What shape does my Input layer need to be? I keep getting ValueError: Layer "model" expects 1 input(s), but it received 2 input tensors
What shape does my Input layer need to be? I keep getting ValueError: Layer "model" expects 1 input(s), but it received 2 input tensors
这是从 this project and converting to the Keras functional API. I un-subclassed the model from here 获取代码并从 inputs 开始重新定义它。
我 运行 遇到的问题是当我尝试拟合模型时出现以下错误。
ValueError: Layer "model" expects 1 input(s), but it received 2 input tensors. Inputs received:
[<tf.Tensor 'IteratorGetNext:0' shape=(None,) dtype=int64>, <tf.Tensor 'IteratorGetNext:1' shape=(None,) dtype=int64>]
所以我的初始张量的形状一定是错误的 - 但我不确定如何继续，因为我尝试了几种不同的方法，但似乎没有任何意义。
import math
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
from tensorflow import keras
from tensorflow.keras import layers
# Import CF Model Architecture
from CFModel import CFModel
RNG_SEED = 42
# Reading ratings file
ratings = pd.read_csv('data/ratings.csv', sep='\t', encoding='latin-1',
usecols=['user_id', 'movie_id', 'user_emb_id', 'movie_emb_id', 'rating'])
max_userid = ratings['user_id'].drop_duplicates().max()
max_movieid = ratings['movie_id'].drop_duplicates().max()
# Reading ratings file
users = pd.read_csv('data/users.csv', sep='\t', encoding='latin-1',
usecols=['user_id', 'gender', 'zipcode', 'age_desc', 'occ_desc'])
# Reading ratings file
movies = pd.read_csv('data/movies.csv', sep='\t', encoding='latin-1',
usecols=['movie_id', 'title', 'genres'])
# Create training set
shuffled_ratings = ratings.sample(frac=1., random_state=RNG_SEED)
# Shuffling users
Users = shuffled_ratings['user_emb_id'].values
print( 'Users:', Users, ', shape =', Users.shape)
# Users: [5411 5439 367 ... 853 4032 785] , shape = (1000209,)
# Shuffling movies
Movies = shuffled_ratings['movie_emb_id'].values
print( 'Movies:', Movies, ', shape =', Movies.shape)
# Movies: [2682 903 3716 ... 3101 3478 1390] , shape = (1000209,)
# Shuffling ratings
Ratings = shuffled_ratings['rating'].values
print( 'Ratings:', Ratings, ', shape =', Ratings.shape)
# Ratings: [2 5 4 ... 3 5 4] , shape = (1000209,)
K_FACTORS = 100 # The number of dimensional embeddings for movies and users
TEST_USER = 2000 # A random test user (user_id = 2000)
# Define model
inputs = layers.Input(shape=(1000209, 100)) # What should this input be?
embeddingUsers = layers.Embedding(max_userid, K_FACTORS, input_length=1)
usersEmbedded = embeddingUsers(inputs)
embeddingMovies = layers.Embedding(max_movieid, K_FACTORS, input_length=1)
moviesEmbedded = embeddingMovies(inputs)
inputs = layers.Dot(axes=1)([usersEmbedded, moviesEmbedded])
outputs = layers.Dense(5, activation='relu')(inputs)
model = keras.Model(inputs=inputs, outputs=outputs)
keras.utils.plot_model(model, "my_first_model_with_shape_info.png", show_shapes=True)
print(model.summary())
# Layer (type) Output Shape Param #
# =================================================================
# input_2 (InputLayer) [(None, 100, 100, 100, 1 0
# 00)]
# dense (Dense) (None, 100, 100, 100, 5) 505
# =================================================================
# Total params: 505
# Trainable params: 505
# Non-trainable params: 0
# _________________________________________________________________
model.compile(optimizer="rmsprop", loss="mse")
history = model.fit(
[Users, Movies],
Ratings,
epochs=10,
batch_size=32,
validation_split=0.2,
)
# ValueError: Layer "model" expects 1 input(s), but it received 2 input tensors. Inputs received:
# [<tf.Tensor 'IteratorGetNext:0' shape=(None,) dtype=int64>, <tf.Tensor 'IteratorGetNext:1' shape=(None,) dtype=int64>]
我认为你混淆了一些东西。 CFModel，您引用并试图将其转换为具有功能 API 的 Model，由两个 Sequential 子模型组成。如果你想将两个输入传递给你的模型，它应该有两个 Input 层：
import tensorflow as tf
max_userid = 5000
max_movieid = 5000
K_FACTORS = 100
user_input = tf.keras.layers.Input(shape=(1,))
