我對此很陌生，我不理解/看到任何解決此問題的方法。該錯誤特別指出：
InvalidArgumentError: required broadcastable shapes
[[node Equal
(defined at c:\Users\Connor\Documents\StockIQ\venv\lib\site-packages\keras\metrics.py:3609)
]] [Op:__inference_train_function_141873]
似乎它可能與我輸入的形狀有關：
print(train_x.shape)
print(train_y.shape)
print(validation_x.shape)
print(validation_y.shape)
----
(77922, 60, 8)
(77922,)
(3860, 60, 8)
(3860,)
這是我的訓練宣告：
#save model
tensorboard = TensorBoard(log_dir="logs/{}".format(NAME))
filepath = "RNN_Final-{epoch:02d}-{val_acc:.3f}" # unique file name that will include the epoch and the validation acc for that epoch
checkpoint = ModelCheckpoint("models/{}.model".format(filepath, monitor='val_acc', verbose=1, save_best_only=True, mode='max')) # saves only the best ones
history = model.fit(
train_x, train_y,
batch_size=BATCH_SIZE,
epochs=EPOCHS,
validation_data=(validation_x, validation_y),
)
對此的任何幫助都會很棒-我確定我缺少一些簡單的東西。如果有幫助，我在下面附上了完整的檔案：
import tensorflow as tf
import numpy as np
import pandas as pd
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense, Dropout, LSTM, BatchNormalization
from tensorflow.keras.callbacks import TensorBoard
from tensorflow.keras.callbacks import ModelCheckpoint
from functools import reduce
from sklearn import preprocessing
from collections import deque
import random
import time
# Prediction Variables
SEQ_LEN = 60
FUTURE_PERIOUD_PREDICT = 3
RATIO_TO_PREDICT = 'LTC-USD'
EPOCHS = 10
BATCH_SIZE = 64
NAME = f"{SEQ_LEN}-SEQ-{FUTURE_PERIOUD_PREDICT}-PRED-{int(time.time())}"
# joining 4 tables to show user potential relatioships b/w coins
main_df = pd.DataFrame() # begin empty
ratios = ["BTC-USD", "LTC-USD", "BCH-USD", "ETH-USD"] # the 4 ratios we want to consider
for ratio in ratios: # begin iteration
dataset = f'crypto_data/{ratio}.csv' # get the full path to the file.
df = pd.read_csv(dataset, names=['time', 'low', 'high', 'open', 'close', 'volume']) # read in specific file
# rename volume and close to include the ticker so we can still which close/volume is which:
df.rename(columns={"close": f"{ratio}_close", "volume": f"{ratio}_volume"}, inplace=True)
df.set_index("time", inplace=True) # set time as index so we can join them on this shared time
df = df[[f"{ratio}_close", f"{ratio}_volume"]] # ignore the other columns besides price and volume
if len(main_df)==0: # if the dataframe is empty
main_df = df # then it's just the current df
else: # otherwise, join this data to the main one
main_df = main_df.join(df)
main_df.fillna(method="ffill", inplace=True) # if there are gaps in data, use previously known values
main_df.dropna(inplace=True)
main_df.head()
# Add result and target columns
# %%
def classify(current, future):
if float(future) > float(current):
return 1
else:
return 0
main_df['future'] = main_df[f'{RATIO_TO_PREDICT}_close'].shift(-FUTURE_PERIOUD_PREDICT) #adding result column
main_df['target'] = list(map(classify, main_df[f'{RATIO_TO_PREDICT}_close'], main_df['future'])) #adding target column
main_df.head()
# seperating training and testing data
# *note the eval data is in the FUTURE of training since it's the same dataset
times = sorted(main_df.index.values)
last_5pct = times[-int(0.05*len(times))]
validation_main_df = main_df[(main_df.index >= last_5pct)]
train_main_df = main_df[(main_df.index < last_5pct)]
