deep learning RestNet problem calculate confusion matrix and other matrixes - deep-learning

i am new to deep learning.
I am running a code to train and test a model and find its precision recall f1-score support and confusion matrix.
plz see the code and tell me that am i coding right for taking F1 score and other matrixes. my accuracy is .97.
not sure about
have i taken the right prediction
have i compute the right confusion matrix.
guide me that the confusion matrix is ok or not.
enterinput_shape = (128, 128, 3)
batch_size = 64
epochs = 10
epoch_list = list(range(1, epochs+1))
Path to training & testing set.
train_dir = 'train'
test_dir = 'test'
train_dir_fake, test_dir_fake = os.path.join(train_dir, 'forged'), os.path.join(test_dir, 'forged')
train_dir_real, test_dir_real = os.path.join(train_dir, 'real'), os.path.join(test_dir, 'real')
train_fake_fnames, test_fake_fnames = os.listdir(train_dir_fake), os.listdir(test_dir_fake)
train_real_fnames, test_real_fnames = os.listdir(train_dir_real), os.listdir(test_dir_real)"
Training Data Generator.
train_datagen = ImageDataGenerator(rescale=1./255.)
Testing Data Generator.
test_datagen = ImageDataGenerator(rescale=1./255.)
Flow training images in batches of 64 using train_datagen generator
train_generator = train_datagen.flow_from_directory(train_dir,
target_size=(128, 128),
batch_size=batch_size,
shuffle='False',
class_mode='binary')
Flow test images in batches of 64 using test_datagen generator
test_generator = test_datagen.flow_from_directory(test_dir,
target_size=(128, 128),
batch_size=batch_size,
shuffle='False',
class_mode='binary')
ResNet50V2_model = ResNet50V2(input_shape=input_shape, include_top=False, weights="imagenet", classes=2)
for i in range(50):
l = ResNet50V2_model.get_layer(index=i)
l.trainable = True
model = Sequential()
model.add(ResNet50V2_model)
model.add(GlobalAveragePooling2D())
model.add(Dense(units=1, activation='sigmoid'))
Compiling the Model.
model.compile(loss='binary_crossentropy',
optimizer=optimizers.Adam(learning_rate=1e-6, beta_1=0.9, beta_2=0.999, epsilon=None, decay=0.0),
metrics=['accuracy'])
reduce = ReduceLROnPlateau(monitor='val_loss', factor=0.1, patience=5, mode='auto')
early_stopping = EarlyStopping(monitor='val_loss', min_delta=1e-4, patience=5, verbose=0, mode='auto')
Starting the Training.
history = model.fit(train_generator, epochs=epochs, validation_data=test_generator)
storing model
network_name = "ResNet50V2"
try:
os.mkdir("./Reference_Data")
os.mkdir("./Reference_Data/Graphs")
os.mkdir("./Reference_Data/Summary")
os.mkdir("./Reference_Data/Model")
except OSError:
pass
try:
os.mkdir(os.path.join("./Reference_Data/Graphs", network_name))
except OSError:
pass
!dir
acc = np.linspace(min(epoch_list), max(epoch_list), 200)
val_acc = np.linspace(min(epoch_list), max(epoch_list), 200)
#define spline for accuracy
spl1 = make_interp_spline(epoch_list, history.history['accuracy'], k=3)
y_smooth1 = spl1(acc)
#define spline accuracy
spl2 = make_interp_spline(epoch_list, history.history['val_accuracy'], k=3)
y_smooth2 = spl2(val_acc)
with open("./Reference_Data/Summary/" + network_name + "summary.txt", 'w+') as f:
model.summary(print_fn=lambda x: f.write(x + '\n'))
Saving the Model for Inference Purpose.
model.save('./Reference_Data/Model/' + network_name + '/')
model.save('./Reference_Data/Model/' + network_name + '/' + network_name + '.h5')
test_generator.reset()
Y_pred = model.predict(test_generator,)
classes = test_generator.classes[test_generator.index_array]
y_pred = np.argmax(Y_pred, axis=-1)
y_pred=y_pred.round()
sum(y_pred==classes)/10000
pred=model.predict(test_generator,verbose=1)
def get_classification_report(
model, data_dir, batch_size=64,
steps=None, threshold=0.5, output_dict=False
):
data = get_test_data_generator(data_dir, batch_size=batch_size)
predictions = predict(model, data, steps, threshold)
predictions = predictions.reshape((predictions.shape[0],))
return classification_report(data.classes, predictions, output_dict=output_dict)
import sklearn.metrics as metrics
#y_pred = np.argmax(y_pred,axis=0)
#y_true=np.argmax(test_generator.classes,axis=0)
report = metrics.classification_report(true_classes, Y_pred.round(), target_names=class_labels,zero_division=0.0)
print(report)
precision recall f1-score support
forged 0.40 0.40 0.40 773
real 0.60 0.60 0.60 1172
accuracy 0.52 1945
macro avg 0.50 0.50 0.50 1945
weighted avg 0.52 0.52 0.52 1945

