TransWikia.com
  1. All Categories
  2. Data Science

Data Science : Recent Questions and Answers (Page 236)

Find answers to your questions about Data Science or help others by answering their Data Science questions.

Representing a 2d-grid around an agent

I'm trying to train a neural network-based model to play a game similar to Pac-Man, except there's no maze. i.e., the player is in a 2-dimensional grid, with dots of...

Asked on 01/26/2021

0 answer

Classification with feature not available at time of model creation

I have problem statement to predict the probability of solving a task depending on multiple features for e.g. when the task was created, the time needed to work on a...

Asked on 01/26/2021 by EricA

1 answer

How can we use the cosine similarity formula on document feature vector without a direction?

In mathematics, a vector has both magnitude and direction. In data science, for identifying document similarity we convert the document into a feature vector. Then apply cosine angle formula between...

Asked on 01/25/2021

1 answer

Why transform embedding dimension in sin-cos positional encoding?

Positional encoding using sine-cosine functions is often used in transformer models. Assume that $X in R^{ltimes d}$ is the embedding of an example, where $l$ is the sequence...

Asked on 01/25/2021 by kyc12

1 answer

Time series plot using netcdf data in python

I am trying to plot a time series for a 3d plot. I know that the variable must be made 1d inorder to make it viable for the time series...

Asked on 01/25/2021 by Debashis Paul

1 answer

I am receiving Tensorflow error "ValueError: None values not supported." while trying to populate tf dataset. Can somebody help me?

I have stored my data in a rank 2 (N x 3) tensor, and I am trying to gather specific rows of this tensor to yield the data of a...

Asked on 01/25/2021

1 answer

Preprocess problem Faster RCNN in tensorflow object detection API

I've wrapped meta-architecture with the code below:num_classes = 1model_conf = 'models/research/object_detection/configs/tf2/faster_rcnn_resnet101_v1_640x640_coco17_tpu-8.config'configs = config_util.get_configs_from_pipeline_file(model_conf)model_config = configs['model']model_config.faster_rcnn.num_classes = num_classesmodel_config.faster_rcnn.feature_extractor.batch_norm_trainable = Falsemodel_config.faster_rcnn.number_of_stages = 2model_config.faster_rcnn.second_stage_post_processing.batch_non_max_suppression.max_detections_per_class=150class MyDetectionModel(tf.keras.Model): # ADAPTER def __init__(self,...

Asked on 01/25/2021 by Agostino Dorano

0 answer

Why there is Different accuracy for two same trained model?

Trained the same model twice with the same dataset, the same parameters (Epochs, Batch Size, Learning rate, etc..). But both trained model shows different train as well as test accuracy...

Asked on 01/25/2021

1 answer

Why does Faster R-CNN use SGD optimizer instead of Adam?

I just start learning Faster R-CNN and I have some doubts about the optimizer of this network. In my understanding, Adam optimizer performs much better than SGD in a lot...

Asked on 01/25/2021 by icebear

0 answer

What to do this type of data

I have plots of feature vs target values as and ...

Asked on 01/25/2021

1 answer

Ask a Question

Get help from others!

© 2024 TransWikia.com. All rights reserved. Sites we Love: PCI Database, UKBizDB, Menu Kuliner, Sharing RPP