Useful methods for CV competition
From SWA to TTA
[Read More]
[DL 101] RAdam - a novel variant of Adam
Rectified Adaptive Learning Rate (RAdam)
[Read More]
[DL 101] Learning Rate Scheduler
What is learning rate scheduler?
[Read More]
[DL 101] Maxpooling? Convolutions?
Can we replace maxpooling with convolutional layers?
[Read More]
[DL 101] Upsampling
In many cases including image segmentation, a model consists of downsampling and upsampling parts and the latter restore the feature map to the input sized image. There are two types of upsampling using torch: UpSampling, ConvTranspose2D.
[Read More]