Related

Resolve overfitting in a convolutional network

I've written a snippet to classify Omniglot images. I calculate the training and validation losses in each epoch, where the latter is computed using images that were not seen by the network before. The two plots are as below:
Since the training loss decreases while the validation loss increases, I have concluded that my model overfits. I've tried several suggestions (e.g. here) to overcome this, including:
Increasing the size of the training set.
shuffling the data.
Adding dropout layers (up to p=0.9).
Using smaller model.
Altering the architecture.
Changing the learning rate.
Reducing the batch size.
Adding weight decay.
However, the validation loss still increases. I wonder if there are any other suggestions to improve this behavior or if this is not overfitting, but the problem is something else. Below is the snippet used in this question.
import torch
import torchvision
import torchvision.transforms as transforms
from torch import nn, optim
from torch.utils.data import DataLoader
class MyModel(nn.Module):
def __init__(self):
super(MyModel, self).__init__()
dim_out = 964
# -- embedding params
self.cn1 = nn.Conv2d(1, 16, 7)
self.cn2 = nn.Conv2d(16, 32, 4)
self.cn3 = nn.Conv2d(32, 64, 3)
self.pool = nn.MaxPool2d(2)
self.bn1 = nn.BatchNorm2d(16)
self.bn2 = nn.BatchNorm2d(32)
self.bn3 = nn.BatchNorm2d(64)
# -- prediction params
self.fc1 = nn.Linear(256, 170)
self.fc2 = nn.Linear(170, 50)
self.fc3 = nn.Linear(50, dim_out)
# -- non-linearity
self.relu = nn.ReLU()
self.Beta = 10
self.sopl = nn.Softplus(beta=self.Beta)
def forward(self, x):
y1 = self.pool(self.bn1(self.relu(self.cn1(x))))
y2 = self.pool(self.bn2(self.relu(self.cn2(y1))))
y3 = self.relu(self.bn3(self.cn3(y2)))
y3 = y3.view(y3.size(0), -1)
y5 = self.sopl(self.fc1(y3))
y6 = self.sopl(self.fc2(y5))
return self.fc3(y6)
class Train:
def __init__(self):
self.device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
# -- data
dim = 28
batch_size = 400
my_transforms = transforms.Compose([transforms.Resize((dim, dim)), transforms.ToTensor()])
trainset = torchvision.datasets.Omniglot(root="./data/omniglot_train/", download=False, transform=my_transforms)
validset = torchvision.datasets.Omniglot(root="./data/omniglot_train/", background=False, download=False,
transform=my_transforms)
self.TrainDataset = DataLoader(dataset=trainset, batch_size=batch_size, shuffle=True)
self.ValidDataset = DataLoader(dataset=validset, batch_size=len(validset), shuffle=False)
self.N_train = len(trainset)
self.N_valid = len(validset)
# -- model
self.model = MyModel().to(self.device)
# -- train
self.epochs = 3000
self.loss = nn.CrossEntropyLoss()
self.optimizer = optim.Adam(self.model.parameters(), lr=1e-3)
def train_epoch(self):
self.model.train()
train_loss = 0
for batch_idx, data_batch in enumerate(self.TrainDataset):
# -- predict
predict = self.model(data_batch[0].to(self.device))
# -- loss
loss = self.loss(predict, data_batch[1].to(self.device))
# -- optimize
self.optimizer.zero_grad()
loss.backward()
self.optimizer.step()
train_loss += loss.item()
return train_loss/(batch_idx+1)
def valid_epoch(self):
with torch.no_grad():
self.model.eval()
for data_batch in self.ValidDataset:
# -- predict
predict = self.model(data_batch[0].to(self.device))
# -- loss
loss = self.loss(predict, data_batch[1].to(self.device))
return loss.item()
def __call__(self):
for epoch in range(self.epochs):
train_loss = self.train_epoch()
valid_loss = self.valid_epoch()
print('Epoch {}: Training loss = {:.5f}, Validation loss = {:.5f}.'.format(epoch, train_loss, valid_loss))
torch.save(self.model.state_dict(), './model_stat.pth')
if __name__ == '__main__':
my_train = Train()
my_train()
If your train accuracy is good but testing (data not used in training) accuracy is bad then you have an overfitting problem. I had the same problem with a CNN model. You can use two methods to overcome overfitting. First is early stopping for your train and second is regularization. Check the below example:
# L2 regularizers for layers
model = keras.Sequential([
keras.layers.InputLayer(input_shape=(32, 32)),
keras.layers.Reshape(target_shape=(32, 32, 1)),
keras.layers.Conv2D(filters=12, kernel_size=(3, 3), activation=tf.nn.relu, use_bias=True , kernel_regularizer =tf.keras.regularizers.l2( l=0.01)),
keras.layers.MaxPooling2D(pool_size=(2, 2)),
keras.layers.Flatten(),
keras.layers.Dense(10, activation = 'softmax', use_bias=True)
])
model.compile(optimizer='adam',
loss=tf.keras.losses.SparseCategoricalCrossentropy(),
metrics=['accuracy'])
#Early Stopping
history = model.fit(X_train, Y_train,
validation_data=(X_dev, Y_dev),
epochs=4000,
callbacks=EarlyStopping(monitor='val_loss'))
Do not forget to import for early stopping.
from tensorflow.keras.callbacks import EarlyStopping

