why is VGG16 giving lesser no. of total parameters?

from tensorflow.keras.applications import VGG16 pre_trained_model = VGG16(weights='imagenet', include_top=False, input_shape=(224, 224, 3)) model = Sequential

AttributeError: 'list' object has no attribute 'i_sd'Which function can be used to get values from a Callback Class

The callback is called when specific events occur in an environment (e.g. at the beginning/end of a reset and beginning/end of a step). I have written a stub of

Error: "ValueError: could not convert string to float: 'Private Sector/Self Employed' "

Output- "ValueError: could not convert string to float: 'Private Sector/Self Employed' ". I need help with this error as I get this error consistently import nu