我的資料中的類別有問題，我無法將 Dense softmax 層設定為“3”而不是 3 個類別的“1”。
我認為我的問題與 vectorize_text 有關，但我不完全確定。我也可以假設我沒有正確設定標簽張量。
# Start of data generation
dummy_data = {'text': ['Love', 'Money', 'War'],
'labels': [1,2,3]
}
dummy_data['text'] = dummy_data['text']*500
dummy_data['labels'] = dummy_data['labels']*500
df_train_bogus = pd.DataFrame(dummy_data)
def df_to_dataset(dataframe, shuffle=True, batch_size=32):
ds = tf.data.Dataset.from_tensor_slices(dict(dataframe)).batch(batch_size)
return ds
batch_size = 32
train_ds = df_to_dataset(df_train_bogus, batch_size=batch_size)
val_ds = df_to_dataset(df_train_bogus, batch_size=batch_size)
# Model constants (can be lower but that doesn't matter for this example)
sequence_length = 128
max_features = 20000 # vocab size
embedding_dim = 128
# End of data generation
# Start of vectorization
vectorize_layer = TextVectorization(
standardize = 'lower_and_strip_punctuation',
max_tokens=max_features,
output_mode="int",
output_sequence_length=sequence_length,
)
def vectorize_text(text, labels):
print(text)
print(labels)
text = tf.expand_dims(text, -1)
return vectorize_layer(text), labels
vectorize_layer.adapt(df_train_bogus['text'])
train_ds_vectorized = train_ds.map(lambda x: (vectorize_text(x['text'], x['labels'])))
val_ds_vectorized = val_ds.map(lambda x: (vectorize_text(x['text'], x['labels'])))
"""
Output:
Tensor("args_1:0", shape=(None,), dtype=string)
Tensor("args_0:0", shape=(None,), dtype=int64)
Tensor("args_1:0", shape=(None,), dtype=string)
Tensor("args_0:0", shape=(None,), dtype=int64)
"""
# The model
model = Sequential()
model.add(Embedding(max_features, embedding_dim, input_length=sequence_length))
model.add(LSTM(embedding_dim, input_shape=(None, sequence_length)))
model.add(Dense(3, activation='softmax'))
# Fails with this error:
# ValueError: Shapes (None, 1) and (None, 3) are incompatible
model.summary()
model.compile(loss="categorical_crossentropy",
optimizer="adam",
metrics=["accuracy"]) # model 4
epochs = 10
# Fit the model using the train and test datasets.
history = model.fit(train_ds_vectorized, validation_data=val_ds_vectorized, epochs=epochs)
uj5u.com熱心網友回復：
您的虛擬資料中的標簽導致了問題。如果它們不是單熱編碼，那么我建議改用sparse_categorical_crossentropy損失函式，它適用于整數目標（您已經擁有）。查看檔案以獲取更多資訊。這是一個完整的作業示例：
import tensorflow as tf
import pandas as pd
dummy_data = {'text': ['Love', 'Money', 'War'],
'labels': [0, 1, 2]
}
dummy_data['text'] = dummy_data['text']*500
dummy_data['labels'] = dummy_data['labels']*500
df_train_bogus = pd.DataFrame(dummy_data)
def df_to_dataset(dataframe, shuffle=True, batch_size=32):
ds = tf.data.Dataset.from_tensor_slices(dict(dataframe)).batch(batch_size)
return ds
batch_size = 32
train_ds = df_to_dataset(df_train_bogus, batch_size=batch_size)
val_ds = df_to_dataset(df_train_bogus, batch_size=batch_size)
# Model constants (can be lower but that doesn't matter for this example)
sequence_length = 128
max_features = 20000 # vocab size
embedding_dim = 128
# Start of vectorization
vectorize_layer = tf.keras.layers.TextVectorization(
standardize = 'lower_and_strip_punctuation',
max_tokens=max_features,
output_mode="int",
output_sequence_length=sequence_length,
)
def vectorize_text(text, labels):
print(text)
print(labels)
text = tf.expand_dims(text, -1)
return vectorize_layer(text), labels
vectorize_layer.adapt(df_train_bogus['text'])
