我正在使用(keras-self-attention)在KERAS中实施注意力LSTM。训练模型后如何可视化注意力部位?这是一个时间序列预测案例。
from keras.models import Sequential
from keras_self_attention import SeqWeightedAttention
from keras.layers import LSTM, Dense, Flatten
model = Sequential()
model.add(LSTM(activation = 'tanh' ,units = 200, return_sequences = True,
input_shape = (TrainD[0].shape[1], TrainD[0].shape[2])))
model.add(SeqSelfAttention())
model.add(Flatten())
model.add(Dense(1, activation = 'relu'))
model.compile(optimizer = 'adam', loss = 'mse')
答案 0 :(得分:4)
一种方法是获取给定输入的SeqSelfAttention
的输出,并组织它们以便显示每通道的预测(请参见下文)。有关更高级的内容,请查看iNNvestigate library(包括使用示例)。
show_features_1D
获取layer_name
(可以是子字符串)层输出,并显示每个通道的预测(标记),沿x轴具有时间步长,沿y轴具有输出值。
input_data
=形状为(1, input_shape)
的数据的单批 prefetched_outputs
=已经获取的图层输出;覆盖input_data
max_timesteps
=最多可显示的时间步数max_col_subplots
=沿着水平方向的子图的最大数量equate_axes
=强制所有x和y轴相等(建议进行公平比较)show_y_zero
=是否将y = 0显示为红线channel_axis
=图层要素尺寸(例如LSTM的units
,这是最后一个)scale_width, scale_height
=缩放显示的图像的宽度和高度dpi
=图像质量(每英寸点数)视觉效果(如下)说明:
print(outs_1)
显示所有幅值都非常小,并且变化不大,因此,包括y = 0点和等轴坐标会产生线状视觉效果,这可以解释为自我关注是偏向的。batch_shape
而不是input_shape
定义模型会删除打印形状中的所有?
,我们可以看到第一个输出的形状为(10, 60, 240)
,第二个输出的形状为(10, 240, 240)
。换句话说,第一个输出返回LSTM通道注意,第二个输出“时间步注意”。下面的热图结果可以解释为显示注意“冷却”w.r.t。时间步长。 SeqWeightedAttention 更容易可视化,但是可视化并不多。您需要摆脱上面的Flatten
才能使其正常工作。注意的输出形状然后变为(10, 60)
和(10, 240)
-您可以使用它们的简单直方图plt.hist
(只需确保您排除批次尺寸-即喂(60,)
或(240,)
。
from keras.layers import Input, Dense, LSTM, Flatten, concatenate
from keras.models import Model
from keras.optimizers import Adam
from keras_self_attention = SeqSelfAttention
import numpy as np
ipt = Input(shape=(240,4))
x = LSTM(60, activation='tanh', return_sequences=True)(ipt)
x = SeqSelfAttention(return_attention=True)(x)
x = concatenate(x)
x = Flatten()(x)
out = Dense(1, activation='sigmoid')(x)
model = Model(ipt,out)
model.compile(Adam(lr=1e-2), loss='binary_crossentropy')
X = np.random.rand(10,240,4) # dummy data
Y = np.random.randint(0,2,(10,1)) # dummy labels
model.train_on_batch(X, Y)
outs = get_layer_outputs(model, 'seq', X[0:1], 1)
outs_1 = outs[0]
outs_2 = outs[1]
show_features_1D(model,'lstm',X[0:1],max_timesteps=100,equate_axes=False,show_y_zero=False)
show_features_1D(model,'lstm',X[0:1],max_timesteps=100,equate_axes=True, show_y_zero=True)
show_features_2D(outs_2[0]) # [0] for 2D since 'outs_2' is 3D
def show_features_1D(model=None, layer_name=None, input_data=None,
prefetched_outputs=None, max_timesteps=100,
max_col_subplots=10, equate_axes=False,
show_y_zero=True, channel_axis=-1,
scale_width=1, scale_height=1, dpi=76):
if prefetched_outputs is None:
layer_outputs = get_layer_outputs(model, layer_name, input_data, 1)[0]
else:
layer_outputs = prefetched_outputs
n_features = layer_outputs.shape[channel_axis]
for _int in range(1, max_col_subplots+1):
if (n_features/_int).is_integer():
n_cols = int(n_features/_int)
n_rows = int(n_features/n_cols)
fig, axes = plt.subplots(n_rows,n_cols,sharey=equate_axes,dpi=dpi)
fig.set_size_inches(24*scale_width,16*scale_height)
subplot_idx = 0
for row_idx in range(axes.shape[0]):
for col_idx in range(axes.shape[1]):
subplot_idx += 1
feature_output = layer_outputs[:,subplot_idx-1]
feature_output = feature_output[:max_timesteps]
ax = axes[row_idx,col_idx]
if show_y_zero:
ax.axhline(0,color='red')
ax.plot(feature_output)
ax.axis(xmin=0,xmax=len(feature_output))
ax.axis('off')
ax.annotate(str(subplot_idx),xy=(0,.99),xycoords='axes fraction',
weight='bold',fontsize=14,color='g')
if equate_axes:
y_new = []
for row_axis in axes:
y_new += [np.max(np.abs([col_axis.get_ylim() for
col_axis in row_axis]))]
y_new = np.max(y_new)
for row_axis in axes:
[col_axis.set_ylim(-y_new,y_new) for col_axis in row_axis]
plt.show()
def show_features_2D(data, cmap='bwr', norm=None,
scale_width=1, scale_height=1):
if norm is not None:
vmin, vmax = norm
else:
vmin, vmax = None, None # scale automatically per min-max of 'data'
plt.imshow(data, cmap=cmap, vmin=vmin, vmax=vmax)
plt.xlabel('Timesteps', weight='bold', fontsize=14)
plt.ylabel('Attention features', weight='bold', fontsize=14)
plt.colorbar(fraction=0.046, pad=0.04) # works for any size plot
plt.gcf().set_size_inches(8*scale_width, 8*scale_height)
plt.show()
def get_layer_outputs(model, layer_name, input_data, learning_phase=1):
outputs = [layer.output for layer in model.layers if layer_name in layer.name]
layers_fn = K.function([model.input, K.learning_phase()], outputs)
return layers_fn([input_data, learning_phase])
SeqWeightedAttention示例:
ipt = Input(batch_shape=(10,240,4))
x = LSTM(60, activation='tanh', return_sequences=True)(ipt)
x = SeqWeightedAttention(return_attention=True)(x)
x = concatenate(x)
out = Dense(1, activation='sigmoid')(x)
model = Model(ipt,out)
model.compile(Adam(lr=1e-2), loss='binary_crossentropy')
X = np.random.rand(10,240,4) # dummy data
Y = np.random.randint(0,2,(10,1)) # dummy labels
model.train_on_batch(X, Y)
outs = get_layer_outputs(model, 'seq', X, 1)
outs_1 = outs[0][0] # additional index since using batch_shape
outs_2 = outs[1][0]
plt.hist(outs_1, bins=500); plt.show()
plt.hist(outs_2, bins=500); plt.show()