movie_input = tf.keras.layers.Input(shape=(1,))
embedding_users = tf.keras.layers.Embedding(max_userid, K_FACTORS, input_length=1)
users_embedded = embedding_users(user_input)
embedding_movies = tf.keras.layers.Embedding(max_movieid, K_FACTORS, input_length=1)
movies_embedded = embedding_movies(movie_input)
inputs = tf.keras.layers.Dot(axes=1)([users_embedded, movies_embedded])
outputs = tf.keras.layers.Dense(5, activation='relu')(inputs)
model = tf.keras.Model(inputs=[user_input, movie_input], outputs=outputs)
tf.keras.utils.plot_model(model, "my_first_model_with_shape_info.png", show_shapes=True)
print(model.summary())
model.compile(optimizer="rmsprop", loss="mse")
history = model.fit(
[Users, Movies],
Ratings,
epochs=10,
batch_size=32,
validation_split=0.2,
)
Model: "model_1"
__________________________________________________________________________________________________
Layer (type) Output Shape Param # Connected to
==================================================================================================
input_4 (InputLayer) [(None, 1)] 0 []
input_5 (InputLayer) [(None, 1)] 0 []
embedding_2 (Embedding) (None, 1, 100) 500000 ['input_4[0][0]']
embedding_3 (Embedding) (None, 1, 100) 500000 ['input_5[0][0]']
dot_1 (Dot) (None, 100, 100) 0 ['embedding_2[0][0]',
'embedding_3[0][0]']
dense_1 (Dense) (None, 100, 5) 505 ['dot_1[0][0]']
==================================================================================================
Total params: 1,000,505
Trainable params: 1,000,505
Non-trainable params: 0
__________________________________________________________________________________________________
None
由于 Users 和 Movies 都具有 (1000209,) 形状，因此 Input 层的输入形状都是 shape=(1,)。这意味着每个样本都包含一个 ID，该 ID 使用 Embedding 层映射到 100 维向量。哦，以防万一这不是故意的，CFModel 在计算点积后不使用 Dense 层。
这是从 this project and converting to the Keras functional API. I un-subclassed the model from here 获取代码并从 inputs 开始重新定义它。
我 运行 遇到的问题是当我尝试拟合模型时出现以下错误。
ValueError: Layer "model" expects 1 input(s), but it received 2 input tensors. Inputs received:
[<tf.Tensor 'IteratorGetNext:0' shape=(None,) dtype=int64>, <tf.Tensor 'IteratorGetNext:1' shape=(None,) dtype=int64>]
所以我的初始张量的形状一定是错误的 - 但我不确定如何继续，因为我尝试了几种不同的方法，但似乎没有任何意义。
import math
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
from tensorflow import keras
from tensorflow.keras import layers
# Import CF Model Architecture
from CFModel import CFModel
RNG_SEED = 42
# Reading ratings file
ratings = pd.read_csv('data/ratings.csv', sep='\t', encoding='latin-1',
usecols=['user_id', 'movie_id', 'user_emb_id', 'movie_emb_id', 'rating'])
max_userid = ratings['user_id'].drop_duplicates().max()
max_movieid = ratings['movie_id'].drop_duplicates().max()
# Reading ratings file
users = pd.read_csv('data/users.csv', sep='\t', encoding='latin-1',
usecols=['user_id', 'gender', 'zipcode', 'age_desc', 'occ_desc'])
# Reading ratings file
movies = pd.read_csv('data/movies.csv', sep='\t', encoding='latin-1',
usecols=['movie_id', 'title', 'genres'])
# Create training set
shuffled_ratings = ratings.sample(frac=1., random_state=RNG_SEED)
# Shuffling users
Users = shuffled_ratings['user_emb_id'].values
print( 'Users:', Users, ', shape =', Users.shape)
# Users: [5411 5439 367 ... 853 4032 785] , shape = (1000209,)
# Shuffling movies
Movies = shuffled_ratings['movie_emb_id'].values
print( 'Movies:', Movies, ', shape =', Movies.shape)
# Movies: [2682 903 3716 ... 3101 3478 1390] , shape = (1000209,)
# Shuffling ratings
Ratings = shuffled_ratings['rating'].values
print( 'Ratings:', Ratings, ', shape =', Ratings.shape)
# Ratings: [2 5 4 ... 3 5 4] , shape = (1000209,)
K_FACTORS = 100 # The number of dimensional embeddings for movies and users
TEST_USER = 2000 # A random test user (user_id = 2000)
# Define model
inputs = layers.Input(shape=(1000209, 100)) # What should this input be?
