So I am training a CNN and compute the training accuracy for each batch. Most of the it gives out 100% batch training accuracy. which I though was okay because I'm testing my model against the data I trained it with. But at some iterations, I get a 90% or 90% batch training accuracy. And worst, sometimes it goes down to 0% real quick and bounces back to 100% batch training accuracy. And I used the algorithm in https://github.com/Hvass-Labs/TensorFlow-Tutorials/blob/master/04_Save_Restore.ipynb and they also computed the batch training accuracy but they don't get the same results I get. They started out with around 80% batch training accuracy and observed a gradual increase until 98%. Why is this?
I was suspecting that my network is overfitting.
Here is my exact code:
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
from scipy import stats
import tensorflow as tf
import pyfftw
from scipy import signal
import xlrd
from tensorflow.python.tools import freeze_graph
from tensorflow.python.tools import optimize_for_inference_lib
import time
from datetime import timedelta
import math
import os
from sklearn.metrics import confusion_matrix
##matplotlib inline
plt.style.use('ggplot')
## define funtions
def read_data(file_path):
## column_names = ['user-id','activity','timestamp', 'x-axis', 'y-axis', 'z-axis']
column_names = ['activity','timestamp', 'Ax', 'Ay', 'Az', 'Gx', 'Gy', 'Gz', 'Mx', 'My', 'Mz'] ## 3 sensors
data = pd.read_csv(file_path,header = None, names = column_names)
return data
def feature_normalize(dataset):
mu = np.mean(dataset,axis = 0)
sigma = np.std(dataset,axis = 0)
return (dataset - mu)/sigma
def plot_axis(ax, x, y, title):
ax.plot(x, y)
ax.set_title(title)
ax.xaxis.set_visible(False)
ax.set_ylim([min(y) - np.std(y), max(y) + np.std(y)])
ax.set_xlim([min(x), max(x)])
ax.grid(True)
def plot_activity(activity,data):
fig, (ax0, ax1, ax2) = plt.subplots(nrows = 3, figsize = (15, 10), sharex = True)
plot_axis(ax0, data['timestamp'], data['Ax'], 'x-axis')
plot_axis(ax1, data['timestamp'], data['Ay'], 'y-axis')
plot_axis(ax2, data['timestamp'], data['Az'], 'z-axis')
plt.subplots_adjust(hspace=0.2)
fig.suptitle(activity)
plt.subplots_adjust(top=0.90)
plt.show()
def windows(data, size):
start = 0
while start < data.count():
yield start, start + size
start += (size / 2)
def segment_signal(data, window_size = None, num_channels=None): # edited
segments = np.empty((0,window_size,num_channels)) #change from 3 to 9 channels for AGM fusion #use variable num_channels=9
labels = np.empty((0))
for (n_start, n_end) in windows(data['timestamp'], window_size):
## x = data["x-axis"][start:end]
## y = data["y-axis"][start:end]
## z = data["z-axis"][start:end]
n_start = int(n_start)
n_end = int(n_end)
Ax = data["Ax"][n_start:n_end]
Ay = data["Ay"][n_start:n_end]
Az = data["Az"][n_start:n_end]
Gx = data["Gx"][n_start:n_end]
Gy = data["Gy"][n_start:n_end]
Gz = data["Gz"][n_start:n_end]
Mx = data["Mx"][n_start:n_end]
My = data["My"][n_start:n_end]
Mz = data["Mz"][n_start:n_end]
if(len(dataset['timestamp'][n_start:n_end]) == window_size): # include only windows with size of 90
segments = np.vstack([segments,np.dstack([Ax,Ay,Az,Gx,Gy,Gz,Mx,My,Mz])])
labels = np.append(labels,stats.mode(data["activity"][n_start:n_end])[0][0])
return segments, labels
def weight_variable(shape):
initial = tf.truncated_normal(shape, stddev = 0.1)
return tf.Variable(initial)
def bias_variable(shape):
initial = tf.constant(0.0, shape = shape)
return tf.Variable(initial)
def depthwise_conv2d(x, W):
return tf.nn.depthwise_conv2d(x,W, [1, 1, 1, 1], padding='VALID')
def apply_depthwise_conv(x,weights,biases):
return tf.nn.relu(tf.add(depthwise_conv2d(x, weights),biases))
def apply_max_pool(x,kernel_size,stride_size):
return tf.nn.max_pool(x, ksize=[1, 1, kernel_size, 1],
strides=[1, 1, stride_size, 1], padding='VALID')
#------------------------get dataset----------------------#
## run shoaib_dataset.py to generate dataset_shoaib_total.txt
## get data from dataset_shoaib_total.txt
dataset = read_data('dataset_shoaib_total.txt')
#--------------------preprocessing------------------------#
dataset['Ax'] = feature_normalize(dataset['Ax'])
dataset['Ay'] = feature_normalize(dataset['Ay'])
dataset['Az'] = feature_normalize(dataset['Az'])
dataset['Gx'] = feature_normalize(dataset['Gx'])
dataset['Gy'] = feature_normalize(dataset['Gy'])
dataset['Gz'] = feature_normalize(dataset['Gz'])
dataset['Mx'] = feature_normalize(dataset['Mx'])
dataset['My'] = feature_normalize(dataset['My'])
dataset['Mz'] = feature_normalize(dataset['Mz'])
###--------------------plot activity data----------------#
##for activity in np.unique(dataset["activity"]):