PyTotch CIFAR-10 vs Kaggle CIFAR-10 : Totally different result for exactly same architecture on CIFAR-10

I have been learning PyTorch for some weeks. While I was practicing with CIFAR-10 dataset from PyTorch datasets, I also thought of practicing with ImageFolder class, so I found a version of Cifar-10 from Kaggle, where the images were foldered.(I you don't remember PyTorch datasets are in tar.gz format, not in folder structure)
To my utter surprise, in spite of using the same loss function, learning rate and architecture, The Kaggle dataset test set accuracy starts from 0.18 and PyTorch dataset accuracy starts from 0.56 at epoch 1.
Finally after 20 epochs ,one almost saturates near 0.45 and the later one almost fixes near 0.86.
I have checked again and again,but not finding any big difference in those two codes.
I really want to know, if I have done anything deadly wrong, or there is anything fundamentally different about those two datasets.
To clarify, I am using this Pytorch dataset, and this Kaggle dataset .
The codes are too large to be provided here, so I am providing links my notebooks, you are welcome to take a look at my whole code, and also can run if necessary [You only need to use your Kaggle API key to download the dataset from kaggle, I can't make mine one public...sorry for the inconvinience]
Kaggle Dataset Notebook here and Pytorch Dataset Notebook here
I am also providing the chunk of code that I think , is mostly different.
Kaggle Dataset:
Epoch 1 score = 0.18
Epoch 20 score = 0.45
from torch.utils.data import DataLoader
def createVal(train_list, root_folder, classes, valid_split ):
try:
os.mkdir(os.path.join(root_folder, 'val'))
except FileExistsError:
pass
for cls in classes:
try:
os.mkdir(os.path.join(root_folder, 'val', cls))
except FileExistsError:
pass
np.random.shuffle(train_list)
valid_len = len(train_list) * valid_split
for i in tqdm(range(int(valid_len))):
shutil.move(train_list[i], train_list[i].replace('/train/', '/val/'))
valid_split = 0.2
batch_size = 32
num_workers = 4
root_folder = "/content/cifar10/cifar10"
train_folder = os.path.join(root_folder, "train")
test_folder = os.path.join(root_folder, "test")
if valid_split:
createVal(train_list, root_folder, classes, valid_split = valid_split)
val_folder = os.path.join(root_folder, "val")
val_data = datasets.ImageFolder(val_folder, transform = transform)
val_loader = DataLoader(val_data, batch_size = batch_size, num_workers = num_workers )
train_data = datasets.ImageFolder(train_folder, transform = transform)
train_loader = DataLoader(train_data, shuffle = True, batch_size = batch_size, num_workers = num_workers )
test_data = datasets.ImageFolder(test_folder, transform = transform)
test_loader = DataLoader(test_data, batch_size = batch_size, num_workers = num_workers )
Pytorch Dataset:
Epoch 1 score = 0.18
Epoch 20 score = 0.45
valid_split = 0.2
batch_size = 32
num_workers = 4
if valid_split:
num_train = len(train_data)
idx = list(range(num_train))
np.random.shuffle(idx)
train_idx = idx[int(valid_split*num_train):]
val_idx = idx[:int(valid_split*num_train)]
train_sampler = SubsetRandomSampler(train_idx)
val_sampler = SubsetRandomSampler(val_idx)
train_loader = DataLoader(train_data, sampler = train_sampler, batch_size = batch_size, num_workers = num_workers )
val_loader = DataLoader(train_data, sampler = val_sampler, batch_size = batch_size, num_workers = num_workers )
else:
train_loader = DataLoader(train_data, batch_size = batch_size, num_workers = num_workers )
test_loader = DataLoader(test_data, batch_size = batch_size, num_workers = num_workers )
I see , difference in method of shuffling the training dataset.
Kaggle dataset : train_loader > shuffle = True
Pytorch Dataset : train_loader > No shuffle
When using shuffle ==True , it will do RandomSampler function .

