我正在尝试调试自定义丢失函数，我希望可视化目标函数中的中间计算步骤中生成的图像。一个tf_summary_image或一个简单的imshow将是完美的，但如果没有使用正确的feed_dict调用sess.run（），它就无法工作。为简单起见，假设我有：
def custom_objective(y_pred, y_true):
diff = y_pred - y_true
#Here I would need something to save and/or show the diff image
square = K.square(diff)
#Here I would need something to save and/or show the square image
mean = K.mean(square, axis=-1)
return mean
有什么建议吗？