## subset = dataset[dataset["activity"] == activity][:180]
## plot_activity(activity,subset)
#------------------fixed hyperparameters--------------------#
window_size = 200 #from 90 #FIXED at 4 seconds
#----------------input hyperparameters------------------#
input_height = 1
input_width = window_size
num_labels = 6
num_channels = 9 #from 3 channels #9 channels for AGM
#-------------------sliding time window----------------#
segments, labels = segment_signal(dataset, window_size=window_size, num_channels=num_channels)
labels = np.asarray(pd.get_dummies(labels), dtype = np.int8)
reshaped_segments = segments.reshape(len(segments), (window_size*num_channels)) #use variable num_channels instead of constant 3 channels
#------------divide data into test and training set-----------#
train_test_split = np.random.rand(len(reshaped_segments)) < 0.80
train_x_init = reshaped_segments[train_test_split]
train_y_init = labels[train_test_split]
test_x = reshaped_segments[~train_test_split]
test_y = labels[~train_test_split]
train_validation_split = np.random.rand(len(train_x_init)) < 0.80
train_x = train_x_init[train_validation_split]
train_y = train_y_init[train_validation_split]
validation_x = train_x_init[~train_validation_split]
validation_y = train_y_init[~train_validation_split]
#---------------training hyperparameters----------------#
batch_size = 10
kernel_size = 60 #from 60 #optimal 2
depth = 15 #from 60 #optimal 15
num_hidden = 1000 #from 1000 #optimal 80
learning_rate = 0.0001
training_epochs = 8
total_batches = train_x.shape[0] ##// batch_size
#---------define placeholders for input----------#
X = tf.placeholder(tf.float32, shape=[None,input_width * num_channels], name="input")
X_reshaped = tf.reshape(X,[-1,input_height,input_width,num_channels])
Y = tf.placeholder(tf.float32, shape=[None,num_labels])
#---------------------perform convolution-----------------#
# first convolutional layer
c_weights = weight_variable([1, kernel_size, num_channels, depth])
c_biases = bias_variable([depth * num_channels])
c = apply_depthwise_conv(X_reshaped,c_weights,c_biases)
p = apply_max_pool(c,20,2)
# second convolutional layer
c2_weights = weight_variable([1, 6,depth*num_channels,depth//10])
c2_biases = bias_variable([(depth*num_channels)*(depth//10)])
c = apply_depthwise_conv(p,c2_weights,c2_biases)
#--------------flatten data for fully connected layers----------#
shape = c.get_shape().as_list()
c_flat = tf.reshape(c, [-1, shape[1] * shape[2] * shape[3]])
#------------fully connected layers----------------#
f_weights_l1 = weight_variable([shape[1] * shape[2] * depth * num_channels * (depth//10), num_hidden])
f_biases_l1 = bias_variable([num_hidden])
f = tf.nn.tanh(tf.add(tf.matmul(c_flat, f_weights_l1),f_biases_l1))
#----------------------dropout------------------#
keep_prob = tf.placeholder(tf.float32)
drop_layer = tf.nn.dropout(f, keep_prob)
#----------------------softmax layer----------------#
out_weights = weight_variable([num_hidden, num_labels])
out_biases = bias_variable([num_labels])
y_ = tf.nn.softmax(tf.add(tf.matmul(drop_layer, out_weights),out_biases), name="y_")
#-----------------loss optimization-------------#
loss = -tf.reduce_sum(Y * tf.log(y_))
optimizer = tf.train.AdamOptimizer(learning_rate = learning_rate).minimize(loss)
#-----------------compute accuracy---------------#
correct_prediction = tf.equal(tf.argmax(y_,1), tf.argmax(Y,1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
cost_history = np.empty(shape=[1],dtype=float)
saver = tf.train.Saver()
session = tf.Session()
session.run(tf.global_variables_initializer())
#-------------early stopping-----------------#
# Best validation accuracy seen so far.
best_validation_accuracy = 0.0
# Iteration-number for last improvement to validation accuracy.
last_improvement = 0
# Stop optimization if no improvement found in this many iterations.
require_improvement = 1000
# Counter for total number of iterations performed so far.
total_iterations = 0
def validation_accuracy():
return session.run(accuracy, feed_dict={X: validation_x, Y: validation_y, keep_prob: 1.0})
def next_batch(b, batch_size, train_x, train_y):
##for b in range(total_batches):
offset = (b * batch_size) % (train_y.shape[0] - batch_size)
batch_x = train_x[offset:(offset + batch_size), :]
batch_y = train_y[offset:(offset + batch_size), :]
return batch_x, batch_y
def optimize(num_iterations):
# Ensure we update the global variables rather than local copies.
global total_iterations
global best_validation_accuracy
global last_improvement
# Start-time used for printing time-usage below.
start_time = time.time()
for i in range(num_iterations):
