import tensorflow as tf
from tensorflow.keras import layers, Input, Model, Sequential
from tensorflow.data.experimental import make_csv_dataset
head = Input(shape=620, name="head")
x = layers.Dense(600)(head)
y= layers.Dense(600)(x)
target = layers.Dense(105542, name="articles", kernel_initializer=tf.keras.initializers.Zeros())(x)
model = tf.keras.Model(
inputs=[head],
outputs=[target]
)
model.compile(optimizer='Adam', loss=tf.keras.losses.SparseCategoricalCrossentropy())
data = make_csv_dataset(['../inputs/inputs_1.csv','../inputs/target.csv'], label_name='common_column', batch_size=5)
model.fit(data, epochs=1, batch_size=5)
There is no way this works because it doesn't have a definition for x and y columns. Can't load into ram so don't suggest from tensors or dictionary (tried already). Documentation is clear as night, how do I do this?
Related
I am practicing how to create an LSTM model on a univariate series using this dataset from Kaggle: https://www.kaggle.com/sumanthvrao/daily-climate-time-series-data
My issue is that I am unable to get an accurate prediction of the temperature and my loss seems to be going all over the place. I have tried multiple methods including
Ensuring that time series data is stationary
Changing the time steps
Changing the hyperparameters
Using a stacked LSTM model
I am really curious as to what is wrong with my code although I do have a few hypothesis:
I made an error when preprocessing the data
I introduced stationarity wrongly
This dataset requires a multivariate approach
%tensorflow_version 2.x # this line is not required unless you are in a notebook
import tensorflow as tf
from numpy import array
from numpy import argmax
import pandas as pd
import matplotlib.pyplot as plt
import numpy as np
import os
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import LSTM
from tensorflow.keras.layers import Dense
from tensorflow.keras.layers import Flatten
# preparing independent and dependent features
def prepare_data(timeseries_data, n_features):
X, y =[],[]
for i in range(len(timeseries_data)):
# find the end of this pattern
end_ix = i + n_features
# check if we are beyond the sequence
if end_ix > len(timeseries_data)-1:
break
# gather input and output parts of the pattern
seq_x, seq_y = timeseries_data[i:end_ix], timeseries_data[end_ix]
X.append(seq_x)
y.append(seq_y)
return np.array(X), np.array(y)
# preparing independent and dependent features
def prepare_x_input(timeseries_data, n_features):
x = []
for i in range(len(timeseries_data)):
# find the end of this pattern
end_ix = i + n_features
# check if we are beyond the sequence
if end_ix > len(timeseries_data):
break
# gather input and output parts of the pattern
seq_x = timeseries_data[i:end_ix]
x.append(seq_x)
x = x[-1:]
#remove non-stationerity
#x = np.log(x)
return np.array(x)
#read data and filter temperature column
df = pd.read_csv('/content/drive/MyDrive/Colab Notebooks/Weather Parameter/DailyDelhiClimateTrain.csv')
df.head()
temp_df = df.pop('meantemp')
plt.plot(temp_df)
#make data stationery
sta_temp_df = np.log(temp_df).diff()
plt.figure(figsize=(15,5))
plt.plot(sta_temp_df)
print(sta_temp_df)
time_step = 7
x, y = prepare_data(sta_temp_df, time_step)
n_features = 1
x = x.reshape((x.shape[0], x.shape[1], n_features))
model = Sequential()
model.add(LSTM(10, return_sequences=True, input_shape=(time_step, n_features)))
model.add(LSTM(10))
model.add(Dense(16, activation='relu'))
model.add(Dense(32, activation='relu'))
model.add(Dense(1))
model.compile(optimizer='adam', loss='mse')
model.summary()
result = model.fit(x, y, epochs=800)
n_days = 113
pred_temp_df = list(temp_df)
test = sta_temp_df.copy()
sta_temp_df = list(sta_temp_df)
i = 0
while(i<n_days):
x_input = prepare_x_input(sta_temp_df, time_step)
print(x_input)
x_input = x_input.reshape((1, time_step, n_features))
#pass data into model
yhat = model.predict(x_input, verbose=0)
yhat.flatten
print(yhat[0][0])
sta_temp_df.append(yhat[0][0])
i = i+1
sta_temp_df[0] = np.log(temp_df[0])
cum_temp_df = np.exp(np.cumsum(sta_temp_df))
print(cum_temp_df)
My code is shown above. Would really appreciate if someone can identify what I did wrong here!
