在 tensorflow 和 keras 上訓練我的 Rnn 模型時遇到問題

Question

這是代碼：

import pandas as pd 
from sklearn import preprocessing  
from collections import deque
import numpy as np
import random
import time
import tensorflow as tf
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense, Dropout, LSTM, BatchNormalization
from tensorflow.keras.callbacks import TensorBoard, ModelCheckpoint 


# SETTING THE EVIRONMENT FOR  
SEQ_LEN = 60
FUTURE_PERIOD_PREDICT = 3 
RATIO_TO_PREDICT = "LTC-USD"
EPOCHS = 20
BATCH_SIZE = 64

NAME = f"{SEQ_LEN}-SEQ-{FUTURE_PERIOD_PREDICT}-PRED-{int(time.time())}"







def classify(current, future):
    if float(future) > float(current): 
        return 1
    else:
        return 0

def preprocess_df(df):
    df = df.drop('future', 1)

    for col in df.columns:
        if col != "target":
            df[col] = df[col].pct_change()
            df.dropna(inplace=True)
            df[col] = preprocessing.scale(df[col].values)

    df.dropna(inplace=True)

    sequential_data = []
    prev_days = deque(maxlen=SEQ_LEN)
    for i in df.values:
        prev_days.append([n for n in i[:-1]])
        if len(prev_days) == SEQ_LEN:
            sequential_data.append([np.array(prev_days), i[-1]])


    random.shuffle(sequential_data)

    buys = []
    sells = []

    for seq, target in sequential_data:
        if target == 0:
            sells.append([seq, target])
        elif target == 1:
            buys.append([seq, target])


    random.shuffle(buys)
    random.shuffle(sells)

    lower = min(len(buys), len(sells))

    buys = buys[:lower]
    sells = sells[:lower]

    sequential_data = buys+sells
    random.shuffle(sequential_data)

    X = []
    y = []

    for seq, target in sequential_data:
        X.append(seq)
        y.append(target)

    return np.array(X), y


main_df = pd.DataFrame()
ratios = ["BTC-USD", "LTC-USD", "ETH-USD", "BCH-USD"]
for ratio in ratios:
    #print(ratio)
    dataset = f"crypto_data/{ratio}.csv"

    df = pd.read_csv(dataset, names=["time", "low", "high", "open", "close", "volume"])
    #print(df.head())
    df.rename(columns={"close": f"{ratio}_close", "volume":f"{ratio}_volume"}, inplace=True)

    df.set_index("time", inplace=True)
    df = df[[f"{ratio}_close", f"{ratio}_volume" ]]
    #print(df.head())

    if len(main_df) == 0:
        main_df = df
    else:
        main_df = main_df.join(df)

    #print(main_df.head)


# be cuz it has trancated our columns i invert using(c) it to column view
#just for viewing process
#for c in main_df.columns:
 #   print(c)

main_df['future'] = main_df[f"{RATIO_TO_PREDICT}_close"].shift(-FUTURE_PERIOD_PREDICT)

main_df['target'] = list(map(classify, main_df[f"{RATIO_TO_PREDICT}_close"], main_df["future"]))

times = sorted(main_df.index.values)
last_5pct = times[-int(0.05*len(times))]

validation_main_df = main_df[(main_df.index >= last_5pct)]
main_df = main_df[(main_df.index < last_5pct)]


train_x, train_y = preprocess_df(main_df)
validation_x, validation_y = preprocess_df(validation_main_df)

print(f"train data: {len(train_x)} validation: {len(validation_x)}")
print(f"Dont buys: {train_y.count(0)}, buys: {train_y.count(1)}")
print(f"VALIDATION Dont buys: {validation_y.count(0)}, buys: {validation_y.count(1)}")

model = Sequential()
model.add(LSTM(128, input_shape=(train_x.shape[1:]), activation="relu", return_sequences=True))
model.add(Dropout(0.2))
model.add(BatchNormalization()) 


model.add(LSTM(128,  input_shape=(train_x.shape[1:]), activation="relu", return_sequences=True))
model.add(Dropout(0.2))
model.add(BatchNormalization()) 


model.add(LSTM(128,  input_shape=(train_x.shape[1:]), activation="relu", return_sequences=True))
model.add(Dropout(0.2))
model.add(BatchNormalization()) 


model.add(Dense(32, activation="relu"))
model.add(Dropout(0.2))  


model.add(Dense(2, activation="softmax"))

opt = tf.keras.optimizers.Adam(lr=0.001, decay=1e-6)

model.compile(loss='sparse_categorical_crossentropy', 
              optimizer=opt,
              metrics=['accuracy'])

tensorboard = TensorBoard(log_dir=f'logs\{NAME}')

filepath = "RNN_Final-{epoch:02d}"
checkpoint = ModelCheckpoint("models\{}.model".format(filepath), verbose=1, save_best_only=True, mode='max')

train_y= np.asarray(train_y) 
validation_y= np.asarray(validation_y)

history = model.fit(
    train_x, train_y,
    batch_size=BATCH_SIZE,
    epochs=EPOCHS,

    validation_data=(validation_x, validation_y),

    callbacks=[tensorboard, checkpoint])

this is the error:

InvalidArgumentError：斷言失敗：[] [條件 x == y 沒有按元素保持：] [x (loss/dense_1_loss/SparseSoftmaxCrossEntropyWithLogits/Shape_1:0) = ] [64 1] [y (loss/dense_1_loss/SparseSoftmaxCrossEntropyWithLogits/ :0) = ] [64 60] [[node loss/dense_1_loss/SparseSoftmaxCrossEntropyWithLogits/assert_equal/Assert/Assert 函數調用棧：distributed_function

Answer 1

在向各個方向拉我的頭發后，我想出了如何解決這個問題。

在上一個 LSTM 中，您不想返回序列。 你的最后一層應該是：

model.add(LSTM(128, input_shape=X_train.shape[1:]))