python - 如何在神经网络训练的损失函数中执行快速傅立叶变换
问题描述
我目前正在研究一个完全卷积神经网络(图像输入,图像输出),我正在尝试实现一个损失函数,在对它们进行一些操作之前对 2 个图像进行快速傅立叶变换,代码是这样的
def fourierLoss2(y_actual,y_pred):
actual_fft = tf.signal.rfft3d(y_actual)
pred_fft = tf.signal.rfft3d(y_pred)
lossV=tf.math.real(tf.math.reduce_mean(tf.math.square(actual_fft-pred_fft)))
return lossV
with strategy.scope():
model = hd_unet_model(INPUT_SIZE)
model.compile(optimizer=Adam(lr=0.1),
loss= fourierLoss2,
metrics=tf.keras.metrics.MeanSquaredError())
2 个张量 (y_actual,y_pred) 具有浮点类型。但是如果我尝试训练模型,我会收到以下错误
/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/training.py:806 train_function *
return step_function(self, iterator)
/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/training.py:796 step_function **
outputs = model.distribute_strategy.run(run_step, args=(data,))
/usr/local/lib/python3.6/dist-packages/tensorflow/python/distribute/distribute_lib.py:1211 run
return self._extended.call_for_each_replica(fn, args=args, kwargs=kwargs)
/usr/local/lib/python3.6/dist-packages/tensorflow/python/distribute/distribute_lib.py:2585 call_for_each_replica
return self._call_for_each_replica(fn, args, kwargs)
/usr/local/lib/python3.6/dist-packages/tensorflow/python/distribute/mirrored_strategy.py:585 _call_for_each_replica
self._container_strategy(), fn, args, kwargs)
/usr/local/lib/python3.6/dist-packages/tensorflow/python/distribute/mirrored_run.py:96 call_for_each_replica
return _call_for_each_replica(strategy, fn, args, kwargs)
/usr/local/lib/python3.6/dist-packages/tensorflow/python/distribute/mirrored_run.py:237 _call_for_each_replica
coord.join(threads)
/usr/local/lib/python3.6/dist-packages/tensorflow/python/training/coordinator.py:389 join
six.reraise(*self._exc_info_to_raise)
/usr/local/lib/python3.6/dist-packages/six.py:703 reraise
raise value
/usr/local/lib/python3.6/dist-packages/tensorflow/python/training/coordinator.py:297 stop_on_exception
yield
/usr/local/lib/python3.6/dist-packages/tensorflow/python/distribute/mirrored_run.py:323 run
self.main_result = self.main_fn(*self.main_args, **self.main_kwargs)
/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/training.py:789 run_step **
outputs = model.train_step(data)
/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/training.py:757 train_step
self.trainable_variables)
/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/training.py:2722 _minimize
gradients = tape.gradient(loss, trainable_variables)
/usr/local/lib/python3.6/dist-packages/tensorflow/python/eager/backprop.py:1073 gradient
unconnected_gradients=unconnected_gradients)
/usr/local/lib/python3.6/dist-packages/tensorflow/python/eager/imperative_grad.py:77 imperative_grad
compat.as_str(unconnected_gradients.value))
/usr/local/lib/python3.6/dist-packages/tensorflow/python/eager/backprop.py:151 _gradient_function
grad_fn = ops._gradient_registry.lookup(op_name) # pylint: disable=protected-access
/usr/local/lib/python3.6/dist-packages/tensorflow/python/framework/registry.py:97 lookup
"%s registry has no entry for: %s" % (self._name, name))
LookupError: gradient registry has no entry for: RFFT3D
经过一些研究,我了解到问题在于操作 tf.signal.rfft3d 没有注册的梯度函数。有人知道解决这个问题的方法吗?
解决方案
我已经找到了解决问题的方法,而不是使用tf.signal.rfft3d
我必须使用tf.signal.fft3d
,这个函数有一个梯度条目并在损失函数中工作,缺点是现在我必须在之前将浮点张量转换为复杂类型傅立叶变换
推荐阅读
- python - 从一个新列中提取x坐标?
- ruby-on-rails - Rails:在传递给模型之前根据用户类型修改参数的设计模式
- flutter - Flutter-onTap 和 Display 快餐栏时如何关闭底部模态表?
- gitlab - 为组中的用户与特定项目中的用户设置不同的角色
- java - 以编程方式模仿 @Bean 方法将多个实例注册为 bean
- testing - QTP - 确定是否继续操作
- python - CSV 文件,错误。Python
- javascript - 修改 Spree Cart.js 以显示正确的购物车项目计数和数量
- swift - 无法在 2 个 ViewController 之间添加 Segue
- django - Facebook 登录在网站上不起作用