How to use DNN to fit these data

I'm using DNN to fit these data, and I use softmax to classify them into 2 class, and each of them has a demensity of 4040, can someone with experience tell me what's wrong with my nets.
It is strange that my initial loss is 7.6 and my initial error is 0.5524, and Basically they won't change anymore.
for train, test in kfold.split(data_pro, valence_labels):
model = keras.Sequential()
model.add(keras.layers.Dense(5000,activation='relu',input_shape=(4040,)))
model.add(keras.layers.Dropout(rate=0.25))
model.add(keras.layers.Dense(500, activation='relu'))
model.add(keras.layers.Dropout(rate=0.5))
model.add(keras.layers.Dense(1000, activation='relu'))
model.add(keras.layers.Dropout(rate=0.5))
model.add(keras.layers.Dense(2, activation='softmax'))
model.add(keras.layers.Dropout(rate=0.5))
model.compile(optimizer=tf.keras.optimizers.RMSprop(learning_rate=0.0001,rho=0.9),
loss='binary_crossentropy',
metrics=['accuracy'])
print('------------------------------------------------------------------------')
print(f'Training for fold {fold_no} ...')
log_dir="logs/fit/" + datetime.datetime.now().strftime("%Y%m%d-%H%M%S")
tensorboard_callback = tf.keras.callbacks.TensorBoard(log_dir=log_dir, histogram_freq=1)
# Fit data to model
history = model.fit(data_pro[train], valence_labels[train],
batch_size=128,
epochs=50,
verbose=1,
callbacks=[tensorboard_callback]
)
# Generate generalization metrics
scores = model.evaluate(data_pro[test], valence_labels[test], verbose=0)
print(f'Score for fold {fold_no}: {model.metrics_names[0]} of {scores[0]}; {model.metrics_names[1]} of {scores[1]*100}%')
acc_per_fold.append(scores[1] * 100)
loss_per_fold.append(scores[0])
# Increase fold number
fold_no = fold_no + 1
# == Provide average scores ==
print('------------------------------------------------------------------------')
print('Score per fold')
for i in range(0, len(acc_per_fold)):
print('------------------------------------------------------------------------')
print(f'> Fold {i+1} - Loss: {loss_per_fold[i]} - Accuracy: {acc_per_fold[i]}%')
print('------------------------------------------------------------------------')
print('Average scores for all folds:')
print(f'> Accuracy: {np.mean(acc_per_fold)} (+- {np.std(acc_per_fold)})')
print(f'> Loss: {np.mean(loss_per_fold)}')
print('------------------------------------------------------------------------')
You shouldn't add Dropout after the final Dense , delete the model.add(keras.layers.Dropout(rate=0.5))
And I think your code may raise error because your labels's dim is 1 , But your final Dense's units is 2 . Change model.add(keras.layers.Dense(2, activation='softmax')) to model.add(keras.layers.Dense(1, activation='sigmoid'))
Read this to learn tensorflow
Update 1 :
Change
model.compile(optimizer= tf.keras.optimizers.SGD(learning_rate = 0.00001,momentum=0.9,nesterov=True),
loss=tf.keras.losses.CategoricalCrossentropy(),
metrics=['accuracy'])
to
model.compile(optimizer= tf.keras.optimizers.Adam(learning_rate=3e-4),
loss=tf.keras.losses.CategoricalCrossentropy(),
metrics=['accuracy'])
And change
accAll = []
for epoch in range(1, 50):
model.fit(train_data, train_labels,
batch_size=50,epochs=5,
validation_data = (val_data, val_labels))
val_loss, val_Accuracy = model.evaluate(val_data,val_labels,batch_size=1)
accAll.append(val_Accuracy)
to
accAll = model.fit(
train_data, train_labels,
batch_size=50,epochs=20,
validation_data = (val_data, val_labels)
)

