I'm using the TensorFlow library in Python. After creating a model and saving it, if I load the entire model, I get inconsistent results.
First of all, I'm using TensorFlow version 2.3.0.
The code I'm using is the following:
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense, Flatten, Conv2D, MaxPooling2D
from tensorflow.keras.callbacks import ModelCheckpoint
def get_new_model():
model = Sequential([
Conv2D(filters=16, input_shape=(32, 32, 3), kernel_size=(3, 3), activation='relu', name='conv_1'),
Conv2D(filters=8, kernel_size=(3, 3), activation='relu', name='conv_2'),
MaxPooling2D(pool_size=(4, 4), name='pool_1'),
Flatten(name='flatten'),
Dense(units=32, activation='relu', name='dense_1'),
Dense(units=10, activation='softmax', name='dense_2')
])
model.compile(optimizer='adam', loss='sparse_categorical_crossentropy', metrics=['accuracy'])
return model
checkpoint_path = 'model_checkpoints'
checkpoint = ModelCheckpoint(filepath=checkpoint_path, save_weights_only=False, frequency='epoch', verbose=1)
model = get_new_model()
model.fit(x_train, y_train, epochs=3, callbacks=[checkpoint])
Until here no problem, I create the model, compile it and train it with some data. I also use ModelCheckpoint to save the model.
The problem comes when I try the following
from tensorflow.keras.models import load_model
model2 = load_model(checkpoint_path)
model.evaluate(x_test, y_test)
model2.evaluate(x_test, y_test)
Then, the first evaluation returns an accuracy of 0.477, while the other returns an accuracy of 0.128, which is essentially a random choice.
What is the problem here? The two models are supposed to be identical, and actually, they give the same value for the loss function up to 16 decimal places.
Related
Newbie to machine learning here.
I'm currently working on a diagnostic machine learning framework using 3D-CNNs on fMRI imaging. My dataset consists of 636 images right now, and I'm trying to distinguish between control and affected (binary classification). However, when I tried to train my model, after every epoch, my accuracy remains at 48.13%, no matter what I do. Additionally, over the epoch, the accuracy decreases from 56% to 48.13%.
So far, I have tried:
changing my loss functions (poisson, categorical cross entropy, binary cross entropy, sparse categorical cross entropy, mean squared error, mean absolute error, hinge, hinge squared)
changing my optimizer (I've tried Adam and SGD)
changing the number of layers
using weight regularization
changing from ReLU to leaky ReLU (I thought perhaps that could help if this was a case of overfitting)
Nothing has worked so far.
Any tips? Here's my code:
#importing important packages
import tensorflow as tf
import os
import keras
from keras.models import Sequential
from keras.layers import Dense, Flatten, Conv3D, MaxPooling3D, Dropout, BatchNormalization, LeakyReLU
import numpy as np
from keras.regularizers import l2
from sklearn.utils import compute_class_weight
from keras.optimizers import SGD
BATCH_SIZE = 64
input_shape=(64, 64, 40, 20)
# Create the model
model = Sequential()
model.add(Conv3D(64, kernel_size=(3,3,3), activation='relu', input_shape=input_shape, kernel_regularizer=l2(0.005), bias_regularizer=l2(0.005), data_format = 'channels_first', padding='same'))
model.add(MaxPooling3D(pool_size=(2, 2, 2)))
model.add(Conv3D(64, kernel_size=(3,3,3), activation='relu', input_shape=input_shape, kernel_regularizer=l2(0.005), bias_regularizer=l2(0.005), data_format = 'channels_first', padding='same'))
model.add(MaxPooling3D(pool_size=(2, 2, 2)))
model.add(BatchNormalization(center=True, scale=True))
model.add(Conv3D(64, kernel_size=(3,3,3), activation='relu', input_shape=input_shape, kernel_regularizer=l2(0.005), bias_regularizer=l2(0.005), data_format = 'channels_first', padding='same'))
model.add(MaxPooling3D(pool_size=(2, 2, 2)))
model.add(Conv3D(64, kernel_size=(3,3,3), activation='relu', input_shape=input_shape, kernel_regularizer=l2(0.005), bias_regularizer=l2(0.005), data_format = 'channels_first', padding='same'))
model.add(MaxPooling3D(pool_size=(2, 2, 2)))
model.add(BatchNormalization(center=True, scale=True))
model.add(Flatten())
model.add(BatchNormalization(center=True, scale=True))
model.add(Dense(128, activation='relu', kernel_regularizer=l2(0.01), bias_regularizer=l2(0.01)))
model.add(Dropout(0.5))
model.add(Dense(128, activation='sigmoid', kernel_regularizer=l2(0.01), bias_regularizer=l2(0.01)))
model.add(Dense(1, activation='softmax', kernel_regularizer=l2(0.01), bias_regularizer=l2(0.01)))
# Compile the model
model.compile(optimizer = keras.optimizers.sgd(lr=0.000001), loss='poisson', metrics=['accuracy', tf.keras.metrics.Precision(), tf.keras.metrics.Recall()])
# Model Testing
history = model.fit(X_train, y_train, batch_size=BATCH_SIZE, epochs=50, verbose=1, shuffle=True)
The main issue is that you are using softmax activation with 1 neuron. Change it to sigmoid with binary_crossentropy as a loss function.