I made a script in tensorflow 2.x but I had to downconvert it to tensorflow 1.x (tested in 1.14 and 1.15). However, the tf1 version performs very differently (10% accuracy lower on the test set). See also the plot for train and validation performance (diagram is attached below).
Looking at the operations needed for the migration from tf1 to tf2 it seems that only the Adam learning rate may be a problem but I'm defining it explicitly tensorflow migration
I've reproduced the same behavior both locally on GPU and CPU and on colab. The keras used was the one built-in in tensorflow (tf.keras). I've used the following functions (both for train,validation and test), using a sparse categorization (integers):
train_datagen = tf.keras.preprocessing.image.ImageDataGenerator(
horizontal_flip=horizontal_flip,
#rescale=None, #not needed for resnet50
preprocessing_function=None,
validation_split=None)
train_dataset = train_datagen.flow_from_directory(
directory=train_dir,
target_size=image_size,
class_mode='sparse',
batch_size=batch_size,
shuffle=True)
And the model is a simple resnet50 with a new layer on top:
IMG_SHAPE = img_size+(3,)
inputs = Input(shape=IMG_SHAPE, name='image_input',dtype = tf.uint8)
x = tf.cast(inputs, tf.float32)
# not working in this version of keras. inserted in imageGenerator
x = preprocess_input_resnet50(x)
base_model = tf.keras.applications.ResNet50(
include_top=False,
input_shape = IMG_SHAPE,
pooling=None,
weights='imagenet')
# Freeze the pretrained weights
base_model.trainable = False
x=base_model(x)
# Rebuild top
x = GlobalAveragePooling2D(data_format='channels_last',name="avg_pool")(x)
top_dropout_rate = 0.2
x = Dropout(top_dropout_rate, name="top_dropout")(x)
outputs = Dense(num_classes,activation="softmax", name="pred_out")(x)
model = Model(inputs=inputs, outputs=outputs,name="ResNet50_comp")
optimizer = tf.keras.optimizers.Adam(lr=learning_rate)
model.compile(optimizer=optimizer,
loss="sparse_categorical_crossentropy",
metrics=['accuracy'])
And then I'm calling the fit function:
history = model.fit_generator(train_dataset,
steps_per_epoch=n_train_batches,
validation_data=validation_dataset,
validation_steps=n_val_batches,
epochs=initial_epochs,
verbose=1,
callbacks=[stopping])
I've reproduced the same behavior for example with the following full script (applied to my dataset and changed to adam and removed intermediate final dense layer):
deep learning sandbox
The easiest way to replicate this behavior was to enable or disable the following line on a tf2 environment with the same script and add the following line to it. However, I've tested also on tf1 environments (1.14 and 1.15):
tf.compat.v1.disable_v2_behavior()
Sadly I cannot provide the dataset.
Update 26/11/2020
For full reproducibility I've obtained a similar behaviour by means of the food101 (101 categories) dataset enabling tf1 behaviour with 'tf.compat.v1.disable_v2_behavior()'. The following is the script executed with tensorflow-gpu 2.2.0:
#%% ref https://medium.com/deeplearningsandbox/how-to-use-transfer-learning-and-fine-tuning-in-keras-and-tensorflow-to-build-an-image-recognition-94b0b02444f2
import os
import sys
import glob
import argparse
import matplotlib.pyplot as plt
import tensorflow as tf
# enable and disable this to obtain tf1 behaviour
tf.compat.v1.disable_v2_behavior()
from tensorflow.keras import __version__
from tensorflow.keras.applications.resnet50 import ResNet50, preprocess_input
from tensorflow.keras.models import Model
from tensorflow.keras.layers import Dense, GlobalAveragePooling2D
from tensorflow.keras.optimizers import Adam
# since i'm using resnet50 weights from imagenet, i'm using food101 for
# similar but different categorization tasks
# pip install tensorflow-datasets if tensorflow_dataset not found
import tensorflow_datasets as tfds
(train_ds,validation_ds),info= tfds.load('food101', split=['train','validation'], shuffle_files=True, with_info=True)
assert isinstance(train_ds, tf.data.Dataset)
print(train_ds)
#%%
IM_WIDTH, IM_HEIGHT = 224, 224
NB_EPOCHS = 10
BAT_SIZE = 32
def get_nb_files(directory):
"""Get number of files by searching directory recursively"""
if not os.path.exists(directory):
return 0
cnt = 0
for r, dirs, files in os.walk(directory):
for dr in dirs:
cnt += len(glob.glob(os.path.join(r, dr + "/*")))
return cnt
def setup_to_transfer_learn(model, base_model):
"""Freeze all layers and compile the model"""
for layer in base_model.layers:
layer.trainable = False
model.compile(optimizer='rmsprop', loss='sparse_categorical_crossentropy', metrics=['accuracy'])
def add_new_last_layer(base_model, nb_classes):
"""Add last layer to the convnet
Args:
base_model: keras model excluding top
nb_classes: # of classes
Returns:
new keras model with last layer
"""
x = base_model.output
x = GlobalAveragePooling2D()(x)
#x = Dense(FC_SIZE, activation='relu')(x) #new FC layer, random init
predictions = Dense(nb_classes, activation='softmax')(x) #new softmax layer
model = Model(inputs=base_model.input, outputs=predictions)
return model
def train(nb_epoch, batch_size):
"""Use transfer learning and fine-tuning to train a network on a new dataset"""
#nb_train_samples = train_ds.cardinality().numpy()
nb_train_samples=info.splits['train'].num_examples
nb_classes = info.features['label'].num_classes
classes_names = info.features['label'].names
#nb_val_samples = validation_ds.cardinality().numpy()
nb_val_samples = info.splits['validation'].num_examples
#nb_epoch = int(args.nb_epoch)
#batch_size = int(args.batch_size)
def preprocess(features):
#print(features['image'], features['label'])
image = tf.image.resize(features['image'], [224,224])
#image = tf.divide(image, 255)
#print(image)
# data augmentation
image=tf.image.random_flip_left_right(image)
image = preprocess_input(image)
label = features['label']
# for categorical crossentropy
#label = tf.one_hot(label,101,axis=-1)
#return image, tf.cast(label, tf.float32)
return image, label
#pre-processing the dataset to fit a specific image size and 2D labelling
train_generator = train_ds.map(preprocess).batch(batch_size).repeat()
validation_generator = validation_ds.map(preprocess).batch(batch_size).repeat()
#train_generator=train_ds
#validation_generator=validation_ds
#fig = tfds.show_examples(validation_generator, info)
# setup model
base_model = ResNet50(weights='imagenet', include_top=False) #include_top=False excludes final FC layer
model = add_new_last_layer(base_model, nb_classes)
# transfer learning
setup_to_transfer_learn(model, base_model)
history = model.fit(
train_generator,
epochs=nb_epoch,
steps_per_epoch=nb_train_samples//BAT_SIZE,
validation_data=validation_generator,
validation_steps=nb_val_samples//BAT_SIZE)
#class_weight='auto')
#execute
history = train(nb_epoch=NB_EPOCHS, batch_size=BAT_SIZE)
And the performance on food101 dataset:
update 27/11/2020
It's possible to see the discrepancy also in the way smaller oxford_flowers102 dataset:
(train_ds,validation_ds,test_ds),info= tfds.load('oxford_flowers102', split=['train','validation','test'], shuffle_files=True, with_info=True)
Nb: the above plot shows confidences given by running the same training multiple times and evaluatind mean and std to check for the effects on random weights initialization and data augmentation.
Moreover I've tried some hyperparameter tuning on tf2 resulting in the following picture:
changing optimizer (adam and rmsprop)
not applying horizontal flipping aumgentation
deactivating keras resnet50 preprocess_input
Thanks in advance for every suggestion. Here are the accuracy and validation performance on tf1 and tf2 on my dataset:
Update 14/12/2020
I'm sharing the colab for reproducibility on oxford_flowers at the clic of a button:
colab script
I came across something similar, when doing the opposite migration (from TF1+Keras to TF2).
Running this code below:
# using TF2
import numpy as np
from tensorflow.keras.applications.resnet50 import ResNet50
fe = ResNet50(include_top=False, pooling="avg")
out = fe.predict(np.ones((1,224,224,3))).flatten()
sum(out)
>>> 212.3205274187726
# using TF1+Keras
import numpy as np
from keras.applications.resnet50 import ResNet50
fe = ResNet50(include_top=False, pooling="avg")
out = fe.predict(np.ones((1,224,224,3))).flatten()
sum(out)
>>> 187.23898954353717
you can see the same model from the same library on different versions does not return the same value (using sum as a quick check-up). I found the answer to this mysterious behavior in this other SO answer: ResNet model in keras and tf.keras give different output for the same image
Another recommendation I'd give you is, try using pooling from inside applications.resnet50.ResNet50 class, instead of the additional layer in your function, for simplicity, and to remove possible problem-generators :)
am working on a classification problem for binary classes, I have finished the training and testing the model in single images now using the below code
import warnings
import time
from urllib.request import urlopen
import os
import urllib.request
start_time = time.time()
with warnings.catch_warnings():
warnings.filterwarnings("ignore", category=FutureWarning)
import numpy as np
from keras.preprocessing.image import img_to_array, load_img
from keras.models import Sequential
from keras.layers import Dropout, Flatten, Dense, GlobalAveragePooling2D
from keras.applications.vgg16 import VGG16
import tensorflow as tf
import logging
logging.getLogger('tensorflow').disabled = True
img_size = 224
class PersonPrediction:
def __init__(self):
self.class_dictionary = np.load(
'class_indices_vgg.npy',
allow_pickle=True).item()
self.top_model_weights_path = 'v2/weights/bottleneck_fc_model_2020-10-10-05.h5'
self.num_classes = len(self.class_dictionary)
self.model = self.create_model(self.num_classes)
self.graph = tf.compat.v1.get_default_graph()
def create_model(self, num_of_cls):
model = Sequential()
vgg_model = VGG16(include_top=False, weights='imagenet', input_shape=(img_size, img_size, 3))
for layer in vgg_model.layers[:-4]:
layer.trainable = False
model.add(vgg_model)
model.add(GlobalAveragePooling2D())
model.add(Dense(512, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(1, activation='sigmoid'))
return model
def predict(self, path=None, file_name=None):
if path:
image_path = path
path = self.url_to_image(image_path)
else:
path = os.path.join('imgs', file_name)
print("[INFO] loading and preprocessing image...")
image = load_img(path, target_size=(224, 224))
image = img_to_array(image)
# important! otherwise the predictions will be '0'
image = image / 255
image = np.expand_dims(image, axis=0)
label_idx = self.model.predict_classes(image)[0][0]
probability = self.model.predict(image)[0]
inv_map = {v: k for k, v in self.class_dictionary.items()}
label = inv_map[label_idx]
return label, probability[0]
path = 'temp.jpg'
tax_model = PersonPrediction()
label, proba = tax_model.predict(
file_name='frame303.jpg')
print(label, proba)
Problem is I keep getting chaning predictions of both label and accuracy every time I rerun the code, am not sure what is causing that
There are a number of sources that create randomness in the results when training a model. First the weights are randomly initialized so your model is starting from a different point in N space (N is the number of trainable parameters). Second layers like dropout have randomness in terms of which nodes will be nodes will be selected. Some GPU processes particularly with multi-processing can also have some degree of randomness. I have seen a number of posts on getting repeatable results in tensorflow but I have not found one that seems to really work. In general though the results should be reasonably close if your model is working correctly and you run enough epochs. Now once the model is trained and you use it for predictions as long as you use the same trained model you should get identical prediction results.
tensorflow.keras api not working on while creating the layers reference, any other methods of creating layers reference?
code :
layer=keras.layers
Error message : NameError: name 'leyer' is not defined
Full code is pasted here...
import tensorflow as tf
from tensorflow import keras
import pandas as pd
from sklearn.model_selection import KFold
from sklearn.model_selection import cross_val_score
from sklearn.preprocessing import LabelEncoder
import numpy as np
#makin seed values
seed=7
np.random.seed(seed)
#setting up the dataset for training
dataframe=pd.read_csv("../datasets/iris.csv",header=None)
data=dataframe.values
input_x = data[:,0:4]
true_y = data[:,4]
#Encoding the true_y data to one hot encoding
le=LabelEncoder()
le.fit(true_y)
y_encoded = le.transform(true_y)
y_encoded = keras.utils.to_categorical(y_encoded,num_classes=3)
# creating the model
def base_fun():
layer=keras.layers
model = keras.models.Sequential()
model.add(layer.Dense(4,input_dim=4,kernel_initializer='normal',activation='relu'))
model.add(leyer.Dense(3, kernel_initializer='normal', activation='relu'))
estimator=keras.wrappers.scikit_learn.KerasClassifier(build_fn=base_fun,epochs=20,batch_size=10)
kfold = KFold(n_splits=10, shuffle=True, random_state=seed)
result = cross_val_score(estimator, input_x, y_encoded,cv=kfold)
print("Accuracy : %.2%% (%.2%%)" %(result.mean()*100, result.std()*100))
Well, this line:
model.add(leyer.Dnese(3, kernel_initializer='normal', activation='relu'))
has two typos, namely leyer should be layer and Dnese should be Dense like
model.add(layer.Dense(3, kernel_initializer='normal', activation='relu'))
Based on your comment, this line also causes an error:
estimator = keras.wrappers.scikit_learn.KerasClassifier( build_fn = base_fun, epochs = 20, batch_size = 10 )
From the Keras Scikit documentation:
build_fn should construct, compile and return a Keras model, which will then be used to fit/predict.
But you function base_fun() does not return anything. Append this line at the end of base_fun():
return model
As per your comment, the last print line could be changed to this (I don't know the % formatting, I generally use the syntax below):
print( "Accuracy : {:.2%} ({:.2%})".format( result.mean(), result.std() ) )
I'm trying to do a small test with my dataset on Keras Regressor (using TensorFlow), but I'm having a small issue. The error seems to be on the function cross_val_score from scikit. It starts on it and the last error message is:
File "/usr/local/lib/python2.7/dist-packages/Keras-2.0.2-py2.7.egg/keras/backend/tensorflow_backend.py", line 298, in _initialize_variables
variables = tf.global_variables()
AttributeError: 'module' object has no attribute 'global_variables'
My full code is basically the example found in http://machinelearningmastery.com/regression-tutorial-keras-deep-learning-library-python/ with small changes.
I've looked upon the " 'module' object has no attribute 'global_variables' " error and it seems to be about the Tensorflow version, but I'm using the most recent one (1.0) and there is no function in the code that works directly with tf that I can change. Below is my full code, is there anyway i can change it so it works? Thanks for the help
import numpy
import pandas
import sys
from keras.models import Sequential
from keras.layers import Dense
from keras.wrappers.scikit_learn import KerasRegressor
from sklearn.model_selection import cross_val_score
from sklearn.model_selection import KFold
from sklearn.preprocessing import StandardScaler
from sklearn.pipeline import Pipeline
from sklearn.datasets import load_svmlight_file
# define base mode
def baseline_model():
# create model
model = Sequential()
model.add(Dense(68, activation="relu", kernel_initializer="normal", input_dim=68))
model.add(Dense(1, kernel_initializer="normal"))
# Compile model
model.compile(loss='mean_squared_error', optimizer='adam')
return model
X, y, query_id = load_svmlight_file(str(sys.argv[1]), query_id=True)
scaler = StandardScaler()
X = scaler.fit_transform(X.toarray())
# fix random seed for reproducibility
seed = 1
numpy.random.seed(seed)
# evaluate model with standardized dataset
estimator = KerasRegressor(build_fn=baseline_model, nb_epoch=100, batch_size=5, verbose=0)
kfold = KFold(n_splits=5, random_state=seed)
results = cross_val_score(estimator, X, y, cv=kfold)
print("Results: %.2f (%.2f) MSE" % (results.mean(), results.std()))
You are probably using an older Tensorflow version install tensorflow 1.2.0rc2 and you should be fine.