# Increase the total number of iterations performed.
# It is easier to update it in each iteration because
# we need this number several times in the following.
total_iterations += 1
# Get a batch of training examples.
# x_batch now holds a batch of images and
# y_true_batch are the true labels for those images.
##x_batch, y_true_batch = data.train.next_batch(train_batch_size)
x_batch, y_true_batch = next_batch(i, batch_size, train_x, train_y)
# Put the batch into a dict with the proper names
# for placeholder variables in the TensorFlow graph.
feed_dict_train = {X: x_batch,
Y: y_true_batch, keep_prob: 0.5}
# Run the optimizer using this batch of training data.
# TensorFlow assigns the variables in feed_dict_train
# to the placeholder variables and then runs the optimizer.
session.run(optimizer, feed_dict=feed_dict_train)
# Print status every 100 iterations and after last iteration.
if (total_iterations % 100 == 0) or (i == (num_iterations - 1)):
# Calculate the accuracy on the training-batch.
acc_train = session.run(accuracy, feed_dict={X: x_batch,
Y: y_true_batch, keep_prob: 1.0})
# Calculate the accuracy on the validation-set.
# The function returns 2 values but we only need the first.
##acc_validation, _ = validation_accuracy()
acc_validation = validation_accuracy()
# If validation accuracy is an improvement over best-known.
if acc_validation > best_validation_accuracy:
# Update the best-known validation accuracy.
best_validation_accuracy = acc_validation
# Set the iteration for the last improvement to current.
last_improvement = total_iterations
# Save all variables of the TensorFlow graph to file.
saver.save(sess=session, save_path="../shoaib-har_agm_es.ckpt")
# A string to be printed below, shows improvement found.
improved_str = '*'
else:
# An empty string to be printed below.
# Shows that no improvement was found.
improved_str = ''
# Status-message for printing.
msg = "Iter: {0:>6}, Train-Batch Accuracy: {1:>6.1%}, Validation Acc: {2:>6.1%} {3}"
# Print it.
print(msg.format(i + 1, acc_train, acc_validation, improved_str))
# If no improvement found in the required number of iterations.
if total_iterations - last_improvement > require_improvement:
print("No improvement found in a while, stopping optimization.")
# Break out from the for-loop.
break
# Ending time.
end_time = time.time()
# Difference between start and end-times.
time_dif = end_time - start_time
# Print the time-usage.
print("Time usage: " + str(timedelta(seconds=int(round(time_dif)))))
optimize(10000)
With the output:
What exactly is training accuracy? Is it even computed? Or do you compute the training accuracy on the entire training data and not just the batch you trained your network with?
Here I printed the results such that it prints out the batch training accuracy and the training accuracy on the entire dataset set for every multiples of 20 iterations.
The data is divided to 3 sets: train, validation and test.
Batch training accuracy is computed on the train set (the difference between the label and the prediction).
Validation accuracy is the accuracy on the validation set.
The batch accuracy can be computed just after a forward pass in the network. The number of samples in one forward pass is the batch size. It is just a way to train models faster (mini-batch gradient descent)
Overfitting is when the model works really good on known data (training set) but performs poorly on new data.
As to the 10% multiples, it is just the printing format you are using.
Related
I am trying to train an LSTM network on a music dataset to create a model that can identify pitches. There are 45 different labels (pitches) that I'm trying to classify a given sample with. However, every label has the same prediction value no matter the sample (i.e. all labels #1 have the same value, all labels #2, ...)
Our X_train_RNN is 16170x20x2688 (each of our 16170 samples has a sequence length of 20), and our y_train_RNN is a 16170x45 (each of our 16170 samples have a 45-dimensional vector containing real numbers). We then say that a negative real number corresponds to that pitch not being there, and a positive real number corresponds to that pitch being there.
