spatial_batchnorm_forward:
def spatial_batchnorm_forward(x, gamma, beta, bn_param):
"""
Computes the forward pass for spatial batch normalization.
Inputs:
- x: Input data of shape (N, C, H, W)
- gamma: Scale parameter, of shape (C,)
- beta: Shift parameter, of shape (C,)
- bn_param: Dictionary with the following keys:
- mode: 'train' or 'test'; required
- eps: Constant for numeric stability
- momentum: Constant for running mean / variance. momentum=0 means that
old information is discarded completely at every time step, while
momentum=1 means that new information is never incorporated. The
default of momentum=0.9 should work well in most situations.
- running_mean: Array of shape (D,) giving running mean of features
- running_var Array of shape (D,) giving running variance of features
Returns a tuple of:
- out: Output data, of shape (N, C, H, W)
- cache: Values needed for the backward pass
"""
out, cache = None, None
###########################################################################
# TODO: Implement the forward pass for spatial batch normalization. #
# #
# HINT: You can implement spatial batch normalization using the vanilla #
# version of batch normalization defined above. Your implementation should#
# be very short; ours is less than five lines. #
###########################################################################
N, C, H, W = x.shape
x_new = x.transpose(0, 2, 3, 1).reshape(N*H*W, C)#x.transpose将x变形为（N,H,W,C)
out, cache = batchnorm_forward(x_new, gamma, beta, bn_param)
out = out.reshape(N, H, W, C).transpose(0, 3, 1, 2)
###########################################################################
# END OF YOUR CODE #
###########################################################################
return out, cache
spatial_batchnorm_backward:
def spatial_batchnorm_backward(dout, cache):
"""
Computes the backward pass for spatial batch normalization.
Inputs:
- dout: Upstream derivatives, of shape (N, C, H, W)
- cache: Values from the forward pass
Returns a tuple of:
- dx: Gradient with respect to inputs, of shape (N, C, H, W)
- dgamma: Gradient with respect to scale parameter, of shape (C,)
- dbeta: Gradient with respect to shift parameter, of shape (C,)
"""
dx, dgamma, dbeta = None, None, None
###########################################################################
# TODO: Implement the backward pass for spatial batch normalization. #
# #
# HINT: You can implement spatial batch normalization using the vanilla #
# version of batch normalization defined above. Your implementation should#
# be very short; ours is less than five lines. #
###########################################################################
N, C, H, W = dout.shape
dout_new = dout.transpose(0, 2, 3, 1).reshape(N*H*W, C)
dx, dgamma, dbeta = batchnorm_backward(dout_new, cache)
dx = dx.reshape(N, H, W, C).transpose(0, 3, 1, 2)
###########################################################################
# END OF YOUR CODE #
###########################################################################
return dx, dgamma, dbeta