def __init__(self, input, pool_shape, method="max"):
"""
method: "max", "avg", "L2", "L4", ...
"""
self.__dict__.update(locals())
del self.self
if method == "max":
out = max_pool_3d(input, pool_shape)
else:
raise NotImplementedError()
self.output = out
def __init__(self, input, n_in_maps, n_out_maps, kernel_shape, video_shape, pool_shape,
batch_size, layer_name="Conv", rng=RandomState(1234),
borrow=True, W=None, b=None):
"""
video_shape: (frames, height, width)
kernel_shape: (frames, height, width)
W_shape: (out, in, kern_frames, kern_height, kern_width)
"""
# init W
if W is not None:
W_val = W
else:
# fan in: filter time x filter height x filter width x input maps
fan_in = prod(kernel_shape) * n_in_maps
norm_scale = 2. * sqrt(1. / fan_in)
W_shape = (n_out_maps, n_in_maps) + kernel_shape
W_val = _asarray(rng.normal(loc=0, scale=norm_scale, size=W_shape), \
dtype=floatX)
self.W = shared(value=W_val, borrow=borrow, name=layer_name + '_W')
self.params = [self.W]
# init bias
if b is not None:
b_val = b
else:
b_val = zeros((n_out_maps,), dtype=floatX)
self.b = shared(b_val, name=layer_name + "_b", borrow=borrow)
self.params.append(self.b)
# 3D convolution; dimshuffle: last 3 dimensions must be (in, h, w)
n_fr, h, w = video_shape
n_fr_k, h_k, w_k = kernel_shape
out = conv3d(
signals=input.dimshuffle([0, 2, 1, 3, 4]),
filters=self.W,
signals_shape=(batch_size, n_fr, n_in_maps, h, w),
filters_shape=(n_out_maps, n_fr_k, n_in_maps, h_k, w_k),
border_mode='valid').dimshuffle([0, 2, 1, 3, 4])
pooled_out = max_pool_3d(out, pool_shape, ignore_border=True)
pooled_out += self.b.dimshuffle('x', 0, 'x', 'x', 'x')
self.output = T.tanh(pooled_out)
