我正在尝试对顺序数据进行多类分类,以根据源的累积读取来了解某些事件的来源。
我使用具有 64 个单元的简单 LSTM 层和具有与目标相同数量的单元的密集层。该模型似乎没有学到任何东西,因为准确度仍然约为 1%。 def create_model(): 模型 = 顺序()
model.add(LSTM(64, return_sequences=False))
model.add(Dense(8))
model.add(Activation("softmax"))
model.compile(
loss="categorical_crossentropy",
optimizer=Adam(lr=0.00001),
metrics=["accuracy"],
)
return model
我尝试将学习率更改为非常小的值(0.001、0.0001、1e-5)并进行更大时期的训练,但没有观察到准确性的变化。我在这里错过了什么吗?是我的数据预处理不正确还是模型创建有问题?
预先感谢您的帮助。
数据集
Accumulated- Source-1 Source-2 Source-3
Reading
217 0 0 0
205 0 0 0
206 0 0 0
231 0 0 0
308 0 0 1
1548 0 0 1
1547 0 0 1
1530 0 0 1
1545 0 0 1
1544 0 0 1
1527 0 0 1
1533 0 0 1
1527 0 0 1
1527 0 0 1
1534 0 0 1
1520 0 0 1
1524 0 0 1
1523 0 0 1
205 0 0 0
209 0 0 0
.
.
.
我创建了一个 SEQ_LEN=5 的滚动窗口数据集,将其馈送到 LSTM 网络:
rolling_window labels
[205, 206, 217, 205, 206] [0, 0, 0]
[206, 217, 205, 206, 231] [0, 0, 0]
[217, 205, 206, 231, 308] [0, 0, 1]
[205, 206, 231, 308, 1548] [0, 0, 1]
[206, 231, 308, 1548, 1547] [0, 0, 1]
[231, 308, 1548, 1547, 1530] [0, 0, 1]
[308, 1548, 1547, 1530, 1545] [0, 0, 1]
[1548, 1547, 1530, 1545, 1544] [0, 0, 1]
[1547, 1530, 1545, 1544, 1527] [0, 0, 1]
[1530, 1545, 1544, 1527, 1533] [0, 0, 1]
[1545, 1544, 1527, 1533, 1527] [0, 0, 1]
[1544, 1527, 1533, 1527, 1527] [0, 0, 1]
[1527, 1533, 1527, 1527, 1534] [0, 0, 1]
[1533, 1527, 1527, 1534, 1520] [0, 0, 1]
[1527, 1527, 1534, 1520, 1524] [0, 0, 1]
[1527, 1534, 1520, 1524, 1523] [0, 0, 1]
[1534, 1520, 1524, 1523, 1520] [0, 0, 1]
[1520, 1524, 1523, 1520, 205] [0, 0, 0]
.
.
.
重塑数据集
X_train = train_df.rolling_window.values
X_train = X_train.reshape(X_train.shape[0], 1, SEQ_LEN)
Y_train = train_df.labels.values
Y_train = Y_train.reshape(Y_train.shape[0], 3)
型号
def create_model():
model = Sequential()
model.add(LSTM(64, input_shape=(1, SEQ_LEN), return_sequences=True))
model.add(Activation("relu"))
model.add(Flatten())
model.add(Dense(3))
model.add(Activation("softmax"))
model.compile(
loss="categorical_crossentropy", optimizer=Adam(lr=0.01), metrics=["accuracy"]
)
return model
培训
model = create_model()
model.fit(X_train, Y_train, batch_size=512, epochs=5)
训练输出
Epoch 1/5
878396/878396 [==============================] - 37s 42us/step - loss: 0.2586 - accuracy: 0.0173
Epoch 2/5
878396/878396 [==============================] - 36s 41us/step - loss: 0.2538 - accuracy: 0.0175
Epoch 3/5
878396/878396 [==============================] - 36s 41us/step - loss: 0.2538 - accuracy: 0.0176
Epoch 4/5
878396/878396 [==============================] - 37s 42us/step - loss: 0.2537 - accuracy: 0.0177
Epoch 5/5
878396/878396 [==============================] - 38s 43us/step - loss: 0.2995 - accuracy: 0.0174
[编辑-1]
尝试了 Max 的建议后,结果如下(损失和准确率仍然没有改变)
推荐型号
def create_model():
model = Sequential()
model.add(LSTM(64, return_sequences=False))
model.add(Dense(8))
model.add(Activation("softmax"))
model.compile(
loss="categorical_crossentropy",
optimizer=Adam(lr=0.001),
metrics=["accuracy"],
)
return model
X_火车
array([[[205],
[217],
[209],
[215],
[206]],
[[217],
[209],
[215],
[206],
[206]],
[[209],
[215],
[206],
[206],
[211]],
...,
[[175],
[175],
[173],
[176],
[174]],
[[175],
[173],
[176],
[174],