Here's the LSTM in PyTorch:
class LSTM1(nn.Module):
def __init__(self):
super(LSTM1, self).__init__()
self.num_classes = 45 #number of classes
self.num_layers = 1 #number of layers
self.input_size = 84*32 #input size
self.hidden_size = 100 #hidden state
self.seq_length = 20 #sequence length
self.lstm = nn.LSTM(input_size=self.input_size, hidden_size=self.hidden_size,
num_layers=self.num_layers, batch_first=True) #lstm
self.fc_1 = nn.Linear(self.hidden_size, 128) #fully connected 1
self.fc = nn.Linear(128, self.num_classes) #fully connected last layer
self.relu = nn.ReLU()
def forward(self,x):
h_0 = Variable(torch.zeros(self.num_layers, x.size(0), self.hidden_size)) #hidden state
c_0 = Variable(torch.zeros(self.num_layers, x.size(0), self.hidden_size)) #internal state
# Propagate input through LSTM
output, (hn, cn) = self.lstm(x, (h_0, c_0)) #lstm with input, hidden, and internal state
hn = hn.view(-1, self.hidden_size) #reshaping the data for Dense layer next
out = self.relu(hn)
out = self.fc_1(out) #first Dense
out = self.relu(out) #relu
out = self.fc(out) #Final Output
return out
And here's how we use it:
from torch.nn.modules.loss import BCEWithLogitsLoss
epochs = 5
model = LSTM1()
criterion = BCEWithLogitsLoss()
optimizer = optim.Adam(model.parameters(), lr=1e-7)
train_loss = []
# training iteration
for epoch in range(epochs):
running_loss = 0
for itr, (image, label) in enumerate(trainloader):
#print("image: " + str(image.shape))
# zero gradient
optimizer.zero_grad()
# forward path
y_predicted = model(image)
#print("label: " + str(label.shape))
#print("y_predicted: " + str(y_predicted.shape))
loss = criterion(y_predicted, label)
running_loss += loss.item()
# backpropagating
loss.backward()
# optimizes the weights
optimizer.step()
with torch.no_grad():
totalPos = 0
for i in range(45):
totalPos += np.count_nonzero(y_predicted.numpy()[:, i] > 0)
print("num of positive: " + str(totalPos))
train_loss.append(running_loss)
print(f'epoch: {epoch+1}, loss: {running_loss:.4f}')
But afterwards when we get our model and get our predictions...
with torch.no_grad():
X = torch.tensor(X_test_RNN).float()
testPreds = model2(X)
testPreds has the same exact prediction for every value in a given column; no matter the sample. This even happens by the first or second epoch it seems. What could be going on?
I am trying to implement Bayesian CNN using Mc Dropout on Pytorch, the main idea is that by applying dropout at test time and running over many forward passes, you get predictions from a variety of different models. I need to obtain the uncertainty, does anyone have an idea of how I can do it Please
This is how I defined my CNN
'''
class Net(nn.Module):
def __init__(self):
super(Net, self).__init__()
self.conv1 = nn.Conv2d(3, 6, 5)
self.pool = nn.MaxPool2d(2, 2)
self.conv2 = nn.Conv2d(6, 16, 5)
self.fc1 = nn.Linear(16 * 5 * 5, 120)
self.fc2 = nn.Linear(120, 84)
self.fc3 = nn.Linear(84, 10)
self.dropout = nn.Dropout(p=0.3)
nn.init.xavier_uniform_(self.conv1.weight)
nn.init.constant_(self.conv1.bias, 0.0)
nn.init.xavier_uniform_(self.conv2.weight)
nn.init.constant_(self.conv2.bias, 0.0)
nn.init.xavier_uniform_(self.fc1.weight)
nn.init.constant_(self.fc1.bias, 0.0)
nn.init.xavier_uniform_(self.fc2.weight)
nn.init.constant_(self.fc2.bias, 0.0)
nn.init.xavier_uniform_(self.fc3.weight)
nn.init.constant_(self.fc3.bias, 0.0)
def forward(self, x):
x = self.pool(F.relu(self.dropout(self.conv1(x)))) # recommended to add the relu
x = self.pool(F.relu(self.dropout(self.conv2(x)))) # recommended to add the relu
x = x.view(-1, 16 * 5 * 5)
x = F.relu(self.fc1(x))
x = F.relu(self.fc2(self.dropout(x)))
x = self.fc3(self.dropout(x)) # no activation function needed for the last layer
return x
model = Net().to(device)
train_accuracies=np.zeros(num_epochs)
test_accuracies=np.zeros(num_epochs)
dataiter = iter(trainloader)
images, labels = dataiter.next()
#initializing variables
loss_acc = []
class_acc_mcdo = []
start_train = True
#Defining the Loss Function and Optimizer
criterion = nn.CrossEntropyLoss()
optimizer = torch.optim.Adam(model.parameters(), lr=learning_rate)
def train():
loss_vals = []
acc_vals = []
for epoch in range(num_epochs): # loop over the dataset multiple times
n_correct = 0 # initialize number of correct predictions
acc = 0 # initialize accuracy of each epoch
somme = 0 # initialize somme of losses of each epoch
epoch_loss = []
for i, (images, labels) in enumerate(trainloader):
