Function get_same_padding

timm/models/layers/padding.py:18–19

(x: int, k: int, s: int, d: int)

# Calculate asymmetric TensorFlow-like 'SAME' padding for a convolution
def get_same_padding(x: int, k: int, s: int, d: int):
    return max((math.ceil(x / s) - 1) * s + (k - 1) * d + 1 - x, 0)


# Can SAME padding for given args be done statically?