问题描述
我想将用tf1编写的笔记本转换为tf2，更具体地说，将 here中的softmax推荐人模型转换为：
这是来自ML课程的，以前的步骤介绍了the logic
我在Mac OS X上有tensorflow版本'2.3.1'
import pandas as pd
import numpy as np
from zipfile import ZipFile
import tensorflow as tf
from tensorflow import keras
from tensorflow.keras import layers
from pathlib import Path
import matplotlib.pyplot as plt
tf.config.experimental_run_functions_eagerly(True)
# tf.random.set_seed(42)
# np.random.seed(42)
# from urllib.request import urlretrieve
# import zipfile
# urlretrieve("http://files.grouplens.org/datasets/movielens/ml-100k.zip","movielens.zip")
# zip_ref = zipfile.ZipFile('movielens.zip',"r")
# zip_ref.extractall()
# print("Done. Dataset contains:")
# print(zip_ref.read('ml-100k/u.info'))
# Load each data set (users,movies,and ratings).
users_cols = ['user_id','age','sex','occupation','zip_code']
users = pd.read_csv(
'ml-100k/u.user',sep='|',names=users_cols,encoding='latin-1')
ratings_cols = ['user_id','movie_id','rating','unix_timestamp']
ratings = pd.read_csv(
'ml-100k/u.data',sep='\t',names=ratings_cols,encoding='latin-1')
# The movies file contains a binary feature for each genre.
genre_cols = [
"genre_unkNown","Action","Adventure","Animation","Children","Comedy","Crime","Documentary","Drama","Fantasy","Film-Noir","Horror","Musical","Mystery","Romance","Sci-Fi","Thriller","War","Western"
]
movies_cols = [
'movie_id','title','release_date',"video_release_date","imdb_url"
] + genre_cols
movies = pd.read_csv(
'ml-100k/u.item',names=movies_cols,encoding='latin-1')
# Since the ids start at 1,we shift them to start at 0.
users["user_id"] = users["user_id"].apply(lambda x: str(x-1))
movies["movie_id"] = movies["movie_id"].apply(lambda x: str(x-1))
movies["year"] = movies['release_date'].apply(lambda x: str(x).split('-')[-1])
ratings["movie_id"] = ratings["movie_id"].apply(lambda x: str(x-1))
ratings["user_id"] = ratings["user_id"].apply(lambda x: str(x-1))
ratings["rating"] = ratings["rating"].apply(lambda x: float(x))
# Compute the number of movies to which a genre is assigned.
genre_occurences = movies[genre_cols].sum().to_dict()
# Since some movies can belong to more than one genre,we create different
# 'genre' columns as follows:
# - all_genres: all the active genres of the movie.
# - genre: randomly sampled from the active genres.
def mark_genres(movies,genres):
def get_random_genre(gs):
active = [genre for genre,g in zip(genres,gs) if g==1]
if len(active) == 0:
return 'Other'
return np.random.choice(active)
def get_all_genres(gs):
active = [genre for genre,gs) if g==1]
if len(active) == 0:
return 'Other'
return '-'.join(active)
movies['genre'] = [
get_random_genre(gs) for gs in zip(*[movies[genre] for genre in genres])]
movies['all_genres'] = [
get_all_genres(gs) for gs in zip(*[movies[genre] for genre in genres])]
mark_genres(movies,genre_cols)
# Create one merged DataFrame containing all the movielens data.
movielens = ratings.merge(movies,on='movie_id').merge(users,on='user_id')
# Utility to split the data into training and test sets.
def split_dataframe(df,holdout_fraction=0.1):
"""Splits a DataFrame into training and test sets.
Args:
df: a dataframe.
holdout_fraction: fraction of dataframe rows to use in the test set.
Returns:
train: dataframe for training
test: dataframe for testing
"""
test = df.sample(frac=holdout_fraction,replace=False,random_state=42)
train = df[~df.index.isin(test.index)]
return train,test
rated_movies = (ratings[["user_id","movie_id"]]
.groupby("user_id",as_index=False)
.aggregate(lambda x: list(x)))
BATCH_SIZE = 32
EMbedDING_SIZE = 35
class softmaxRecommender(keras.Model):
def __init__(self,feature_columns,**kwargs):
super(softmaxRecommender,self).__init__(**kwargs)
self.movie_embedding = layers.DenseFeatures(feature_columns['movie'])
self.other_features = layers.DenseFeatures(feature_columns['other'])
self.hidden_layer = layers.Dense(EMbedDING_SIZE,kernel_initializer=keras.initializers.Truncatednormal(
stddev=1. / np.sqrt(EMbedDING_SIZE) / 10.))
