Skip to main content

Table 4 The structure of DEEPSEN-4L

From: DEEPSEN: a convolutional neural network based method for super-enhancer prediction

LayerSizeOutput Shape
Input 36 ×1
Convo132 ×3×132 ×36×1
Pool11 ×332 ×12×1
Convo264 ×3×1×3264 ×12×1
Pool21 ×364 ×4×1
Convo3128 ×3×1×64128 ×4×1
Pool31 ×2128 ×2×1
Convo4256 ×3×1×128256 ×2×1
Pool41 ×2256 ×1×1
Full-connected25664
softmax642