占位符错误的IoU keras（后端tensorflow）提要dict（Tensor.eval（）

Question

当我试图为keras创建自定义度量（并集上的交集）时，我出现了错误。我想找到两个图像（张量）的并集上的交

def IoU(y_true,y_pred):
    y_true_f = K.flatten(y_true)
    y_pred_f = K.flatten(y_pred)
    #assert len(y_true_f) != len(y_pred_f)
    y_true_f = y_true_f.eval(session = K.get_session())
    y_pred_f = y_pred_f.eval(session = K.get_session())
    union1 = [i  for i,j in zip(y_true_f,y_pred_f) if i != j]
    union2 = [j  for i,j in zip(y_true_f,y_pred_f) if i != j]
    intersection = [i for i,j in zip(y_true_f,y_pred_f) if i == j]
    unionAll = union1 + union2 + intersection
    return (np.sum(intersection) + smooth) / float(np.sum(unionAll)+ smooth)

我得到的错误是：

InvalidArgumEnterRorr（参见上面的跟踪）：您必须为占位符张量'Activation_1_Target'提供一个带有dtype float和shape[？,？,？]的值[[节点:activation_1_target=placeholderdtype=dt_float,shape=[？,？,？],_device=“/job:localhost/replica:0/task:0/GPU:0”]][[节点:metrics/iou/reshape/_5=_recvclient_terminated=false,recv_device=“/job:localhost/replica:0/task:0/cpu:0”,send_device=“/job:localhost/replica:0/task:0/GPU:0”,pe=dt_float,_device=“/job:localhost/replica:0/task:0/cpu:0”]]

Answer 1

eps = 1.
def iou(y_true, y_pred):
   y_true_f = K.flatten(y_true)
   y_pred_f = K.flatten(y_pred)
   intersection = K.sum(y_true_f*y_pred_f)
   union = K.sum(y_true_f)+K.sum(y_pred_f)-intersection+eps
   return intersection/union