# origin shape: [4, 3, 32, 32] = 4, 3, 1024
# input_layer: 3 input channels, 6 output channels, 5 kernel size
images = images.to(device)
labels = labels.to(device)
# Forward pass
outputs = model.train()(images)
loss = criterion(outputs, labels)
# Backward and optimize
optimizer.zero_grad() # zero the parameter gradients
loss.backward()
epoch_loss.append(loss.item()) # add the loss to epoch_loss list
optimizer.step()
# max returns (value ,index)
_, predicted = torch.max(outputs, 1)
n_correct += (predicted == labels).sum().item()
# print statistics
if (i + 1) % 2000 == 0:
print(f'Epoch [{epoch + 1}/{num_epochs}], Step [{i + 1}/{n_total_steps}], Loss:
{loss.item():.4f}')
somme = (sum(epoch_loss)) / len(epoch_loss)
loss_vals.append(somme) # add the epoch's loss to loss_vals
print("Loss = {}".format(somme))
acc = 100 * n_correct / len(trainset)
acc_vals.append(acc) # add the epoch's Accuracy to acc_vals
print("Accuracy = {}".format(acc))
# SAVE
PATH = './cnn.pth'
torch.save(model.state_dict(), PATH)
loss_acc.append(loss_vals)
loss_acc.append(acc_vals)
return loss_acc
And here is the code of the mc dropout
'''
def enable_dropout(model):
""" Function to enable the dropout layers during test-time """
for m in model.modules():
if m.__class__.__name__.startswith('Dropout'):
m.train()
def test():
# set non-dropout layers to eval mode
model.eval()
# set dropout layers to train mode
enable_dropout(model)
test_loss = 0
correct = 0
n_samples = 0
n_class_correct = [0 for i in range(10)]
n_class_samples = [0 for i in range(10)]
T = 100
for images, labels in testloader:
images = images.to(device)
labels = labels.to(device)
with torch.no_grad():
output_list = []
# getting outputs for T forward passes
for i in range(T):
output_list.append(torch.unsqueeze(model(images), 0))
# calculating mean
output_mean = torch.cat(output_list, 0).mean(0)
test_loss += F.nll_loss(F.log_softmax(output_mean, dim=1), labels,
reduction='sum').data # sum up batch loss
_, predicted = torch.max(output_mean, 1) # get the index of the max log-probability
correct += (predicted == labels).sum().item() # sum up correct predictions
n_samples += labels.size(0)
for i in range(batch_size):
label = labels[i]
predi = predicted[i]
if (label == predi):
n_class_correct[label] += 1
n_class_samples[label] += 1
test_loss /= len(testloader.dataset)
# PRINT TO HTML PAGE
print('\n Average loss: {:.4f}, Accuracy: ({:.3f}%)\n'.format(
test_loss,
100. * correct / n_samples))
# Accuracy for each class
acc_classes = []
for i in range(10):
acc = 100.0 * n_class_correct[i] / n_class_samples[i]
print(f'Accuracy of {classes[i]}: {acc} %')
acc_classes.append(acc)
class_acc_mcdo.extend(acc_classes)
print('Finished Testing')
You can compute the statistics, such as the sample mean or the sample variance, of different stochastic forward passes at test time (i.e. with the test or validation data), when the dropout is enabled. These statistics can be used to represent uncertainty. For example, you can compute the entropy, which is a measure of uncertainty, from the sample mean.
I have been trying to implement a CNN on the CIFAR-10 dataset for a few days and my test set accuracy does not seem to go beyond the 10% and the error just hang around 69.07733. I have tweaking the model and few days but in vain. I haven't been able to spot out where I am going wrong. Please help me recognise the fault in the model. Here is the code for it:
import os
import sys
import pickle
import tensorflow as tf
import numpy as np
from matplotlib import pyplot as plt
data_root = './cifar-10-batches-py'
train_data = np.ndarray(shape=(50000,3072), dtype=np.float32)
train_labels = np.ndarray(shape=(50000), dtype=np.float32)
num_images = 0
test_data = np.ndarray(shape=(10000,3072),dtype = np.float32)
test_labels = np.ndarray(shape=(10000),dtype=np.float32)
meta_data = {}
for file in os.listdir(data_root):
file_path = os.path.join(data_root,file)
with open(file_path,'rb') as f:
temp = pickle.load(f,encoding ='bytes')
if file == 'batches.meta':
for i,j in enumerate(temp[b'label_names']):
meta_data[i] = j
if 'data_batch_' in file:
for i in range(10000):
train_data[num_images,:] = temp[b'data'][i]
train_labels[num_images] = temp[b'labels'][i]
num_images += 1
if 'test_batch' in file:
for i in range(10000):
test_data[i,:] = temp[b'data'][i]
test_labels[i] = temp[b'labels'][i]
'''
print('meta: \n',meta_data)
train_data = train_data.reshape(50000,3,32,32).transpose(0,2,3,1)