# normalize, sequence, and balance data
def preprocess_df(df):
df = df.drop('future', axis=1)
# normalize data
for col in df.columns: # normalizing all columns (except target since that's already binary)
if col != 'target':
df[col] = df[col].pct_change()
df.dropna(inplace=True)
df[col] = preprocessing.scale(df[col].values)
df.dropna(inplace=True)
# sequencing (scaling) data
sequential_data = []
prev_days = deque(maxlen=SEQ_LEN) # this builds a list and then pops new records in and out to keep the same list length
for i in df.values:
prev_days.append([n for n in i[:-1]]) # take all columns excpet target
if len(prev_days) == SEQ_LEN:
sequential_data.append([np.array(prev_days), i[-1]])
random.shuffle(sequential_data)
# balance data
buys = []
sells = []
for seq, target in sequential_data: # generate two lists to compare buys vs sells
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: #seperate features and labels into X & Y lists
X.append(seq)
Y.append(target)
return np.array(X), np.array(Y)
train_x, train_y = preprocess_df(train_main_df)
validation_x, validation_y = preprocess_df(validation_main_df)
# Build model
#adding layers
model = Sequential()
model.add(LSTM(128, input_shape=(train_x.shape[1:]), return_sequences=True))
model.add(Dropout(0.2))
model.add(BatchNormalization())
model.add(LSTM(128, input_shape=(train_x.shape[1:]), return_sequences=True))
model.add(Dropout(0.2))
model.add(BatchNormalization())
model.add(LSTM(128, input_shape=(train_x.shape[1:]), return_sequences=True))
model.add(Dropout(0.1))
model.add(BatchNormalization())
model.add(Dense(32, activation="tanh"))
model.add(Dropout(0.2))
model.add(Dense(2, activation='softmax'))
# set optimizers
opt = tf.keras.optimizers.Adam(lr=0.001, decay=1e-6)
# compile model
model.compile(
loss='sparse_categorical_crossentropy',
optimizer=opt,
metrics=['accuracy']
)
# Train Model
#save model
tensorboard = TensorBoard(log_dir="logs/{}".format(NAME))
filepath = "RNN_Final-{epoch:02d}-{val_acc:.3f}" # unique file name that will include the epoch and the validation acc for that epoch
checkpoint = ModelCheckpoint("models/{}.model".format(filepath, monitor='val_acc', verbose=1, save_best_only=True, mode='max')) # saves only the best ones
history = model.fit(
train_x, train_y,
batch_size=BATCH_SIZE,
epochs=EPOCHS,
validation_data=(validation_x, validation_y),
)
uj5u.com熱心網友回復：
由于您的標簽是標量，因此將最后一層更改為輸出定標器：
model.add(Dense(1, activation='sigmoid'))
并更改損失函式：
loss='binary_crossentropy'
你的模型將是：
#adding layers
model = Sequential()
model.add(LSTM(128, input_shape=(train_x.shape[1:]), return_sequences=True))
model.add(Dropout(0.2))
model.add(BatchNormalization())
model.add(LSTM(128, return_sequences=True))
model.add(Dropout(0.2))
model.add(BatchNormalization())
model.add(LSTM(128, return_sequences=False))
model.add(Dropout(0.1))
model.add(BatchNormalization())
model.add(Dense(32, activation="tanh"))
model.add(Dropout(0.2))
model.add(Dense(1, activation='sigmoid'))
uj5u.com熱心網友回復：
我發現這解決了這個問題。我的標簽格式不正確：
“如果你正在做二元交叉熵，那么你的資料集可能有 2 個類并且錯誤即將到來，因為你的標簽向量（在測驗和訓練中）具有 [0,1,0,1,1,1, 0,0,1,...]。要對二進制標簽進行一次熱編碼，可以使用以下函式：Labels = tf.one_hot(Labels, depth=2)"
我在我的火車和驗證標簽上都使用了它，它至少正在運行。不知道模型是否表現良好哈哈！
感謝大家對此的投入：）
轉載請註明出處，本文鏈接：https://www.uj5u.com/qiye/406137.html
標籤：