Potential bug using kernel regularizer

Abierto
  • ¿Algo no está bien?
#352 0 comentarios 0 reacciones 0 asignados Ver en GitHub

Nadie ha tomado este issue todavía.

Evaluación

Dificultad
4/5
Tiempo estimado
3-5 días
Aptitud para principiantes
32/100
Tipo de issue
Error
Claridad
Bastante claro
Estado de actividad
Estancado
Stack tecnológico
python, tensorflow
Área
machine-learning

Línea de trabajo

Comienza ejecutando la reproducción adjunta de code.txt con la combinación de Conv2D kernel_regularizer, MeanSquaredError loss y DPKerasAdamOptimizer, y compárala después con la versión sin el regularizer. Inspecciona el error de incompatibilidad de formas de AddN reportado y determina si esta combinación es compatible. Se considera terminado cuando se haya identificado la causa y se haya proporcionado una corrección verificada o una explicación clara de compatibilidad.

Escrito por el modelo de indexación a partir del texto del issue.

Descripción

I got a ValueError when using TensorFlow to create a model. Based on the error there is a problem that occurs with the kernel regularizer applied on the Conv2D layer and the mean squared error function. I used the L1 regularizer provided by the TensorFlow keras package. I've tried setting different values for the L1 regularization factor and even setting the value to 0, but I get the same error. My model works fine if i get rid of the kernel_regularizer argument. I'm just wondering if this is some type of bug?

Context: Creating a model that predicts phenotype traits given genotypes and phenotypes datasets. The genotype input data has 4276 samples, and the input shape that the model takes is (28220,1). My labels represent the phenotype data. The labels include 4276 samples with 20 as the number of phenotype traits in the dataset. In this model we use differential privacy(DP) and add it to a CNN model which uses the Mean squared error loss function and the DPKerasAdamOptimizer to add DP.

Here is my code I also will provide an attachment with the code:

`from future import absolute_import
from future import division
from future import print_function

!pip install tensorflow-privacy
import numpy as np
import tensorflow as tf
from tensorflow_privacy import *
import tensorflow_privacy

from matplotlib import pyplot as plt
import pylab as pl
import numpy as np
import pandas as pd

from tensorflow.keras.models import Model
from tensorflow.keras import datasets, layers, models, losses
from tensorflow.keras import backend as bke
from tensorflow.keras.optimizers import Adam
from tensorflow.keras.regularizers import l1, l2, l1_l2

from sklearn import preprocessing
from sklearn.model_selection import train_test_split

batch_size = 32
epochs = 4
microbatches = 8

inChannel = 1
kr = 0
num_kernels=8
drop_perc=0.25
dim = 1

l2_norm_clip = 1.5
noise_multiplier = 1.3

learning_rate = 0.25
latent_dim = 0

def print_datashape():
print('genotype data: ', genotype_data.shape)
print('phenotype data: ', single_pheno.shape)

genotype_data = tf.random.uniform([4276, 28220],1,3, dtype=tf.dtypes.int32)
phenotype_data = tf.random.uniform([4276, 20],-4.359688,34,dtype=tf.dtypes.float32)

genotype_data = genotype_data.numpy()
phenotype_data = phenotype_data.numpy()

small_geno = genotype_data
single_pheno = phenotype_data[:, 1]

print_datashape()

df = small_geno
min_max_scaler = preprocessing.MinMaxScaler()
df = min_max_scaler.fit_transform(df)
scaled_pheno = min_max_scaler.fit_transform(single_pheno.reshape(-1,1)).reshape(-1)

feature_size= df.shape[1]
df = df.reshape(-1, feature_size, 1, 1)

train_data,test_data,train_Y,test_Y = train_test_split(df, scaled_pheno, test_size=0.2, random_state=13)
train_X,valid_X,train_Y,valid_Y = train_test_split(train_data, train_Y, test_size=0.2, random_state=13)

def print_shapes():
print('train_X: {}'.format(train_X.shape))
print('train_Y: {}'.format(train_Y.shape))
print('valid_X: {}'.format(valid_X.shape))
print('valid_Y: {}'.format(valid_Y.shape))

input_shape= (feature_size, dim, inChannel)

predictor = tf.keras.Sequential()
predictor.add(layers.Conv2D(num_kernels, (5,1), padding='same', strides=(12, 1), activation='relu', kernel_regularizer=tf.keras.regularizers.L1(kr),input_shape= input_shape))
predictor.add(layers.AveragePooling2D(pool_size=(2,1)))
predictor.add(layers.Dropout(drop_perc))
predictor.add(layers.Flatten())
predictor.add(layers.Dense(int(feature_size / 4), activation='relu'))
predictor.add(layers.Dropout(drop_perc))
predictor.add(layers.Dense(int(feature_size / 10), activation='relu'))
predictor.add(layers.Dropout(drop_perc))
predictor.add(layers.Dense(1))

mse = tf.keras.losses.MeanSquaredError(reduction=tf.keras.losses.Reduction.NONE)
optimizer = DPKerasAdamOptimizer(learning_rate=learning_rate, l2_norm_clip=l2_norm_clip, noise_multiplier=noise_multiplier, num_microbatches=microbatches)

predictor.compile(loss=mse, optimizer=optimizer, metrics=['mse'])

predictor.summary()

print_shapes()

predictor.fit(train_X, train_Y,batch_size=batch_size,epochs=epochs,verbose=1, validation_data=(valid_X, valid_Y))`

ValueError: Shapes must be equal rank, but are 1 and 0 From merging shape 0 with other shapes. for '{{node AddN}} = AddN[N=2, T=DT_FLOAT](mean_squared_error/weighted_loss/Mul, conv2d_2/kernel/Regularizer/mul)' with input shapes: [?], [].

code.txt

Lenguaje dominante
Python
Estrellas
2k
Forks
477
Merge medio
17 h 24 min
PR fusionados (30 d)
4

Preparar el entorno

Primeros pasos

  1. Lee el issue completo y luego la guía de contribución del proyecto.
  2. Comenta en el issue que vas a ocuparte — evita que dos personas hagan lo mismo.
  3. Haz un fork del repositorio y trabaja en una rama.
  4. Abre un pull request que haga referencia al número del issue.

Más de tensorflow/privacy

Todos los issues de tensorflow/privacy

Issues similares

Más issues de Python

Recibe los nuevos issues en tu correo

Un resumen breve de issues de GitHub para principiantes.