print('\ntrain data: \n',train_data.shape,'\nLabels: \n',train_labels[0])
print('\ntest data: \n',test_data[0].shape,'\nLabels: \n',train_labels[0])'''
#accuracy function acc = (no. of correct prediction/total attempts) * 100
def accuracy(predictions, labels):
return (100 * (np.sum(np.argmax(predictions,1)== np.argmax(labels, 1))/predictions.shape[0]))
#reformat the data
def reformat(data,labels):
data = data.reshape(data.shape[0],3,32,32).transpose(0,2,3,1).astype(np.float32)
labels = (np.arange(10) == labels[:,None]).astype(np.float32)
return data,labels
train_data, train_labels = reformat(train_data,train_labels)
test_data, test_labels = reformat(test_data, test_labels)
print ('Train ',train_data[0][1])
plt.axis("off")
plt.imshow(train_data[1], interpolation = 'nearest')
plt.savefig("1.png")
plt.show()
'''
print("Train: \n",train_data.shape,test_data[0],"\nLabels: \n",train_labels.shape,train_labels[:11])
print("Test: \n",test_data.shape,test_data[0],"\nLabels: \n",test_labels.shape,test_labels[:11])'''
image_size = 32
num_channels = 3
batch_size = 30
patch_size = 5
depth = 64
num_hidden = 256
num_labels = 10
graph = tf.Graph()
with graph.as_default():
#input data and labels
train_input = tf.placeholder(tf.float32,shape=(batch_size,image_size,image_size,num_channels))
train_output = tf.placeholder(tf.float32,shape=(batch_size,num_labels))
test_input = tf.constant(test_data)
#layer weights and biases
layer_1_weights = tf.Variable(tf.truncated_normal([patch_size,patch_size,num_channels,depth]))
layer_1_biases = tf.Variable(tf.zeros([depth]))
layer_2_weights = tf.Variable(tf.truncated_normal([patch_size,patch_size,depth,depth]))
layer_2_biases = tf.Variable(tf.constant(0.1, shape=[depth]))
layer_3_weights = tf.Variable(tf.truncated_normal([64*64, num_hidden]))
layer_3_biases = tf.Variable(tf.constant(0.1, shape=[num_hidden]))
layer_4_weights = tf.Variable(tf.truncated_normal([num_hidden, num_labels]))
layer_4_biases = tf.Variable(tf.constant(0.1, shape=[num_labels]))
def convnet(data):
conv_1 = tf.nn.conv2d(data, layer_1_weights,[1,1,1,1], padding = 'SAME')
hidden_1 = tf.nn.relu(conv_1+layer_1_biases)
norm_1 = tf.nn.lrn(hidden_1, 4, bias=1.0, alpha=0.001 / 9.0, beta=0.75)
pool_1 = tf.nn.max_pool(norm_1,[1,2,2,1],[1,2,2,1], padding ='SAME')
conv_2 = tf.nn.conv2d(pool_1,layer_2_weights,[1,1,1,1], padding = 'SAME')
hidden_2 = tf.nn.relu(conv_2+layer_2_biases)
norm_2 = tf.nn.lrn(hidden_2, 4, bias=1.0, alpha=0.001 / 9.0, beta=0.75)
pool_2 = tf.nn.max_pool(norm_2,[1,2,2,1],[1,2,2,1], padding ='SAME')
shape = pool_2.get_shape().as_list()
hidd2_trans = tf.reshape(pool_2,[shape[0],shape[1]*shape[2]*shape[3]])
hidden_3 = tf.nn.relu(tf.matmul(hidd2_trans,layer_3_weights) + layer_3_biases)
return tf.nn.relu(tf.matmul(hidden_3,layer_4_weights) + layer_4_biases)
logits = convnet(train_input)
loss = tf.reduce_sum(tf.nn.softmax_cross_entropy_with_logits(labels=train_output, logits = logits))
optimizer = tf.train.AdamOptimizer(1e-4).minimize(loss)
train_prediction = tf.nn.softmax(logits)
test_prediction = tf.nn.softmax(convnet(test_input))
num_steps = 100000
with tf.Session(graph=graph) as session:
tf.global_variables_initializer().run()
print('Initialized \n')
for step in range(num_steps):
offset = (step * batch_size) % (train_labels.shape[0] - batch_size)
batch = train_data[offset:(offset+batch_size),:,:,:]
batch_labels = train_labels[offset:(offset+batch_size),:]
feed_dict ={train_input: batch, train_output: batch_labels}
_,l,prediction = session.run([optimizer, loss, train_prediction], feed_dict = feed_dict)
if (step % 500 == 0):
print("Loss at step %d: %f" %(step, l))
print("Accuracy: %f" %(accuracy(prediction, batch_labels)))
print("Test accuracy: %f" %(accuracy(session.run(test_prediction), test_labels)))
On a first glance I would say the initialization of the CNN is the culprit. A convnet is an optimization algorithm in a highly non-convex space and therefore depends a lot on careful initialization to not get stuck on local minima or saddle points. Look at xavier initialization for an example on how to fix that.
Example Code:
W = tf.get_variable("W", shape=[784, 256],
initializer=tf.contrib.layers.xavier_initializer())
Problem is your network is having very high depth(number of filters = 64 for both layers). Also, you are training the network from scratch. And your dataset of CIFAR10 (50000 images) is very little. Moreover, each CIFAR10 image is only 32x32x3 size.
