- Главная
- Информатика
- Image resnet 34
Содержание
Слайд 2code : version dummy_11a
train classifier
make csv for detection only
train segmentation
make csv for
code : version dummy_11a
train classifier
make csv for detection only
train segmentation
make csv for
![code : version dummy_11a train classifier make csv for detection only train](/_ipx/f_webp&q_80&fit_contain&s_1440x1080/imagesDir/jpg/972050/slide-1.jpg)
segmentation only
make final submission csv by merging detection + segmentation
Слайд 3The detection and segmentation code are similar. We explain how to use
The detection and segmentation code are similar. We explain how to use
![The detection and segmentation code are similar. We explain how to use](/_ipx/f_webp&q_80&fit_contain&s_1440x1080/imagesDir/jpg/972050/slide-2.jpg)
the code using segmentation.
if the training loss cannot decrease initially, use class weight or balance class sampler. You can finetune without weight + normal random sampler at the end
- Предыдущая
Бытовая химия для дома Clean HomeСледующая -
House of my dream