At the same time, bear in mind that you are using Poisson loss function, which is suitable for regression problems not classification ones. Ensure that you detect the exact scenario that your are trying to solve.
Softmax with one neuron makes the model illogical and only use one of the sigmoid activation functions or Softmax in the last layer
I am trying to use this to classify the images into two categories. Also I applied model.fit() function but its showing error.
ValueError: A target array with shape (90, 1) was passed for an output of shape (None, 10) while using as loss binary_crossentropy. This loss expects targets to have the same shape as the output.
import tensorflow as tf
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense, Dropout, Activation, Flatten, Conv2D, MaxPooling2D, LSTM
import pickle
import numpy as np
X = np.array(pickle.load(open("X.pickle","rb")))
Y = np.array(pickle.load(open("Y.pickle","rb")))
#scaling our image data
X = X/255.0
model = Sequential()
model.add(Conv2D(64 ,(3,3), input_shape = (300,300,1)))
# model.add(MaxPooling2D(pool_size = (2,2)))
model.add(tf.keras.layers.Reshape((16, 16*512)))
model.add(LSTM(128, activation='relu', return_sequences=True))
model.add(Dropout(0.2))
model.add(LSTM(128, activation='relu'))
model.add(Dropout(0.2))
model.add(Dense(32, activation='relu'))
model.add(Dropout(0.2))
model.add(Dense(10, activation='softmax'))
opt = tf.keras.optimizers.Adam(lr=1e-3, decay=1e-5)
model.compile(loss='binary_crossentropy', optimizer=opt,
metrics=['accuracy'])
# model.summary()
model.fit(X, Y, batch_size=32, epochs = 2, validation_split=0.1)
If your problem is categorical, your issue is that you are using binary_crossentropy instead of categorical_crossentropy; ensure that you do have a categorical instead of a binary classification problem.
Also, please note that if your labels are in simple integer format like [1,2,3,4...] and not one-hot-encoded, your loss_function should be sparse_categorical_crossentropy, not categorical_crossentropy.
If you do have a binary classification problem, like said in the error of the above ensure that:
Loss is binary_crossentroy + Dense(1,activation='sigmoid')
Loss is categorical_crossentropy + Dense(2,activation='softmax')
Im trying to save my deep learning model and be able to load it. When I try to load it I get the following error
load_model("test.mod",True/False,False)
I have the following test code:
import tensorflow as tf
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense, Dropout, LSTM
import keras
load data set
mnist = tf.keras.datasets.mnist # mnist is a dataset of 28x28 images of handwritten digits and their labels
(x_train, y_train),(x_test, y_test) = mnist.load_data() # unpacks images to x_train/x_test and labels to y_train/y_test
normlize it
x_train = x_train/255.0
x_test = x_test/255.0
print(x_train.shape)
print(x_train[0].shape)
model = Sequential()
explain input shape
model.add(LSTM(128, input_shape=(x_train.shape[1:]), activation='relu', return_sequences=True))
what does drop out do????
model.add(Dropout(0.2))
model.add(LSTM(128, activation='relu'))
model.add(Dropout(0.1))
model.add(Dense(32, activation='relu'))
model.add(Dropout(0.2))
model.add(Dense(10, activation='softmax'))
opt = tf.keras.optimizers.Adam(lr=0.001, decay=1e-6)
model.compile(
loss='sparse_categorical_crossentropy',
optimizer=opt,
metrics=['accuracy'],
)
model.fit(x_train,
y_train,
epochs=3,
validation_data=(x_test, y_test))
model.save("test.mod")
from keras.models import load_model
model = load_model("test.mod",True/False,False)
I have a numeric health record dataset. I used a 1D CNN keras model for the classification step.
I am giving a reproductible example in Python:
import tensorflow as tf
import keras
from keras.models import Sequential
from keras.layers import Conv1D, Activation, Flatten, Dense
import numpy as np
a = np.array([[0,1,2,9,3], [0,5,1,33,6], [1, 12,1,8,9]])
train = np.reshape(a[:,1:],(a[:,1:].shape[0], a[:,1:].shape[1],1))
y_train = keras.utils.to_categorical(a[:,:1])
model = Sequential()
model.add(Conv1D(filters=2, kernel_size=2, strides=1, activation='relu', padding="same", input_shape=(train.shape[1], 1), kernel_initializer='he_normal'))
model.add(Flatten())
model.add(Dense(2, activation='sigmoid'))
model.compile(loss=keras.losses.binary_crossentropy,
optimizer=keras.optimizers.Adam(lr=0.001, beta_1=0.9, beta_2=0.999, amsgrad=False),
metrics=['accuracy'])
model.fit(train, y_train, epochs=3, verbose=1)
I am getting this error when I apply lime to my 1D CNN model
IndexError: boolean index did not match indexed array along dimension 1; dimension is 4 but corresponding boolean dimension is 1
import lime
import lime.lime_tabular
explainer = lime.lime_tabular.LimeTabularExplainer(train)
Is there a solution ?
