我正在尝试在Keras中实现自定义损失函数,但无法使其正常工作。
我已经使用numpy和keras.backend实现了它:
def log_rmse_np(y_true, y_pred):
d_i = np.log(y_pred) - np.log(y_true)
loss1 = (np.sum(np.square(d_i))/np.size(d_i))
loss2 = ((np.square(np.sum(d_i)))/(2 * np.square(np.size(d_i))))
loss = loss1 - loss2
print('np_loss = %s - %s = %s'%(loss1, loss2, loss))
return loss
def log_rmse(y_true, y_pred):
d_i = (K.log(y_pred) - K.log(y_true))
loss1 = K.mean(K.square(d_i))
loss2 = K.square(K.sum(K.flatten(d_i),axis=-1))/(K.cast_to_floatx(2) * K.square(K.cast_to_floatx(K.int_shape(K.flatten(d_i))[0])))
loss = loss1 - loss2
return loss
当我使用以下函数进行测试和比较损失时,一切似乎都正常。
def check_loss(_shape):
if _shape == '2d':
shape = (6, 7)
elif _shape == '3d':
shape = (5, 6, 7)
elif _shape == '4d':
shape = (8, 5, 6, 7)
elif _shape == '5d':
shape = (9, 8, 5, 6, 7)
y_a = np.random.random(shape)
y_b = np.random.random(shape)
out1 = K.eval(log_rmse(K.variable(y_a), K.variable(y_b)))
out2 = log_rmse_np(y_a, y_b)
print('shapes:', str(out1.shape), str(out2.shape))
print('types: ', type(out1), type(out2))
print('log_rmse: ', np.linalg.norm(out1))
print('log_rmse_np: ', np.linalg.norm(out2))
print('difference: ', np.linalg.norm(out1-out2))
assert out1.shape == out2.shape
#assert out1.shape == shape[-1]
def test_loss():
shape_list = ['2d', '3d', '4d', '5d']
for _shape in shape_list:
check_loss(_shape)
print ('======================')
test_loss()
以上代码输出:
np_loss = 1.34490449177 - 0.000229461787517 = 1.34467502998
shapes: () ()
types: <class 'numpy.float32'> <class 'numpy.float64'>
log_rmse: 1.34468
log_rmse_np: 1.34467502998
difference: 3.41081509703e-08
======================
np_loss = 1.68258448859 - 7.67580654591e-05 = 1.68250773052
shapes: () ()
types: <class 'numpy.float32'> <class 'numpy.float64'>
log_rmse: 1.68251
log_rmse_np: 1.68250773052
difference: 1.42057615005e-07
======================
np_loss = 1.99736933814 - 0.00386228512295 = 1.99350705302
shapes: () ()
types: <class 'numpy.float32'> <class 'numpy.float64'>
log_rmse: 1.99351
log_rmse_np: 1.99350705302
difference: 2.53924863358e-08
======================
np_loss = 1.95178217182 - 1.60006871892e-05 = 1.95176617114
shapes: () ()
types: <class 'numpy.float32'> <class 'numpy.float64'>
log_rmse: 1.95177
log_rmse_np: 1.95176617114
difference: 3.78277884572e-08
======================
当我使用这个损失函数编译和拟合我的模型时,从来没有出现过异常。当我使用'adam'损失函数运行模型时,一切都正常。但是,当我使用这个损失函数时,keras一直显示nan-loss:
Epoch 1/10000
17/256 [>.............................] - ETA: 124s - loss: nan
有点卡在这里了...我做错了什么吗?
在Ubuntu 16.04上使用Tensorflow 1.4
更新:
在Marcin Możejko的建议下,我更新了代码,但是训练损失仍然为NaN:
def get_log_rmse(normalization_constant):
def log_rmse(y_true, y_pred):
d_i = (K.log(y_pred) - K.log(y_true))
loss1 = K.mean(K.square(d_i))
loss2 = K.square(K.sum(K.flatten(d_i),axis=-1))/K.cast_to_floatx(2 * normalization_constant ** 2)
loss = loss1 - loss2
return loss
return log_rmse
然后模型通过以下方式编译:
model.compile(optimizer='adam', loss=get_log_rmse(batch_size))
更新2:
模型摘要如下:
Layer (type) Output Shape Param #
=================================================================
input_2 (InputLayer) (None, 160, 256, 3) 0
_________________________________________________________________
block1_conv1 (Conv2D) (None, 160, 256, 64) 1792
_________________________________________________________________
block1_conv2 (Conv2D) (None, 160, 256, 64) 36928
_________________________________________________________________
block1_pool (MaxPooling2D) (None, 80, 128, 64) 0
_________________________________________________________________
block2_conv1 (Conv2D) (None, 80, 128, 128) 73856
_________________________________________________________________
block2_conv2 (Conv2D) (None, 80, 128, 128) 147584
_________________________________________________________________
block2_pool (MaxPooling2D) (None, 40, 64, 128) 0
_________________________________________________________________
block3_conv1 (Conv2D) (None, 40, 64, 256) 295168
_________________________________________________________________
block3_conv2 (Conv2D) (None, 40, 64, 256) 590080
_________________________________________________________________
block3_conv3 (Conv2D) (None, 40, 64, 256) 590080
_________________________________________________________________
block3_conv4 (Conv2D) (None, 40, 64, 256) 590080
_________________________________________________________________
block3_pool (MaxPooling2D) (None, 20, 32, 256) 0
_________________________________________________________________
block4_conv1 (Conv2D) (None, 20, 32, 512) 1180160
_________________________________________________________________
block4_conv2 (Conv2D) (None, 20, 32, 512) 2359808
_________________________________________________________________
block4_conv3 (Conv2D) (None, 20, 32, 512) 2359808
_________________________________________________________________
block4_conv4 (Conv2D) (None, 20, 32, 512) 2359808
_________________________________________________________________
block4_pool (MaxPooling2D) (None, 10, 16, 512) 0
_________________________________________________________________
conv2d_transpose_5 (Conv2DTr (None, 10, 16, 128) 1048704
_________________________________________________________________
up_sampling2d_5 (UpSampling2 (None, 20, 32, 128) 0
_________________________________________________________________
conv2d_transpose_6 (Conv2DTr (None, 20, 32, 64) 131136
_________________________________________________________________
up_sampling2d_6 (UpSampling2 (None, 40, 64, 64) 0
_________________________________________________________________
conv2d_transpose_7 (Conv2DTr (None, 40, 64, 32) 32800
_________________________________________________________________
up_sampling2d_7 (UpSampling2 (None, 80, 128, 32) 0
_________________________________________________________________
conv2d_transpose_8 (Conv2DTr (None, 80, 128, 16) 8208
_________________________________________________________________
up_sampling2d_8 (UpSampling2 (None, 160, 256, 16) 0
_________________________________________________________________
conv2d_2 (Conv2D) (None, 160, 256, 1) 401
=================================================================
Total params: 11,806,401
Trainable params: 11,806,401
Non-trainable params: 0
更新3:
y_true示例: