Related
I've trained an LSTM model with 8 features and 1 output. I have one dataset and split it into two separate files to train and predict with the first half of the set, and then attempt to predict the second half of the set using the trained model from the first part of my dataset. My model predicts the trained and testing sets from the dataset I used to train the model pretty well (RMSE of around 5-7), however when I attempt to predict using the second half of the set I get very poor predictions (RMSE of around 50-60). How can I get my trained model to predict outside datasets well?
dataset at this link
file = r'/content/drive/MyDrive/only_force_pt1.csv'
df = pd.read_csv(file)
df.head()
X = df.iloc[:, 1:9]
y = df.iloc[:,9]
print(X.shape)
print(y.shape)
plt.figure(figsize = (20, 6), dpi = 100)
plt.plot(y)
WINDOW_LEN = 50
def window_size(size, inputdata, targetdata):
X = []
y = []
i=0
while(i + size) <= len(inputdata)-1:
X.append(inputdata[i: i+size])
y.append(targetdata[i+size])
i+=1
assert len(X)==len(y)
return (X,y)
X_series, y_series = window_size(WINDOW_LEN, X, y)
print(len(X))
print(len(X_series))
print(len(y_series))
X_train, X_val, y_train, y_val = train_test_split(np.array(X_series),np.array(y_series),test_size=0.3, shuffle = True)
X_val, X_test,y_val, y_test = train_test_split(np.array(X_val),np.array(y_val),test_size=0.3, shuffle = False)
n_timesteps, n_features, n_outputs = X_train.shape[1], X_train.shape[2],1
[verbose, epochs, batch_size] = [1, 300, 32]
input_shape = (n_timesteps, n_features)
model = Sequential()
# LSTM
model.add(LSTM(64, input_shape=input_shape, return_sequences = False))
model.add(Dropout(0.2))
model.add(Dense(64, activation='relu', kernel_regularizer=keras.regularizers.l2(0.001)))
#model.add(Dropout(0.2))
model.add(Dense(32, activation='relu', kernel_regularizer=keras.regularizers.l2(0.001)))
model.add(Dense(1, activation='relu'))
earlystopper = EarlyStopping(monitor='val_loss', min_delta=0, patience = 30, verbose =1, mode = 'auto')
model.summary()
model.compile(loss = 'mse', optimizer = Adam(learning_rate = 0.001), metrics=[tf.keras.metrics.RootMeanSquaredError()])
history = model.fit(X_train, y_train, batch_size = batch_size, epochs = epochs, verbose = verbose, validation_data=(X_val,y_val), callbacks = [earlystopper])
Second dataset:
tests = r'/content/drive/MyDrive/only_force_pt2.csv'
df_testing = pd.read_csv(tests)
X_testing = df_testing.iloc[:4038,1:9]
torque = df_testing.iloc[:4038,9]
print(X_testing.shape)
print(torque.shape)
plt.figure(figsize = (20, 6), dpi = 100)
plt.plot(torque)
X_testing = X_testing.to_numpy()
X_testing_series, y_testing_series = window_size(WINDOW_LEN, X_testing, torque)
X_testing_series = np.array(X_testing_series)
y_testing_series = np.array(y_testing_series)
scores = model.evaluate(X_testing_series, y_testing_series, verbose =1)
X_prediction = model.predict(X_testing_series, batch_size = 32)
If your model is working fine on training data but performs bad on validation data, then your model did not learn the "true" connection between input and output variables but simply memorized the corresponding output to your input. To tackle this you can do multiple things:
Typically you would use 80% of your data to train and 20% to test, this will present more data to the model, which should make it learn more of the true underlying function
If your model is too complex, it will have neurons which will just be used to memorize input-output data pairs. Try to reduce the complexity of your model (layers, neurons) to make it more simple, so that the remaining layers can really learn instead of memorize
Look into more detail on training performance here
I have created a simple pytorch classification model with sample datasets generated using sklearns make_classification. Even after training for thousands of epochs the accuracy of the model hovers between 30 and 40 percentage. During training itself the loss value is fluctuating very far and wide. I am wondering why this model is not learning, whether it's due to some logical error in the code.
import torch
from torch.utils.data import Dataset, DataLoader
import torch.nn as nn
from sklearn.datasets import make_classification
from sklearn.model_selection import train_test_split
X,y = make_classification(n_features=15,n_classes=5,n_informative=4)
DEVICE = torch.device('cuda')
epochs = 5000
class CustomDataset(Dataset):
def __init__(self,X,y):
self.X = torch.from_numpy(X)
self.y = torch.from_numpy(y)
def __len__(self):
return len(self.X)
def __getitem__(self, index):
X = self.X[index]
y = self.y[index]
return (X,y)
class Model(nn.Module):
def __init__(self):
super().__init__()
self.l1 = nn.Linear(15,10)
self.l2 = nn.Linear(10,5)
self.relu = nn.ReLU()
def forward(self,x):
x = self.l1(x)
x = self.relu(x)
x = self.l2(x)
x = self.relu(x)
return x
model = Model().double().to(DEVICE)
optimizer = torch.optim.Adam(model.parameters(), lr=0.001)
loss_function = nn.CrossEntropyLoss()
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.33, random_state=42)
train_data = CustomDataset(X_train,y_train)
test_data = CustomDataset(X_test,y_test)
trainloader = DataLoader(train_data, batch_size=32, shuffle=True)
testloader = DataLoader(test_data, batch_size=32, shuffle=True)
for i in range(epochs):
for (x,y) in trainloader:
x = x.to(DEVICE)
y = y.to(DEVICE)
optimizer.zero_grad()
output = model(x)
loss = loss_function(output,y)
loss.backward()
optimizer.step()
if i%200==0:
print("epoch: ",i," Loss: ",loss.item())
correct = 0
total = 0
# since we're not training, we don't need to calculate the gradients for our outputs
with torch.no_grad():
for x, y in testloader:
# calculate outputs by running x through the network
outputs = model(x.to(DEVICE)).to(DEVICE)
# the class with the highest energy is what we choose as prediction
_, predicted = torch.max(outputs.data, 1)
total += y.size(0)
correct += (predicted == y.to(DEVICE)).sum().item()
print(f'Accuracy of the network on the test data: {100 * correct // total} %')
EDIT
I tried to over-fit my model with only 10 samples (batch_size=5) X,y = make_classification(n_samples=10,n_features=15,n_classes=5,n_informative=4) but now the accuracy decreased to 15-20%. I then normalize the input data between the values 0 and 1 which pushed the accuracy a bit higher but not over 50 percentage. Any idea why this might be happening?
You should not be using ReLU activation on your output layer. Usually softmax activation is used for multi class classification on the final layer, or the logits are fed to the loss function directly without explicitly adding a softmax activation layer.
Try removing the ReLU activation from the final layer.
Issue:
I'm trying to predict the future stock price of Google using the LSTM model in Keras. I'm able to train the model successfully and the test prediction also goes well, but the after test/future prediction is bad. It forms a steadily decreasing curve which is not an actual future data.
Some Explanation
I'm training the model with two inputs and expecting a single output from it.
# Feature Scaling
from sklearn.preprocessing import MinMaxScaler
sc = MinMaxScaler(feature_range = (0, 1))
training_set_scaled = sc.fit_transform(training_set)
# Creating a data structure with 60 timesteps and 1 output
X_train = []
y_train = []
for i in range(2, 999):
X_train.append(training_set_scaled[i-2:i, 0])
y_train.append(training_set_scaled[i, 0])
X_train, y_train = np.array(X_train), np.array(y_train)
# Reshaping
X_train = np.reshape(X_train, (X_train.shape[0], X_train.shape[1], 1))
# Part 2 - Building the RNN
# Importing the Keras libraries and packages
from keras.models import Sequential
from keras.layers import Dense
from keras.layers import LSTM
from keras.layers import Dropout
# Initialising the RNN
regressor = Sequential()
# Adding the first LSTM layer and some Dropout regularisation
regressor.add(LSTM(units = 50, return_sequences = True, input_shape = (X_train.shape[1], 1)))
regressor.add(Dropout(0.2))
# Adding a second LSTM layer and some Dropout regularisation
regressor.add(LSTM(units = 50, return_sequences = True))
regressor.add(Dropout(0.2))
# Adding a third LSTM layer and some Dropout regularisation
regressor.add(LSTM(units = 50, return_sequences = True))
regressor.add(Dropout(0.2))
# Adding a fourth LSTM layer and some Dropout regularisation
regressor.add(LSTM(units = 50))
regressor.add(Dropout(0.2))
# Adding the output layer
regressor.add(Dense(units = 1))
# Compiling the RNN
regressor.compile(optimizer = 'rmsprop', loss = 'mean_squared_error')
# Fitting the RNN to the Training set
regressor.fit(X_train, y_train, epochs = 500, batch_size = 50)
Testing the predicted model
dataset_test = pd.read_csv('/media/vinothubuntu/Ubuntu Storage/Downloads/Test - Test.csv')
real_stock_price = dataset_test.iloc[:, 2:3].values
# Getting the predicted stock price of 2017
dataset_total = pd.concat((dataset_train['data'], dataset_test['data']), axis = 0)
inputs = dataset_total[len(dataset_total) - len(dataset_test) -0:].values
inputs = inputs.reshape(-1,1)
inputs = sc.transform(inputs)
X_test = []
test_var = []
for i in range(0, 28):
X_test.append(inputs[i:i+2, 0])
test_var.append(inputs[i, 0])
X_test_pred = np.array(X_test)
X_test_pred = np.reshape(X_test_pred, (X_test_pred.shape[0], X_test_pred.shape[1], 1))
predicted_stock_price = regressor.predict(X_test_pred)
This part goes very well, the test prediction give a perfect result.
After test/future prediction:
for x in range(0,30):
X_test_length = X_test[len(X_test)-1] # get the last array of X_test list
future=[]
Prev_4 = X_test_length[1:2] # get the last four value of the X_test_length
Last_pred = predicted_stock_price.flat[-1] # get the last value from prediction
merger = np.append(Prev_4,Last_pred)
X_test.append(merger) #append the new array to X_test
future.append(merger) #append the new array to future array
one_time_pred=np.array(future)
one_time_pred = np.reshape(one_time_pred, (one_time_pred.shape[0], one_time_pred.shape[1], 1))
future_prediction = regressor.predict(one_time_pred) #predict future - gives one new prediction
predicted_stock_price = np.append(predicted_stock_price, future_prediction, axis=0) #put the new predicction on predicted_stock_price array
Here comes the actual problem, I'm getting the last value from the test prediction and predicting a single output and creating a loop on the new precited value. [Please suggest me a better way, if you feel this is a bad idea]
My output:
Expected Result: Actual future data, which is definitely not a decreasing curve.
I’ve made a custom CNN in PyTorch for classifying 10 classes in the CIFAR-10 dataset. My classification accuracy on the test dataset is 45.739%, this is very low and I thought it’s because my model is not very deep but I implemented the same model in Keras and the classification accuracy come outs to be 78.92% on test dataset. No problem in Keras however I think there's something I'm missing in my PyTorch program.
I have used the same model architecture, strides, padding, dropout rate, optimizer, loss function, learning rate, batch size, number of epochs on both PyTorch and Keras and despite that, the difference in the classification accuracy is still huge thus I’m not able to decide how I should debug my PyTorch program further.
For now I suspect 3 things: in Keras, I use the categorical cross entropy loss function (one hot vector labels) and in PyTorch I use the standard cross entropy loss function (scalar indices labels), can this be a problem?, if not then I suspect either my training loop or the code for calculating classification accuracy in PyTorch. I have attached both my programs below, will be grateful to any suggestions.
My program in Keras:
#================Function that defines the CNN model===========
def CNN_model():
model = Sequential()
model.add(Conv2D(32,(3,3),activation='relu',padding='same', input_shape=(size,size,channels))) #SAME PADDING
model.add(Conv2D(32,(3,3),activation='relu')) #VALID PADDING
model.add(MaxPooling2D(pool_size=(2,2))) #VALID PADDING
model.add(Dropout(0.25))
model.add(Conv2D(64,(3,3),activation='relu', padding='same')) #SAME PADDING
model.add(Conv2D(64,(3,3),activation='relu')) #VALID PADDING
model.add(MaxPooling2D(pool_size=(2,2))) #VALID PADDING
model.add(Dropout(0.25))
model.add(Conv2D(128,(3,3),activation='relu', padding='same')) #SAME PADDING
model.add(Conv2D(128,(3,3),activation='relu')) #VALID PADDING
model.add(MaxPooling2D(pool_size=(2,2),name='feature_extractor_layer')) #VALID PADDING
model.add(Dropout(0.25))
model.add(Flatten())
model.add(Dense(512, activation='relu', name='second_last_layer'))
model.add(Dropout(0.25))
model.add(Dense(10, activation='softmax', name='softmax_layer')) #10 nodes in the softmax layer
model.summary()
return model
#=====Main program starts here========
#get_train_data() and get_test_data() are my own custom functions to get CIFAR-10 dataset
images_train, labels_train, class_train = get_train_data(0,10)
images_test, labels_test, class_test = get_test_data(0,10)
model = CNN_model()
model.compile(loss='categorical_crossentropy', #loss function of the CNN
optimizer=Adam(lr=1.0e-4), #Optimizer
metrics=['accuracy'])#'accuracy' metric is to be evaluated
#images_train and images_test contain images and
#class_train and class_test contains one hot vectors labels
model.fit(images_train,class_train,
batch_size=128,
epochs=50,
validation_data=(images_test,class_test),
verbose=1)
scores=model.evaluate(images_test,class_test,verbose=0)
print("Accuracy: "+str(scores[1]*100)+"% \n")
My program in PyTorch:
#========DEFINE THE CNN MODEL=====
class Net(nn.Module):
def __init__(self):
super(Net, self).__init__()
self.conv1 = nn.Conv2d(3, 32, 3,1,1)#SAME PADDING
self.conv2 = nn.Conv2d(32,32,3,1,0)#VALID PADDING
self.pool1 = nn.MaxPool2d(2,2) #VALID PADDING
self.drop1 = nn.Dropout2d(0.25) #DROPOUT OF 0.25
self.conv3 = nn.Conv2d(32,64,3,1,1)#SAME PADDING
self.conv4 = nn.Conv2d(64,64,3,1,0)#VALID PADDING
self.pool2 = nn.MaxPool2d(2,2)#VALID PADDING
self.drop2 = nn.Dropout2d(0.25) #DROPOUT OF 0.25
self.conv5 = nn.Conv2d(64,128,3,1,1)#SAME PADDING
self.conv6 = nn.Conv2d(128,128,3,1,0)#VALID PADDING
self.pool3 = nn.MaxPool2d(2,2)#VALID PADDING
self.drop3 = nn.Dropout2d(0.25) #DROPOUT OF 0.25
self.fc1 = nn.Linear(128*2*2, 512)#128*2*2 IS OUTPUT DIMENSION AFTER THE PREVIOUS LAYER
self.drop4 = nn.Dropout(0.25) #DROPOUT OF 0.25
self.fc2 = nn.Linear(512,10) #10 output nodes
def forward(self, x):
x = F.relu(self.conv1(x))
x = F.relu(self.conv2(x))
x = self.pool1(x)
x = self.drop1(x)
x = F.relu(self.conv3(x))
x = F.relu(self.conv4(x))
x = self.pool2(x)
x = self.drop2(x)
x = F.relu(self.conv5(x))
x = F.relu(self.conv6(x))
x = self.pool3(x)
x = self.drop3(x)
x = x.view(-1,2*2*128) #FLATTENING OPERATION 2*2*128 IS OUTPUT AFTER THE PREVIOUS LAYER
x = F.relu(self.fc1(x))
x = self.drop4(x)
x = self.fc2(x) #LAST LAYER DOES NOT NEED SOFTMAX BECAUSE THE LOSS FUNCTION WILL TAKE CARE OF IT
return x
#=======FUNCTION TO CONVERT INPUT AND TARGET TO TORCH TENSORS AND LOADING INTO GPU======
def PrepareInputDataAndTargetData(device,images,labels,batch_size):
#GET MINI BATCH OF TRAINING IMAGES AND RESHAPE THE TORCH TENSOR FOR CNN PROCESSING
mini_batch_images = torch.tensor(images)
mini_batch_images = mini_batch_images.view(batch_size,3,32,32)
#GET MINI BATCH OF TRAINING LABELS, TARGET SHOULD BE IN LONG FORMAT SO CONVERT THAT TOO
mini_batch_labels = torch.tensor(labels)
mini_batch_labels = mini_batch_labels.long()
#FEED THE INPUT DATA AND TARGET LABELS TO GPU
mini_batch_images = mini_batch_images.to(device)
mini_batch_labels = mini_batch_labels.to(device)
return mini_batch_images,mini_batch_labels
#==========MAIN PROGRAM==========
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
#get_train_data() and get_test_data() are my own custom functions to get CIFAR-10 dataset
Images_train, Labels_train, Class_train = get_train_data(0,10)
Images_test, Labels_test, Class_test = get_test_data(0,10)
net = Net()
net = net.double() #https://discuss.pytorch.org/t/runtimeerror-expected-object-of-scalar-type-double-but-got-scalar-type-float-for-argument-2-weight/38961
print(net)
#MAP THE MODEL ONTO THE GPU
net = net.to(device)
#CROSS ENTROPY LOSS FUNCTION AND ADAM OPTIMIZER
criterion = nn.CrossEntropyLoss()
optimizer = optim.Adam(net.parameters(), lr=1e-4)
#PREPARE THE DATALOADER
#Images_train contains images and Labels_trains contains indices i.e. 0,1,...,9
dataset = TensorDataset( Tensor(Images_train), Tensor(Labels_train) )
trainloader = DataLoader(dataset, batch_size= 128, shuffle=True)
#START TRAINING THE CNN MODEL FOR 50 EPOCHS
for epoch in range(0,50):
for i, data in enumerate(trainloader, 0):
inputs, labels = data
inputs = torch.tensor(inputs).double()
inputs = inputs.view(len(inputs),3,32,32) #RESHAPE THE IMAGES
labels = labels.long() #MUST CONVERT LABEL TO LONG FORMAT
#MAP THE INPUT AND LABELS TO THE GPU
inputs=inputs.to(device)
labels=labels.to(device)
#FORWARD PROP, BACKWARD PROP, PARAMETER UPDATE
optimizer.zero_grad()
outputs = net.forward(inputs)
loss = criterion(outputs, labels)
loss.backward()
optimizer.step()
#CALCULATE CLASSIFICATION ACCURACY ON ALL 10 CLASSES
with torch.no_grad():
Images_class,Labels_class = PrepareInputDataAndTargetData(device,Images_test,Labels_test,len(Images_test))
network_outputs = net.forward(Images_class)
correct = (torch.argmax(network_outputs.data,1) == Labels_class.data).float().sum()
acc = float(100.0*(correct/len(Images_class)))
print("Accuracy is: "+str(acc)+"\n")
del Images_class
del Labels_class
del network_outputs
del correct
del acc
torch.cuda.empty_cache()
print("Done\n")
I am not fully aware of how the actual core backend works in both libraries however I suppose that the classification accuracy of any model should be almost the same regardless of the library.
I was reading the original paper on BN and the stack overflow question on How could I use Batch Normalization in TensorFlow? which provides a very useful piece of code to insert a batch normalization block to a Neural Network but does not provides enough guidance on how to actually use it during training, inference and when evaluating models.
For example, I would like to track the train error during training and test error to make sure I don't overfit. Its clear that the batch normalization block should be off during test, but when evaluating the error on the training set, should the batch normalization block be turned off too? My main questions are:
During inference and error evaluation, should the batch normalization block be turned off regardless of the data set?
Does that mean that the batch normalization block should only be on during the training step then?
To make it very clear, I will provide an extract (of simplified) code I have been using to run batch normalization with Tensor flow according to what is my understanding of what is the right thing to do:
## TRAIN
if phase_train is not None:
#DO BN
feed_dict_train = {x:X_train, y_:Y_train, phase_train: False}
feed_dict_cv = {x:X_cv, y_:Y_cv, phase_train: False}
feed_dict_test = {x:X_test, y_:Y_test, phase_train: False}
else:
#Don't do BN
feed_dict_train = {x:X_train, y_:Y_train}
feed_dict_cv = {x:X_cv, y_:Y_cv}
feed_dict_test = {x:X_test, y_:Y_test}
def get_batch_feed(X, Y, M, phase_train):
mini_batch_indices = np.random.randint(M,size=M)
Xminibatch = X[mini_batch_indices,:] # ( M x D^(0) )
Yminibatch = Y[mini_batch_indices,:] # ( M x D^(L) )
if phase_train is not None:
#DO BN
feed_dict = {x: Xminibatch, y_: Yminibatch, phase_train: True}
else:
#Don't do BN
feed_dict = {x: Xminibatch, y_: Yminibatch}
return feed_dict
with tf.Session() as sess:
sess.run( tf.initialize_all_variables() )
for iter_step in xrange(steps):
feed_dict_batch = get_batch_feed(X_train, Y_train, M, phase_train)
# Collect model statistics
if iter_step%report_error_freq == 0:
train_error = sess.run(fetches=l2_loss, feed_dict=feed_dict_train)
cv_error = sess.run(fetches=l2_loss, feed_dict=feed_dict_cv)
test_error = sess.run(fetches=l2_loss, feed_dict=feed_dict_test)
do_stuff_with_errors(train_error, cv_error, test_error)
# Run Train Step
sess.run(fetches=train_step, feed_dict=feed_dict_batch)
and the code I am using to produce batch normalization blocks is:
def standard_batch_norm(l, x, n_out, phase_train, scope='BN'):
"""
Batch normalization on feedforward maps.
Args:
x: Vector
n_out: integer, depth of input maps
phase_train: boolean tf.Varialbe, true indicates training phase
scope: string, variable scope
Return:
normed: batch-normalized maps
"""
with tf.variable_scope(scope+l):
#beta = tf.Variable(tf.constant(0.0, shape=[n_out], dtype=tf.float64 ), name='beta', trainable=True, dtype=tf.float64 )
#gamma = tf.Variable(tf.constant(1.0, shape=[n_out],dtype=tf.float64 ), name='gamma', trainable=True, dtype=tf.float64 )
init_beta = tf.constant(0.0, shape=[n_out], dtype=tf.float64)
init_gamma = tf.constant(1.0, shape=[n_out],dtype=tf.float64)
beta = tf.get_variable(name='beta'+l, dtype=tf.float64, initializer=init_beta, regularizer=None, trainable=True)
gamma = tf.get_variable(name='gamma'+l, dtype=tf.float64, initializer=init_gamma, regularizer=None, trainable=True)
batch_mean, batch_var = tf.nn.moments(x, [0], name='moments')
ema = tf.train.ExponentialMovingAverage(decay=0.5)
def mean_var_with_update():
ema_apply_op = ema.apply([batch_mean, batch_var])
with tf.control_dependencies([ema_apply_op]):
return tf.identity(batch_mean), tf.identity(batch_var)
mean, var = tf.cond(phase_train, mean_var_with_update, lambda: (ema.average(batch_mean), ema.average(batch_var)))
normed = tf.nn.batch_normalization(x, mean, var, beta, gamma, 1e-3)
return normed
I found that there is 'official' batch_norm layer in tensorflow. Try it out:
https://github.com/tensorflow/tensorflow/blob/b826b79718e3e93148c3545e7aa3f90891744cc0/tensorflow/contrib/layers/python/layers/layers.py#L100
Most likely it is not mentioned in docs since it included in some RC or 'beta' version only.
I haven't inspected deep into this matter yet, but as far as I see from documentation you just use binary parameter is_training in this batch_norm layer, and set it to true only for training phase. Try it out.
UPDATE: Below is the code to load data, build a network with one hidden ReLU layer and L2 normalization and introduce batch normalization for both hidden and out layer. This runs fine and trains fine.
# These are all the modules we'll be using later. Make sure you can import them
# before proceeding further.
from __future__ import print_function
import numpy as np
import tensorflow as tf
from six.moves import cPickle as pickle
pickle_file = '/home/maxkhk/Documents/Udacity/DeepLearningCourse/SourceCode/tensorflow/examples/udacity/notMNIST.pickle'
with open(pickle_file, 'rb') as f:
save = pickle.load(f)
train_dataset = save['train_dataset']
train_labels = save['train_labels']
valid_dataset = save['valid_dataset']
valid_labels = save['valid_labels']
test_dataset = save['test_dataset']
test_labels = save['test_labels']
del save # hint to help gc free up memory
print('Training set', train_dataset.shape, train_labels.shape)
print('Validation set', valid_dataset.shape, valid_labels.shape)
print('Test set', test_dataset.shape, test_labels.shape)
image_size = 28
num_labels = 10
def reformat(dataset, labels):
dataset = dataset.reshape((-1, image_size * image_size)).astype(np.float32)
# Map 2 to [0.0, 1.0, 0.0 ...], 3 to [0.0, 0.0, 1.0 ...]
labels = (np.arange(num_labels) == labels[:,None]).astype(np.float32)
return dataset, labels
train_dataset, train_labels = reformat(train_dataset, train_labels)
valid_dataset, valid_labels = reformat(valid_dataset, valid_labels)
test_dataset, test_labels = reformat(test_dataset, test_labels)
print('Training set', train_dataset.shape, train_labels.shape)
print('Validation set', valid_dataset.shape, valid_labels.shape)
print('Test set', test_dataset.shape, test_labels.shape)
def accuracy(predictions, labels):
return (100.0 * np.sum(np.argmax(predictions, 1) == np.argmax(labels, 1))
/ predictions.shape[0])
#for NeuralNetwork model code is below
#We will use SGD for training to save our time. Code is from Assignment 2
#beta is the new parameter - controls level of regularization.
#Feel free to play with it - the best one I found is 0.001
#notice, we introduce L2 for both biases and weights of all layers
batch_size = 128
beta = 0.001
#building tensorflow graph
graph = tf.Graph()
with graph.as_default():
# Input data. For the training data, we use a placeholder that will be fed
# at run time with a training minibatch.
tf_train_dataset = tf.placeholder(tf.float32,
shape=(batch_size, image_size * image_size))
tf_train_labels = tf.placeholder(tf.float32, shape=(batch_size, num_labels))
tf_valid_dataset = tf.constant(valid_dataset)
tf_test_dataset = tf.constant(test_dataset)
#introduce batchnorm
tf_train_dataset_bn = tf.contrib.layers.batch_norm(tf_train_dataset)
#now let's build our new hidden layer
#that's how many hidden neurons we want
num_hidden_neurons = 1024
#its weights
hidden_weights = tf.Variable(
tf.truncated_normal([image_size * image_size, num_hidden_neurons]))
hidden_biases = tf.Variable(tf.zeros([num_hidden_neurons]))
#now the layer itself. It multiplies data by weights, adds biases
#and takes ReLU over result
hidden_layer = tf.nn.relu(tf.matmul(tf_train_dataset_bn, hidden_weights) + hidden_biases)
#adding the batch normalization layerhi()
hidden_layer_bn = tf.contrib.layers.batch_norm(hidden_layer)
#time to go for output linear layer
#out weights connect hidden neurons to output labels
#biases are added to output labels
out_weights = tf.Variable(
tf.truncated_normal([num_hidden_neurons, num_labels]))
out_biases = tf.Variable(tf.zeros([num_labels]))
#compute output
out_layer = tf.matmul(hidden_layer_bn,out_weights) + out_biases
#our real output is a softmax of prior result
#and we also compute its cross-entropy to get our loss
#Notice - we introduce our L2 here
loss = (tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(
out_layer, tf_train_labels) +
beta*tf.nn.l2_loss(hidden_weights) +
beta*tf.nn.l2_loss(hidden_biases) +
beta*tf.nn.l2_loss(out_weights) +
beta*tf.nn.l2_loss(out_biases)))
#now we just minimize this loss to actually train the network
optimizer = tf.train.GradientDescentOptimizer(0.5).minimize(loss)
#nice, now let's calculate the predictions on each dataset for evaluating the
#performance so far
# Predictions for the training, validation, and test data.
train_prediction = tf.nn.softmax(out_layer)
valid_relu = tf.nn.relu( tf.matmul(tf_valid_dataset, hidden_weights) + hidden_biases)
valid_prediction = tf.nn.softmax( tf.matmul(valid_relu, out_weights) + out_biases)
test_relu = tf.nn.relu( tf.matmul( tf_test_dataset, hidden_weights) + hidden_biases)
test_prediction = tf.nn.softmax(tf.matmul(test_relu, out_weights) + out_biases)
#now is the actual training on the ANN we built
#we will run it for some number of steps and evaluate the progress after
#every 500 steps
#number of steps we will train our ANN
num_steps = 3001
#actual training
with tf.Session(graph=graph) as session:
tf.initialize_all_variables().run()
print("Initialized")
for step in range(num_steps):
# Pick an offset within the training data, which has been randomized.
# Note: we could use better randomization across epochs.
offset = (step * batch_size) % (train_labels.shape[0] - batch_size)
# Generate a minibatch.
batch_data = train_dataset[offset:(offset + batch_size), :]
batch_labels = train_labels[offset:(offset + batch_size), :]
# Prepare a dictionary telling the session where to feed the minibatch.
# The key of the dictionary is the placeholder node of the graph to be fed,
# and the value is the numpy array to feed to it.
feed_dict = {tf_train_dataset : batch_data, tf_train_labels : batch_labels}
_, l, predictions = session.run(
[optimizer, loss, train_prediction], feed_dict=feed_dict)
if (step % 500 == 0):
print("Minibatch loss at step %d: %f" % (step, l))
print("Minibatch accuracy: %.1f%%" % accuracy(predictions, batch_labels))
print("Validation accuracy: %.1f%%" % accuracy(
valid_prediction.eval(), valid_labels))
print("Test accuracy: %.1f%%" % accuracy(test_prediction.eval(), test_labels))