Pytorch Fully Connected Feed Forward Network for a regression problem - Gives same result for all inputs

I build a neural network model in Pytorch for a simple regression problem (w1x1+w2x2+w3x3 = y) where I generated 2000 records for training data with random values for x1,x2,x3 and W1=4, W2=6, W3=2. I created a test dataset of 20 records with just values for x1,x2,x3 and I was hoping to get the result for But, the model returns same value for all 20 input rows. I don't know where the issue is. Below is the code snippet.
inputs = df[['x1', 'x2', 'x3']]
target = df['y']
inputs = torch.tensor(inputs.values).float()
target = torch.tensor(target.values).float()
test_data = torch.tensor(test_data.values).float()
import torch.nn as nn
import torch.nn.functional as F
class Net(nn.Module):
def __init__(self):
super(Net,self).__init__()
hidden1 = 10
hidden2 = 15
self.fc1 = nn.Linear(3,hidden1)
self.fc2 = nn.Linear(hidden1,hidden2)
self.fc3 = nn.Linear(hidden2,1)
def forward(self,x):
x = F.relu(self.fc1(x))
x = F.relu(self.fc2(x))
x = self.fc3(x)
return x
#instantiate the model
model = Net()
print(model)
criterion = nn.MSELoss()
optimizer = torch.optim.SGD(model.parameters(),lr=0.01)
model.train()
#epochs
epochs = 500
for x in range(epochs):
#initialize the training loss to 0
train_loss = 0
#clear out gradients
optimizer.zero_grad()
#calculate the output
output = model(inputs)
#calculate loss
loss = criterion(output,target)
#backpropagate
loss.backward()
#update parameters
optimizer.step()
if ((x%5)==0):
print('Training Loss after epoch {:2d} is {:2.6f}'.format(x,loss))
#set the model in evaluation mode
model.eval()
#Test the model on unseen data
test_output = model(test_data)
print(test_output)

