IOU KERAS(后端TensorFlow)供占持有人错误(Tensor.eval()的feed dict

Question

当我尝试为keras创建自定义度量时(联合交集(时，我有错误。我想找到有关两个图像(张量(的联合的交集

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)

错误我得到：

无效的人(请参见上文，请参阅上面的追踪(：您必须喂养一个值 用于占位符张量'activation_1_target'带dtype float和 shape [？，？，？] [[node：activation_1_target = = OptarholderDtype = dt_float，shape = [？，？，？]，， _device ="/job：localhost/replica：0/task：0/gpu：0"]] recv_device ="/job：localhost/replica：0/任务：0/cpu：0"， send_device ="/job：localhost/replica：0/任务：0/gpu：0"， send_device_incarnation = 1，tensor_name =" edge_8_metrics/iou/reshape"， tensor_type = dt_float， _device ="/job：localhost/replica：0/任务：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