[176]],
[[173],
[176],
[174],
[176],
[173]]])
Y_train(P.S:实际上有8个目标类。上面的例子是对实际问题的简化)
array([[0, 0, 0, ..., 0, 0, 0],
[0, 0, 0, ..., 0, 0, 0],
[0, 0, 0, ..., 0, 0, 0],
...,
[0, 0, 0, ..., 0, 0, 0],
[0, 0, 0, ..., 0, 0, 0],
[0, 0, 0, ..., 0, 0, 0]])
训练输出
Epoch 1/5
878396/878396 [==============================] - 15s 17us/step - loss: 0.1329 - accuracy: 0.0190
Epoch 2/5
878396/878396 [==============================] - 15s 17us/step - loss: 0.1313 - accuracy: 0.0190
Epoch 3/5
878396/878396 [==============================] - 16s 18us/step - loss: 0.1293 - accuracy: 0.0190
Epoch 4/5
878396/878396 [==============================] - 16s 18us/step - loss: 0.1355 - accuracy: 0.0195
Epoch 5/5
878396/878396 [==============================] - 15s 18us/step - loss: 0.1315 - accuracy: 0.0236
[编辑-2]
根据 Max 和 Marcin 的以下建议,准确率大多保持在 3% 以下。虽然只有十分之一,但准确率高达 95%。这完全取决于第一个纪元开始时的准确性。如果它没有在正确的位置开始梯度下降,就无法达到良好的精度。我需要使用不同的初始化程序吗?改变学习率不会带来可重复的结果。
建议:
1. 缩放/标准化 X_train(完成)
2.不重塑Y_train(完成)
3. LSTM层的单元更少(从64个减少到16个)
4. 拥有更小的batch_size(从512减少到64)
缩放X_train
array([[[ 0.01060734],
[ 0.03920736],
[ 0.02014085],
[ 0.03444091],
[ 0.01299107]],
[[ 0.03920728],
[ 0.02014073],
[ 0.03444082],
[ 0.01299095],
[ 0.01299107]],
[[ 0.02014065],
[ 0.0344407 ],
[ 0.01299086],
[ 0.01299095],
[ 0.02490771]],
...,
[[-0.06089251],
[-0.06089243],
[-0.06565897],
[-0.05850889],
[-0.06327543]],
[[-0.06089251],
[-0.06565908],
[-0.05850898],
[-0.06327555],
[-0.05850878]],
[[-0.06565916],
[-0.0585091 ],
[-0.06327564],
[-0.05850889],
[-0.06565876]]])
未重塑Y_train
array([[0, 0, 0, ..., 0, 0, 0],
[0, 0, 0, ..., 0, 0, 0],
[0, 0, 0, ..., 0, 0, 0],
...,
[0, 0, 0, ..., 0, 0, 0],
[0, 0, 0, ..., 0, 0, 0],
[0, 0, 0, ..., 0, 0, 0]])
具有较少 LSTM 单元的模型
def create_model():
model = Sequential()
model.add(LSTM(16, return_sequences=False))
model.add(Dense(8))
model.add(Activation("softmax"))
model.compile(
loss="categorical_crossentropy", optimizer=Adam(lr=0.001), metrics=["accuracy"]
)
return model
训练输出
Epoch 1/5
878396/878396 [==============================] - 26s 30us/step - loss: 0.1325 - accuracy: 0.0190
Epoch 2/5
878396/878396 [==============================] - 26s 29us/step - loss: 0.1352 - accuracy: 0.0189
Epoch 3/5
878396/878396 [==============================] - 26s 30us/step - loss: 0.1353 - accuracy: 0.0192
Epoch 4/5
878396/878396 [==============================] - 26s 29us/step - loss: 0.1365 - accuracy: 0.0197
Epoch 5/5
878396/878396 [==============================] - 27s 31us/step - loss: 0.1378 - accuracy: 0.0201
序列应该是 LSTM 的第一个维度(输入数组的第二个维度),即:
重塑数据集
X_train = train_df.rolling_window.values
X_train = X_train.reshape(X_train.shape[0], SEQ_LEN, 1)
Y_train = train_df.labels.values
Y_train = Y_train.reshape(Y_train.shape[0], 3)
LSTM 不需要输入形状。 LSTM 默认具有“tanh”激活,这通常是一个不错的选择。
型号
def create_model():
model = Sequential()
model.add(LSTM(64, return_sequences=True))
model.add(Flatten())
model.add(Dense(3))
model.add(Activation("softmax"))
model.compile(loss="categorical_crossentropy", optimizer=Adam(lr=0.01), metrics=["accuracy"])
return model
也许不使用 Flatten() 层而是对 LSTM 使用 return_sequences=False 会是更好的选择。试试吧。
还可以尝试对数据的特征缩放进行预处理。数据值看起来相当大。