Couple of alternatives what I can suggest you is to retrain a pre-trained model, i.e do transfer learning.
Other better alternative is to reduce the number of filters in each layer. In this way, you will be able to train the model from scratch and also it will be faster. (Assuming you don't have GPU).
Next you are making use of local response normalization. I would suggest you to remove this layer and do mean normalization in pre-processing step.
Next, if you feel the learning is not picking up at all, try increasing the learning rate a little and see.
Lastly, just to reduce some operation in your code, you are reshaping your tensor and then doing transpose in many places like this:
data.reshape(data.shape[0],3,32,32).transpose(0,2,3,1)
Why not directly reshape it to something like this?
data.reshape(data.shape[0], 32, 32, 3)
Hope the answer helps you.
The following RNN model decreases the loss for the first one or two epochs and then fluctuates around the cost of 6. This seems like the model is so random and not learning at all. I varied the learning rate from 0.1 to 0.0001 and it didn't help. The data is fed with an input pipeline, which worked fine with other models, so the functions that extract the label and images are not presented here. I have looked at this for so many times but still couldn't find what's wrong with it. Here's the code:
n_steps = 224
n_inputs = 224
learning_rate = 0.00015
batch_size = 256 # n_neurons
epochs = 100
num_batch = int(len(trainnames)/batch_size)
keep_prob = tf.placeholder(tf.float32)
# TRAIN QUEUE
train_queue = tf.RandomShuffleQueue(len(trainnames)*1.5, 0, [tf.string, tf.float32], shapes=[[],[num_labels,]])
enqueue_train = train_queue.enqueue_many([trainnames, train_label])
train_image, train_image_label = train_queue.dequeue()
train_image = read_image_file(train_image)
train_batch, train_label_batch = tf.train.batch(
[train_image, train_image_label],
batch_size=batch_size,
num_threads=1,
capacity=10*batch_size,
enqueue_many=False,
shapes=[[224,224], [num_labels,]],
allow_smaller_final_batch=True
)
train_close = train_queue.close()
def RNN(inputs, reuse):
with tf.variable_scope('cells', reuse=reuse):
basic_cell = tf.contrib.rnn.BasicRNNCell(num_units=batch_size, reuse=reuse)
with tf.variable_scope('rnn'):
outputs, states = tf.nn.dynamic_rnn(basic_cell, inputs, dtype=tf.float32)
fc_drop = tf.nn.dropout(states, keep_prob)
logits = tf.contrib.layers.fully_connected(fc_drop, num_labels, activation_fn=None)
return logits
#Training
with tf.name_scope("cost_function") as scope:
cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(labels=train_label_batch, logits=RNN(train_batch, reuse=None)))
train_step = tf.train.MomentumOptimizer(learning_rate, 0.9).minimize(cost)
cost_summary = tf.summary.scalar("cost_function", cost)
file_writer = tf.summary.FileWriter(logdir)
#Session
with tf.Session() as sess:
sess.run(tf.local_variables_initializer())
sess.run(tf.global_variables_initializer())
coord = tf.train.Coordinator()
threads = tf.train.start_queue_runners(sess=sess, coord=coord, start=True)
step = 0
for epoch in range(epochs):
sess.run(enqueue_train)
for batch in range(num_batch):
if step % 100 == 0:
summary_str = cost_summary.eval(feed_dict={keep_prob: 1.0})
file_writer.add_summary(summary_str, step)
else:
sess.run(train_step, feed_dict={keep_prob: 0.5})
step += 1
sess.run(train_close)
coord.request_stop()
coord.join(threads)
file_writer.close()
I have a data set which contains a list of stock prices. I need to use the tensorflow and python to predict the close price.
Q1: I have the following code which takes the first 2000 records as training and 2001 to 20000 records as test but I don't know how to change the code to do the prediction of the close price of today and 1 day later??? Please advise!
