def pyconv3d(signals, filters, border_mode='valid'):
Ns, Ts, C, Hs, Ws = signals.shape
Nf, Tf, C, Hf, Wf = filters.shape
# if border_mode is not 'valid', the signals need zero-padding
if border_mode == 'full':
Tpad = Tf - 1
Hpad = Hf - 1
Wpad = Wf - 1
elif border_mode == 'half':
Tpad = Tf // 2
Hpad = Hf // 2
Wpad = Wf // 2
else:
Tpad = 0
Hpad = 0
Wpad = 0
if Tpad > 0 or Hpad > 0 or Wpad > 0:
# zero-pad signals
signals_padded = numpy.zeros((Ns, Ts + 2 * Tpad, C,
Hs + 2 * Hpad, Ws + 2 * Wpad), 'float32')
signals_padded[:, Tpad:(Ts + Tpad), :, Hpad:(Hs + Hpad),
Wpad:(Ws + Wpad)] = signals
Ns, Ts, C, Hs, Ws = signals_padded.shape
signals = signals_padded
Tf2 = Tf // 2
Hf2 = Hf // 2
Wf2 = Wf // 2
rval = numpy.zeros((Ns, Ts - Tf + 1, Nf, Hs - Hf + 1, Ws - Wf + 1))
for ns in xrange(Ns):
for nf in xrange(Nf):
for c in xrange(C):
s_i = signals[ns, :, c, :, :]
f_i = filters[nf, :, c, :, :]
r_i = rval[ns, :, nf, :, :]
o_i = ndimage.convolve(s_i, f_i, mode='constant', cval=1)
o_i_sh0 = o_i.shape[0]
# print s_i.shape, f_i.shape, r_i.shape, o_i.shape
r_i += o_i[Tf2:o_i_sh0 - Tf2, Hf2:-Hf2, Wf2:-Wf2]
return rval
评论列表
文章目录
