[英]How can I change subsets value in theano tensor impeded into loop?
大小(1,96,236,236)的layer_Fmaps大小(1,96,708,708)的小地圖
在layer_Fmaps的每個3 x 3矩陣中,只有一個值為1的單元格應由相反的情景
我找不到通過使用循環將直接值分配給特定位置來解決問題的方法
def switchs(layer_Fmaps, step=2, switches):
for idx in range(96):
for i in range(0, 708, step):
for j in range(0, 708, step):
val = layer_Fmaps[0][idx][i/2,j/2]
switches = T.set_subtensor(switches[0][idx][i:i + step, j:j + step],val)
return switches
知道switch和layer_Fmaps是tensor4
img = np.zeros((1,96,236,236))
sswitchs = np.zeros((1,96,708,708))
inp = T.tensor4('img')
SW = T.tensor4('SW')
tester = switchs(inp,3,SW)
f = theano.function([inp, SW], tester)
d = f(img,sswitchs)
任何建議,將不勝感激。
def switchs(layer_Fmaps, switches, step=2):
for idx in range(96):
for i in range(0, 708, step):
for j in range(0, 708, step):
val = layer_Fmaps[0,idx,i/2,j/2]
switches = T.set_subtensor(switches[0, idx, i:i + step, j:j + step],val)
return switches
和:
img = np.zeros((1,96,236,236))
sswitchs = np.zeros((1,96,708,708))
inp = T.tensor4('img')
SW = T.tensor4('SW')
tester = switchs(inp,SW, 3)
f = theano.function([inp, SW], tester)
d = f(img,sswitchs)
我修改了幾件事:
聲明:本站的技術帖子網頁,遵循CC BY-SA 4.0協議,如果您需要轉載,請注明本站網址或者原文地址。任何問題請咨詢:yoyou2525@163.com.