train_ds_vectorized = train_ds.map(lambda x: (vectorize_text(x['text'], x['labels'])))
val_ds_vectorized = val_ds.map(lambda x: (vectorize_text(x['text'], x['labels'])))
"""
Output:
Tensor("args_1:0", shape=(None,), dtype=string)
Tensor("args_0:0", shape=(None,), dtype=int64)
Tensor("args_1:0", shape=(None,), dtype=string)
Tensor("args_0:0", shape=(None,), dtype=int64)
"""
model = tf.keras.Sequential()
model.add(tf.keras.layers.Embedding(max_features, embedding_dim, input_length=sequence_length))
model.add(tf.keras.layers.LSTM(embedding_dim, input_shape=(None, sequence_length)))
model.add(tf.keras.layers.Dense(3, activation='softmax'))
model.summary()
model.compile(loss="sparse_categorical_crossentropy",
optimizer="adam",
metrics=["sparse_categorical_accuracy"]) # model 4
epochs = 10
history = model.fit(train_ds_vectorized, validation_data=val_ds_vectorized, epochs=epochs)
"""
Output:
Tensor("args_1:0", shape=(None,), dtype=string)
Tensor("args_0:0", shape=(None,), dtype=int64)
Tensor("args_1:0", shape=(None,), dtype=string)
Tensor("args_0:0", shape=(None,), dtype=int64)
"""
model = tf.keras.Sequential()
model.add(tf.keras.layers.Embedding(max_features, embedding_dim, input_length=sequence_length))
model.add(tf.keras.layers.LSTM(embedding_dim, input_shape=(None, sequence_length)))
model.add(tf.keras.layers.Dense(3, activation='softmax'))
model.summary()
model.compile(loss="sparse_categorical_crossentropy",
optimizer="adam",
metrics=["accuracy"]) # model 4
epochs = 10
history = model.fit(train_ds_vectorized, validation_data=val_ds_vectorized, epochs=epochs)
請注意，您的標簽需要從開始zero到n，因為sparse_categorical_crossentropy產生的最有可能的類的類指標，它可以是0。
更新：準確度 0.333 是正確的，因為您有 3 個類，每個類的樣本數相同。您需要使用更大的資料集來查看任何合理的結果。
uj5u.com熱心網友回復：
你的問題是你的損失函式。Keras 中的分類交叉熵要求類不是 idx 形式，而是作為它們的目標 logits/激活輸出。所以，你的訓練損失應該是這樣的：
from tensorflow.keras.utils import to_categorical
n_classes = 3
y = [0,1,2] #IMPORTANT TO INDEX FROM 0
cat_y = to_categorical(y,n_classes)
array([[1., 0., 0.],
[0., 1., 0.],
[0., 0., 1.]], dtype=float32)
為此，您需要對處理資料的方式進行一些更改，如下所示：
# Start of data generation
dummy_data = {'text': ['Love', 'Money', 'War'],
'labels': [1,2,0]
}
dummy_data['text'] = dummy_data['text']*500
dummy_data['labels'] = dummy_data['labels']*500
dummy_data['labels'] = to_categorical(dummy_data['labels'],3)
def df_to_dataset(dataframe, shuffle=True, batch_size=32):
ds = tf.data.Dataset.from_tensor_slices((dummy_data['text'],dummy_data['labels']))
return ds
batch_size = 32
train_ds = df_to_dataset(dummy_data, batch_size=batch_size)
val_ds = df_to_dataset(dummy_data, batch_size=batch_size)
# Model constants (can be lower but that doesn't matter for this example)
sequence_length = 128
max_features = 20000 # vocab size
embedding_dim = 128
# End of data generation
# Start of vectorization
vectorize_layer = TextVectorization(
standardize = 'lower_and_strip_punctuation',
max_tokens=max_features,
output_mode="int",
output_sequence_length=sequence_length,
)
def vectorize_text(text, labels):
print(text)
print(labels)
text = tf.expand_dims(text, -1)
return vectorize_layer(text), tf.expand_dims(labels, 0)
vectorize_layer.adapt(dummy_data['text'])
train_ds_vectorized = train_ds.map(lambda x,y: vectorize_text(x,y))
val_ds_vectorized = val_ds.map(lambda x,y: vectorize_text(x,y))
轉載請註明出處，本文鏈接：https://www.uj5u.com/qiye/346305.html