Getting polynomial regression to overfit with TensorFlow

The Sklearn documentation contains an example of a polynomial regression which beautifully illustrates the idea of overfitting (link).
The third plot shows a 15th order polynomial that overfits the simulated data. I replicated this model in TensorFlow, but I cannot get it to overfit.
Even when tuning the learning rate and the numbers of learning epochs, I cannot get the model to overfit. What am I missing?
import tensorflow as tf
import numpy as np
import matplotlib.pyplot as plt
def true_fun(X):
return np.cos(1.5 * np.pi * X)
# Generate dataset
n_samples = 30
np.random.seed(0)
x_train = np.sort(np.random.rand(n_samples)) # Draw from uniform distribution
y_train = true_fun(x_train) + np.random.randn(n_samples) * 0.1
x_test = np.linspace(0, 1, 100)
y_true = true_fun(x_test)
# Helper function
def run_dir(base_dir, dirname='run'):
"Number log directories incrementally"
import os
import re
pattern = re.compile(dirname+'_(\d+)')
try:
previous_runs = os.listdir(base_dir)
except FileNotFoundError:
previous_runs = []
run_number = 0
for name in previous_runs:
match = pattern.search(name)
if match:
number = int(match.group(1))
if number > run_number:
run_number = number
run_number += 1
logdir = os.path.join(base_dir, dirname + '_%02d' % run_number)
return(logdir)
# Define the polynomial model
def model(X, w):
"""Polynomial model
param X: data
param y: coeficients in the polynomial regression
returns: Polynomial function Y(X, w)
"""
terms = []
for i in range(int(w.shape[0])):
term = tf.multiply(w[i], tf.pow(X, i))
terms.append(term)
return(tf.add_n(terms))
# Create the computation graph
order = 15
tf.reset_default_graph()
X = tf.placeholder("float")
Y = tf.placeholder("float")
w = tf.Variable([0.]*order, name="parameters")
lambda_reg = tf.placeholder('float', shape=[])
learning_rate_ph = tf.placeholder('float', shape=[])
y_model = model(X, w)
loss = tf.div(tf.reduce_mean(tf.square(Y-y_model)), 2) # Square error
loss_rg = tf.multiply(lambda_reg, tf.reduce_sum(tf.square(w))) # L2 pentalty
loss_total = tf.add(loss, loss_rg)
loss_hist1 = tf.summary.scalar('loss', loss)
loss_hist2 = tf.summary.scalar('loss_rg', loss_rg)
loss_hist3 = tf.summary.scalar('loss_total', loss_total)
summary = tf.summary.merge([loss_hist1, loss_hist2, loss_hist3])
train_op = tf.train.GradientDescentOptimizer(learning_rate_ph).minimize(loss_total)
init = tf.global_variables_initializer()
def train(sess, x_train, y_train, lambda_val=0, epochs=2000, learning_rate=0.01):
feed_dict={X: x_train, Y: y_train, lambda_reg: lambda_val, learning_rate_ph: learning_rate}
logdir = run_dir("logs/polynomial_regression2/")
writer = tf.summary.FileWriter(logdir)
sess.run(init)
for epoch in range(epochs):
_, summary_str = sess.run([train_op, summary], feed_dict=feed_dict)
writer.add_summary(summary_str, global_step=epoch)
final_cost, final_cost_rg, w_learned = sess.run([loss, loss_rg, w], feed_dict=feed_dict)
return final_cost, final_cost_rg, w_learned
def plot_test(w_learned, x_test, x_train, y_train):
y_learned = calculate_y(x_test, w_learned)
plt.scatter(x_train, y_train)
plt.plot(x_test, y_true, label="true function")
plt.plot(x_test, y_learned,'r', label="learned function")
#plt.title('$\lambda = {:03.2f}$'.format(lambda_values[i]))
plt.ylabel('y')
plt.xlabel('x')
plt.legend()
plt.show()
def calculate_y(x, w):
y = 0
for i in range(w.shape[0]):
y += w[i] * np.power(x, i)
return y
sess = tf.Session()
final_cost, final_cost_rg, w_learned = train(sess, x_train, y_train, lambda_val=0,
learning_rate=0.3, epochs=2000)
sess.close()
plot_test(w_learned, x_test, x_train, y_train)
I have same problem about this. When I do polynomial regression, I also can't overfit the data by using GD in Tensorflow.
Then I compare the coefficients(weights) of the model by using sklearn LinearRegression, I found when the polynomial degree is larger the coefficient of high order is very smaller(i.e. 1e-4), and the low order is relative large(i.e. 0.1).
That's mean when you using GD algorithm for searching the best value of weights, the high order coefficient become extreme sensitive about the value change, and the low order coefficient is not.
And I guess the best coefficient(overfit with data) of low order term is large, and of high order term is tiny. When you set large learning rate, it's impossible to find the right answer, and when you set tiny learning rate, you need lots of iterations.
It's obvious when you using GD algorithm with small data set to make overfit.