2
votes
When using class weights is bad?
Applying class weights (or resampling) to reach a more-balanced training dataset is usually done specifically to get more predictions of the rarer classes. That will very often cause a decrease in ...
Only top scored, non community-wiki answers of a minimum length are eligible
Related Tags
deep-learning × 4842machine-learning × 2016
neural-network × 1422
keras × 794
tensorflow × 649
python × 579
cnn × 512
nlp × 432
classification × 311
lstm × 311
convolutional-neural-network × 281
computer-vision × 265
image-classification × 209
pytorch × 198
rnn × 193
time-series × 190
transformer × 130
reinforcement-learning × 125
convolution × 116
dataset × 115
training × 112
object-detection × 108
loss-function × 106
regression × 104
machine-learning-model × 103