时间戳

首页 > 解决方案 > 使用张量流 keras 的 python 代码中没有名为“tensorflow.python.keras.engine.base_layer_v1”的模块

python - 使用张量流 keras 的 python 代码中没有名为“tensorflow.python.keras.engine.base_layer_v1”的模块

问题描述

嗨，我在 google colab 中执行此代码，但出现此错误No module named 'tensorflow.python.keras.engine.base_layer_v1' in python code with tensor flow keras

我确实使用了 tensorflow.keras 而不是 keras，因为我使用 tensorflow v=2.1.0 和 keras v=2.3.0-tf

i tried both tensorflow  v=2.1.0 and v=2.2.0-rc2
import tensorflow as tf
from tensorflow import keras
from tensorflow.keras import layers
from tensorflow.keras.models import Sequential, load_model
from tensorflow.keras.callbacks import EarlyStopping
from tensorflow.keras.layers import Dense, Embedding, LSTM, SpatialDropout1D
from sklearn.model_selection import train_test_split

MAX_NB_WORDS=50000
EMBEDDING_DIM=100

model = tf.keras.Sequential()
model.add(Embedding(MAX_NB_WORDS, EMBEDDING_DIM, input_length=train.shape[1]))
model.add(SpatialDropout1D(0.2))
model.add(LSTM(100, dropout=0.2, recurrent_dropout=0.2))
model.add(Dense(13, activation='softmax'))
model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])
print(model.summary())

epochs = 5
batch_size = 64
history = model.fit(x_train, y_train, epochs=epochs, batch_size=batch_size, validation_split=0.1, callbacks=[EarlyStopping(monitor='val_loss', patience=3, min_delta=0.0001)])

accr = model.evaluate(x_test,y_test)
print('Test set\n  Loss: {:0.3f}\n  Accuracy: {:0.3f}'.format(accr[0],accr[1]))

标签： pythontensorflowdeep-learninggoogle-colaboratorytf.keras

解决方案

我在使用 gaborNet-CNN 时遇到了类似的错误。我厌倦了追随，它在我的情况下有效。

import numpy as np
from matplotlib import pyplot as plt
from tqdm import tqdm
import keras
from keras import backend as K
from keras import activations, initializers, regularizers, constraints, metrics
from keras.datasets import cifar10
from keras.preprocessing.image import ImageDataGenerator
from keras.models import Sequential, Model
from keras.layers import (Dense, Dropout, Activation, Flatten, Reshape, Layer,
                          BatchNormalization, LocallyConnected2D,
                          ZeroPadding2D, Conv2D, MaxPooling2D, Conv2DTranspose,
                          GaussianNoise, UpSampling2D, Input)
from keras.utils import conv_utils, multi_gpu_model
from keras.layers import Lambda
from keras.engine import Layer, InputSpec
from keras.legacy import interfaces

推荐阅读