embeddingUsers = layers.Embedding(max_userid, K_FACTORS, input_length=1)
usersEmbedded = embeddingUsers(inputs)
embeddingMovies = layers.Embedding(max_movieid, K_FACTORS, input_length=1)
moviesEmbedded = embeddingMovies(inputs)
inputs = layers.Dot(axes=1)([usersEmbedded, moviesEmbedded])
outputs = layers.Dense(5, activation='relu')(inputs)
model = keras.Model(inputs=inputs, outputs=outputs)
keras.utils.plot_model(model, "my_first_model_with_shape_info.png", show_shapes=True)
print(model.summary())
# Layer (type) Output Shape Param #
# =================================================================
# input_2 (InputLayer) [(None, 100, 100, 100, 1 0
# 00)]
# dense (Dense) (None, 100, 100, 100, 5) 505
# =================================================================
# Total params: 505
# Trainable params: 505
# Non-trainable params: 0
# _________________________________________________________________
model.compile(optimizer="rmsprop", loss="mse")
history = model.fit(
[Users, Movies],
Ratings,
epochs=10,
batch_size=32,
validation_split=0.2,
)
# ValueError: Layer "model" expects 1 input(s), but it received 2 input tensors. Inputs received:
# [<tf.Tensor 'IteratorGetNext:0' shape=(None,) dtype=int64>, <tf.Tensor 'IteratorGetNext:1' shape=(None,) dtype=int64>]
我认为你混淆了一些东西。 CFModel，您引用并试图将其转换为具有功能 API 的 Model，由两个 Sequential 子模型组成。如果你想将两个输入传递给你的模型，它应该有两个 Input 层：
import tensorflow as tf
max_userid = 5000
max_movieid = 5000
K_FACTORS = 100
user_input = tf.keras.layers.Input(shape=(1,))
movie_input = tf.keras.layers.Input(shape=(1,))
embedding_users = tf.keras.layers.Embedding(max_userid, K_FACTORS, input_length=1)
users_embedded = embedding_users(user_input)
embedding_movies = tf.keras.layers.Embedding(max_movieid, K_FACTORS, input_length=1)
movies_embedded = embedding_movies(movie_input)
inputs = tf.keras.layers.Dot(axes=1)([users_embedded, movies_embedded])
outputs = tf.keras.layers.Dense(5, activation='relu')(inputs)
model = tf.keras.Model(inputs=[user_input, movie_input], outputs=outputs)
tf.keras.utils.plot_model(model, "my_first_model_with_shape_info.png", show_shapes=True)
print(model.summary())
model.compile(optimizer="rmsprop", loss="mse")
history = model.fit(
[Users, Movies],
Ratings,
epochs=10,
batch_size=32,
validation_split=0.2,
)
Model: "model_1"
__________________________________________________________________________________________________
Layer (type) Output Shape Param # Connected to
==================================================================================================
input_4 (InputLayer) [(None, 1)] 0 []
input_5 (InputLayer) [(None, 1)] 0 []
embedding_2 (Embedding) (None, 1, 100) 500000 ['input_4[0][0]']
embedding_3 (Embedding) (None, 1, 100) 500000 ['input_5[0][0]']
dot_1 (Dot) (None, 100, 100) 0 ['embedding_2[0][0]',
'embedding_3[0][0]']
dense_1 (Dense) (None, 100, 5) 505 ['dot_1[0][0]']
==================================================================================================
Total params: 1,000,505
Trainable params: 1,000,505
Non-trainable params: 0
__________________________________________________________________________________________________
None
由于 Users 和 Movies 都具有 (1000209,) 形状，因此 Input 层的输入形状都是 shape=(1,)。这意味着每个样本都包含一个 ID，该 ID 使用 Embedding 层映射到 100 维向量。哦，以防万一这不是故意的，CFModel 在计算点积后不使用 Dense 层。