# self.linear = layers.Dense(num_movies,use_bias=True,activation='softmax')
# self.softmax_activation = keras.layers.Activation('softmax')
def call(self,inputs,train=True,**kwargs):
V = self.movie_embedding({'movie_id': inputs['movie_id']})
inputs.pop('movie_id')
other_fts = self.other_features(inputs)
U = tf.concat([V,other_fts],axis=1)
U = self.hidden_layer(U)
logits = tf.matmul(U,self.movie_embedding.get_weights()[0],transpose_b=True)
# logits = self.linear(logits)
# logits = self.softmax_activation(logits)
return logits
def custom_loss(labels,logits):
# labels = tf.reshape(labels,[-1])
# labels_org = labels.copy()
labels = select_random(labels)
# labels = tf.cast(labels,'float32')
labels = tf.reshape(labels,[-1,1])
# cce = keras.losses.SparseCategoricalCrossentropy(from_logits=True)
# preds = tf.argmax(logits,axis=1)
# preds = tf.cast(preds,'float32')
# loss = cce(y_true=labels,y_pred=logits)
loss = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(
logits=logits,labels=labels))
return loss
years_dict = {
movie: year for movie,year in zip(movies["movie_id"],movies["year"])
}
genres_dict = {
movie: genres.split('-')
for movie,genres in zip(movies["movie_id"],movies["all_genres"])
}
def select_random(x):
"""Selectes a random elements from each row of x."""
def to_float(x):
return tf.cast(x,tf.float32)
def to_int(x):
return tf.cast(x,tf.int64)
batch_size = tf.shape(x)[0]
rn = tf.range(batch_size)
nnz = to_float(tf.math.count_nonzero(x >= 0,axis=1))
rnd = tf.random.uniform([batch_size])
ids = tf.stack([to_int(rn),to_int(nnz * rnd)],axis=1)
return to_int(tf.gather_nd(x,ids))
def make_embedding_col(key,embedding_dim):
categorical_col = tf.feature_column.categorical_column_with_vocabulary_list(
key=key,vocabulary_list=list(set(list(movies[key].values))),num_oov_buckets=0)
return tf.feature_column.embedding_column(
categorical_column=categorical_col,dimension=embedding_dim,initializer=keras.initializers.Truncatednormal(
stddev=1. / np.sqrt(embedding_dim) / 10.),# default initializer: trancated normal with stddev=1/sqrt(dimension)
combiner='mean')
def make_dataset(ratings):
"""Creates a batch of examples.
Args:
ratings: A DataFrame of ratings such that examples["movie_id"] is a list of
movies rated by a user.
batch_size: The batch size.
"""
def pad(x,fill):
return pd.DataFrame.from_dict(x).fillna(fill).values
movie = []
year = []
genre = []
label = []
for movie_ids in ratings["movie_id"].values:
movie.append(movie_ids)
genre.append([x for movie_id in movie_ids for x in genres_dict[movie_id]])
year.append([years_dict[movie_id] for movie_id in movie_ids])
label.append([int(movie_id) for movie_id in movie_ids])
features = {
"movie_id": pad(movie,""),"year": pad(year,"genre": pad(genre,}
y = pad(label,-1)
# y = select_random(y)
# print('y.nunique:',len(np.unique(y.numpy())))
return features,y
train_rated_movies,test_rated_movies = split_dataframe(rated_movies)
x_train,y_train = make_dataset(train_rated_movies)
x_val,y_val = make_dataset(test_rated_movies)
# create two separate DenseFeatures in model to be able to access movie_embeddings
feature_cols = {
'movie': [make_embedding_col("movie_id",35)],'other': [make_embedding_col("genre",3),make_embedding_col("year",2)]
}
model = softmaxRecommender(feature_columns=feature_cols)
model.compile(
loss=custom_loss,optimizer=keras.optimizers.SGD(.1,clipnorm=1)
# loss=keras.losses.SparseCategoricalCrossentropy(from_logits=True),clipnorm=1)
)
# batch_x1 = {
# 'movie_id':x_train['movie_id'][:32],# 'year':x_train['year'][:32],# 'genre':x_train['genre'][:32]
# }
#
# batch_y1 = y_train[:32]
#
# logits = model(batch_x1)
# loss = custom_loss(batch_y1,logits)
#
# batch_x2 = {
# 'movie_id':x_train['movie_id'][32:64],# 'year':x_train['year'][32:64],# 'genre':x_train['genre'][32:64]
# }
#
# batch_y2 = y_train[32:64]
#
# logits = model(batch_x2)
# loss = custom_loss(batch_y2,logits)
history = model.fit(
x=x_train,y=y_train,batch_size=32,epochs=10,verbose=2,validation_data=(x_val,y_val),)
上述带有{_1}}且具有custom_loss的模型会导致梯度爆炸。
我还尝试在模型类中添加softmax激活，并在对tf.nn.softmax_cross_entropy_with_logits函数中的标签执行keras.losses.SparseCategoricalCrossentropy(from_logits=True)时使用select_random一次，而不是每批处理一次。这种方法使重量保持稳定。如果我使用make_dataset而未在logit中添加softmax激活，则损失会再次爆炸。这可能是因为矩阵中的所有值都太小了，以至于softmax赋予了它们相等的概率。
我对keras.losses.SparseCategoricalCrossentropy及其keras.Model方法的理解可能是错误的，并且/或者是我的call()层应用程序。我知道随着损失成倍增加，可能是数据集出了问题，但是数据准备步骤是直接从原始代码中复制的。
非常感谢您的帮助！
解决方法
暂无找到可以解决该程序问题的有效方法，小编努力寻找整理中！
如果你已经找到好的解决方法，欢迎将解决方案带上本链接一起发送给小编。
小编邮箱:dio#foxmail.com (将#修改为@）