外部Python代码的TensorFlow占位持有人解耦

Question

仍在学习tensorflow，我正在尝试在darkflow中的某些代码中更改损失函数

网络输出具有形状的给定张量[49,3,2]。我想在张量的最后一部分中取两个元素，并使用一些代码对其进行处理。然后，我想退还数据。因此，有点像可以与TensorFlow一起使用的地图。

更多上下文-https：//github.com/thtrieu/darkflow/blob/master/master/darkflow/net/yolo/yolo/train.py我要更改的文件。

因此，不确定如何做到这一点，如果我对问题不够清楚，请询问更多信息。我仍然试图让自己想做的事情。

例如

S = 7
SS = S * S 
C = 8 
B = 3
size1 = [None, SS, C]
size2 = [None, SS, B]

# Extract the coordinate prediction from net.out
coords = net_out[:, SS * (C + B):]
# Take flatten array and make it back into a tensor.
coords = tf.reshape(coords, [-1, SS, B, 4])
wh = tf.pow(coords[:,:,:,2:4], 2) * S # unit: grid cell
area_pred = wh[:,:,:,0] * wh[:,:,:,1] # unit: grid cell^2
centers = coords[:,:,:,0:2] # [batch, SS, B, 2]
floor = centers - (wh * .5) # [batch, SS, B, 2]
ceil  = centers + (wh * .5) # [batch, SS, B, 2]
# calculate the intersection areas 
# WHAT HAPPENS CURRENTLY 
intersect_upleft   = tf.maximum(floor, _upleft)
intersect_botright = tf.minimum(ceil , _botright)
intersect_wh = intersect_botright - intersect_upleft
intersect_wh = tf.maximum(intersect_wh, 0.0)
intersect = tf.multiply(intersect_wh[:,:,:,0], intersect_wh[:,:,:,1])
 # I WANT TO CALCULATE THE AREA OF INTERSECTION THE BOX DIFFERENTLY SO 
   I WOULD HAVE 
   MY OWN FUNCTION DOING SOMETHING. BUT I ONLY WANT IT DONE FOR CENTERS 
   AND THEN RETURN A BIT LIKE A MAP FUNCTION BUT I NEED IT TO WORK WITH 
   TENSORFLOW PLACEHOLDERS 

任何提示或建议都很好，谢谢伙计：D

Answer 1

看来tf.map_fn功能适合您的需求。该文档说明您可以将Python可呼叫应用于张量或一系列张量。

当前文档的提取，介绍该功能的主要参数：

fn：要执行的可调用。它接受一个参数，该参数将具有与Elems相同的(可能嵌套(结构。如果提供了它的输出，则必须具有与dtype相同的结构，否则必须具有与元素相同的结构。

Elems：张量或(可能嵌套的(张量序列，每个张量将沿其第一个尺寸拆开。所得切片的嵌套序列将应用于fn。

此功能可从TensorFlow 0.8获得，因此几乎总是可用。