#!/usr/bin/env python2
import numpy as np
import pandas as pd
import tensorflow as tf
import matplotlib.pyplot as plt
def feature_scaling(input_pd, scaling_meathod):
if scaling_meathod == 'z-score':
scaled_pd = (input_pd - input_pd.mean()) / input_pd.std()
elif scaling_meathod == 'min-max':
scaled_pd = (input_pd - input_pd.min()) / (input_pd.max() -
input_pd.min())
return scaled_pd
def input_reshape(input_pd, start, end, batch_size, batch_shift, n_features):
temp_pd = input_pd[start-1: end+batch_size-1]
output_pd = map(lambda y : temp_pd[y:y+batch_size], xrange(0, end-start+1, batch_shift))
output_temp = map(lambda x : np.array(output_pd[x]).reshape([-1]), xrange(len(output_pd)))
output = np.reshape(output_temp, [-1, batch_size, n_features])
return output
def target_reshape(input_pd, start, end, batch_size, batch_shift, n_step_ahead, m_steps_pred):
temp_pd = input_pd[start+batch_size+n_step_ahead-2: end+batch_size+n_step_ahead+m_steps_pred-2]
print temp_pd
output_pd = map(lambda y : temp_pd[y:y+m_steps_pred], xrange(0, end-start+1, batch_shift))
output_temp = map(lambda x : np.array(output_pd[x]).reshape([-1]), xrange(len(output_pd)))
output = np.reshape(output_temp, [-1,1])
return output
def lstm(input, n_inputs, n_steps, n_of_layers, scope_name):
num_layers = n_of_layers
input = tf.transpose(input,[1, 0, 2])
input = tf.reshape(input,[-1, n_inputs])
input = tf.split(0, n_steps, input)
with tf.variable_scope(scope_name):
cell = tf.nn.rnn_cell.BasicLSTMCell(num_units=n_inputs)
cell = tf.nn.rnn_cell.MultiRNNCell([cell]*num_layers)
output, state = tf.nn.rnn(cell, input, dtype=tf.float32) yi1
output = output[-1]
return output
feature_to_input = ['open price', 'highest price', 'lowest price', 'close price','turnover', 'volume','mean price']
feature_to_predict = ['close price']
feature_to_scale = ['volume']
sacling_meathod = 'min-max'
train_start = 1
train_end = 1000
test_start = 1001
test_end = 20000
batch_size = 100
batch_shift = 1
n_step_ahead = 1
m_steps_pred = 1
n_features = len(feature_to_input)
lstm_scope_name = 'lstm_prediction'
n_lstm_layers = 1
n_pred_class = 1
learning_rate = 0.1
EPOCHS = 1000
PRINT_STEP = 100
read_data_pd = pd.read_csv('./stock_price.csv')
temp_pd = feature_scaling(input_pd[feature_to_scale],sacling_meathod)
input_pd[feature_to_scale] = temp_pd
train_input_temp_pd = input_pd[feature_to_input]
train_input_nparr = input_reshape(train_input_temp_pd,
train_start, train_end, batch_size, batch_shift, n_features)
train_target_temp_pd = input_pd[feature_to_predict]
train_target_nparr = target_reshape(train_target_temp_pd, train_start, train_end, batch_size, batch_shift, n_step_ahead, m_steps_pred)
test_input_temp_pd = input_pd[feature_to_input]
test_input_nparr = input_reshape(test_input_temp_pd, test_start, test_end, batch_size, batch_shift, n_features)
test_target_temp_pd = input_pd[feature_to_predict]
test_target_nparr = target_reshape(test_target_temp_pd, test_start, test_end, batch_size, batch_shift, n_step_ahead, m_steps_pred)
tf.reset_default_graph()
x_ = tf.placeholder(tf.float32, [None, batch_size, n_features])
y_ = tf.placeholder(tf.float32, [None, 1])
lstm_output = lstm(x_, n_features, batch_size, n_lstm_layers, lstm_scope_name)
W = tf.Variable(tf.random_normal([n_features, n_pred_class]))
b = tf.Variable(tf.random_normal([n_pred_class]))
y = tf.matmul(lstm_output, W) + b
cost_func = tf.reduce_mean(tf.square(y - y_))
train_op = tf.train.GradientDescentOptimizer(learning_rate).minimize(cost_func)
optimizer = tf.train.GradientDescentOptimizer(learning_rate).minimize(loss, global_step=global_step)
init = tf.initialize_all_variables()
with tf.Session() as sess:
sess.run(init)
for ii in range(EPOCHS):
sess.run(train_op, feed_dict={x_:train_input_nparr, y_:train_target_nparr})
if ii % PRINT_STEP == 0:
cost = sess.run(cost_func, feed_dict={x_:train_input_nparr, y_:train_target_nparr})
print 'iteration =', ii, 'training cost:', cost
Very simply, prediction (a.k.a. scoring or inference) comes from running the input through only the forward pass, and collecting the score for each input vector. It's the same process flow as testing. The difference is the four stages of model use:
Train: learn from the training data set; adjust weights as needed.
Test: evaluate the model's performance; if accuracy has converged, stop training.
Validate: evaluate the accuracy of the trained model. If it doesn't meet acceptance criteria, change something and start over with the training.
Predict: you've passed validation -- release the model for use by the intended application.
All four steps follow the same forward logic flow; training includes back-propagation; the others do not. Simply follow the forward-only process, and you'll get the result form you need.
I worry about your data partition: only 10% for training, 90% for testing, and none for validation. A more typical split is 50-30-20, or something in that general area.
Q-1 : You should change your LSTM parameter to return a sequence of size two which will be prediction for that day and the day after.
Q-2 it's clearly that your model is underfitting the data, which is so obvious with your 10% train 90% test data ! You should more equilibrated ratio as suggested in the previous answer.