[英]Reason for Validation loss is going high?
我對深度學習模型非常陌生,並嘗試使用 LSTM 訓練多標簽分類文本 model。我有大約 2600 條記錄,有 4 個類別。使用 80% 進行訓練,使用 rest 進行驗證。
代碼中沒有什么復雜的,即正在讀取 csv,標記數據並饋送到 model。 但是在 3-4 個 epoch 之后,驗證損失變得大於 1,而 train_loss 趨於零。據我搜索,這是過度擬合的情況。 為了克服這個問題,我嘗試了不同的層,改變了單位。但問題仍然存在。 如果我停在 1-2 個時期,那么預測就會出錯。
下面是我的 model 創建代碼:-
ACCURACY_THRESHOLD = 0.75
class myCallback(tf.keras.callbacks.Callback):
def on_epoch_end(self, epoch, logs={}):
print(logs.get('val_accuracy'))
fname='Arabic_Model_'+str(logs.get('val_accuracy'))+'.h5'
if(logs.get('val_accuracy') > ACCURACY_THRESHOLD):
#print("\nWe have reached %2.2f%% accuracy, so we will stopping training." %(acc_thresh*100))
#self.model.stop_training = True
self.model.save(fname)
#from google.colab import files
#files.download(fname)
# The maximum number of words to be used. (most frequent)
MAX_NB_WORDS = vocab_len
# Max number of words in each complaint.
MAX_SEQUENCE_LENGTH = 50
# This is fixed.
EMBEDDING_DIM = 100
callbacks = myCallback()
def create_model(vocabulary_size, seq_len):
model = models.Sequential()
model.add(Embedding(input_dim=MAX_NB_WORDS+1, output_dim=EMBEDDING_DIM,
input_length=seq_len,mask_zero=True))
model.add(GRU(units=64, return_sequences=True))
model.add(Dropout(0.4))
model.add(LSTM(units=50))
#model.add(LSTM(100))
#model.add(Dropout(0.4))
#Bidirectional(tf.keras.layers.LSTM(embedding_dim))
#model.add(Bidirectional(LSTM(128)))
model.add(Dense(50, activation='relu'))
#model.add(Dense(200, activation='relu'))
model.add(Dense(4, activation='softmax'))
model.compile(loss='categorical_crossentropy', optimizer='adam',
metrics=['accuracy'])
model.summary()
return model
model=create_model(MAX_NB_WORDS, MAX_SEQUENCE_LENGTH)
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
embedding_4 (Embedding) (None, 50, 100) 2018600
_________________________________________________________________
gru_2 (GRU) (None, 50, 64) 31680
_________________________________________________________________
dropout_10 (Dropout) (None, 50, 64) 0
_________________________________________________________________
lstm_6 (LSTM) (None, 14) 4424
_________________________________________________________________
dense_7 (Dense) (None, 50) 750
_________________________________________________________________
dropout_11 (Dropout) (None, 50) 0
_________________________________________________________________
dense_8 (Dense) (None, 4) 204
=================================================================
Total params: 2,055,658
Trainable params: 2,055,658
Non-trainable params: 0
_________________________________________________________________
model.fit(sequences, y_train, validation_data=(sequences_test, y_test),
epochs=25, batch_size=5, verbose=1,
callbacks=[callbacks]
)
如果我能確定克服過度擬合的問題,那將非常有幫助。您可以參考下面的協作以查看完整的代碼:-
https://colab.research.google.com/drive/13N94kBKkHIX2TR5B_lETyuH1QTC5VuRf?usp=sharing
編輯:--- 我現在使用的是我用 gensim 創建的預訓練嵌入層,但現在准確度下降了。另外,我的記錄大小是 4643。
附上以下代碼:- 在這個“English_dict.p”中是我使用 gensim 創建的字典。
embeddings_index=load(open('English_dict.p', 'rb'))
vocab_size=len(embeddings_index)+1
embedding_model = zeros((vocab_size, 100))
for word, i in embedding_matrix.word_index.items():
embedding_vector = embeddings_index.get(word)
if embedding_vector is not None:
embedding_model[i] = embedding_vector
model.add(Embedding(input_dim=MAX_NB_WORDS, output_dim=EMBEDDING_DIM,
weights=[embedding_model],trainable=False,
input_length=seq_len,mask_zero=True))
Model: "sequential_2"
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
embedding_2 (Embedding) (None, 50, 100) 2746300
_________________________________________________________________
gru_2 (GRU) (None, 50, 64) 31680
_________________________________________________________________
dropout_2 (Dropout) (None, 50, 64) 0
_________________________________________________________________
lstm_2 (LSTM) (None, 128) 98816
_________________________________________________________________
dense_3 (Dense) (None, 50) 6450
_________________________________________________________________
dense_4 (Dense) (None, 4) 204
=================================================================
Total params: 2,883,450
Trainable params: 137,150
Non-trainable params: 2,746,300
_________________________________________________________________
如果我做錯了什么,請告訴我。 您可以參考上面的協作以供參考。
是的,這是經典的過擬合。 為什么會發生 - 神經網絡有超過 200 萬個可訓練參數(2 055 658),而您只有 2600 條記錄(您將 80% 用於訓練)。 NN 太大,不是泛化,而是記憶。
怎么解決:
聲明:本站的技術帖子網頁,遵循CC BY-SA 4.0協議,如果您需要轉載,請注明本站網址或者原文地址。任何問題請咨詢:yoyou2525@163.com.