I did some minor changes to your initial code (changed from keras to tensorflow.keras)
import tensorflow as tf
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Conv1D, Activation, Flatten, Dense
import numpy as np
a = np.array([[0,1,2,9,3], [0,5,1,33,6], [1, 12,1,8,9]])
train = np.reshape(a[:,1:],(a[:,1:].shape[0], a[:,1:].shape[1],1))
y_train = tf.keras.utils.to_categorical(a[:,:1])
model = Sequential()
model.add(Conv1D(filters=2, kernel_size=2, strides=1, activation='relu',
padding="same", input_shape=(train.shape[1], 1),
kernel_initializer='he_normal'))
model.add(Flatten())
model.add(Dense(2, activation='sigmoid'))
model.compile(loss=tf.keras.losses.binary_crossentropy,
optimizer=tf.keras.optimizers.Adam(lr=0.001, beta_1=0.9,
beta_2=0.999, amsgrad=False),
metrics=['accuracy'])
model.fit(train, y_train, epochs=3, verbose=1)
Then I added some test data because you don't want to train and test your LIME model on the same data
b = np.array([[1,4,5,3,2], [1,4,2,55,1], [7, 3,22,3,10]])
test = np.reshape(b[:,1:],(b[:,1:].shape[0], b[:,1:].shape[1],1))
Here I show how the RecurrentTabularExplainer can be trained
import lime
from lime import lime_tabular
explainer = lime_tabular.RecurrentTabularExplainer(train,training_labels=y_train, feature_names=["random clf"],
discretize_continuous=False, feature_selection='auto', class_names=['class 1','class 2'])
Then you can run your LIME model on one of the examples in your test data:
exp = explainer.explain_instance(np.expand_dims(test[0],axis=0), model.predict, num_features=10)
and finally display the predictions
exp.show_in_notebook()
or just printing the prediction
print(exp.as_list())
You should try lime_tabular.RecurrentTabularExplainer instead of LimeTabularExplainer. It is an explainer for keras-style recurrent neural networks. Check out the examples in LIME documentation for better understanding. Good luck:)
Even though Ive tried to initialise Tensorboard several ways - from tensorflow.keras.callbacks import TensorBoard , from keras.callbacks import TensorBoard , atd. when initialising right before model.fit function I always get ModuleNotFoundError or similar.
I've tried several different directories for Tensorboard logs, several ways to initialize via Keras layer
import tensorflow as tf
#sess = tf.Session()
from tensorflow.keras.datasets import cifar10
from tensorflow.keras.preprocessing.image import ImageDataGenerator
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense, Dropout, Activation, Flatten
from tensorflow.keras.layers import Conv2D, MaxPooling2D
# more info on callbakcs: https://keras.io/callbacks/ model saver is cool too.
#from tensorflow.keras.callbacks import TensorBoard
from keras.callbacks import TensorBoard
import pickle
import time
NAME = "Cats-vs-dogs-CNN"
pickle_in = open("X.pickle","rb")
X = pickle.load(pickle_in)
pickle_in = open("y.pickle","rb")
y = pickle.load(pickle_in)
X = X/255.0
model = Sequential()
model.add(Conv2D(256, (3, 3), input_shape=X.shape[1:]))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Conv2D(256, (3, 3)))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Flatten()) # this converts our 3D feature maps to 1D feature vectors
model.add(Dense(64))
model.add(Dense(1))
model.add(Activation('sigmoid'))
model.compile(loss='binary_crossentropy',
optimizer='adam',
metrics=['accuracy'],
)
tensor_board = TensorBoard(log_dir='./Graph', histogram_freq=0, write_graph=True, write_images=True)
model.fit(X, y,
batch_size=16,
epochs=1,
validation_split=0.3,
callbacks=[tensor_board])
Its based on tutorial https://pythonprogramming.net/tensorboard-analysis-deep-learning-python-tensorflow-keras/?completed=/convolutional-neural-network-deep-learning-python-tensorflow-keras/
Original code was written like this:
tensorboard = TensorBoard(log_dir="logs/{}".format(NAME))
model.compile(loss='binary_crossentropy',
optimizer='adam',
metrics=['accuracy'],
)
model.fit(X, y,
batch_size=32,
epochs=10,
validation_split=0.3,
callbacks=[tensorboard])
But I was getting an error that callbacks=[tensorboard]) is not found so I've kinda deducted it is because I use Tensorflow2.0 and this is based on r1 version.
Dave,
You have to use
tensorflow.keras.callbacks.TensorBoard
you are using directly keras api, like you try to use two different APIs.
Please try to follow the documentation of tf 2.0 api, it works well.
https://www.tensorflow.org/tensorboard/r2/get_started