# Create a Sequential model Instance
model = Sequential()
#Build your network
model.add(Conv2D(input_shape=(1, 28, 28), filters=128, kernel_size=3))
model.add(ReLU())
model.add(Conv2D(filters=64, kernel_size=3))
model.add(ReLU())
model.add(Conv2D(filters=32, kernel_size=3))
model.add(ReLU())
model.add(Flatten())
model.add(Dense(n_nodes=10))
model.build()
model.compile(optimizer=SGD(),
loss_function=CrossEntropyLoss(),
metrics=["accuracy"])
print(model.summary())
#Get the MNIST dataset
train_set = torchvision.datasets.MNIST(root='./data',
train=True,
download=True,
transform=transforms.Compose(
[transforms.ToTensor()]))
# Load the dataset from pytorch's Dataloader function
train_loader = torch.utils.data.DataLoader(train_set, batch_size=1000)
#Get the data
mnist_data = next(iter(train_loader))
#Split into train and test set
# Model
model = Sequential()
model.add(Dense(n_nodes=64, n_inputs=784))
model.add(ReLU())
model.add(Dropout())
model.add(Dense(n_nodes=10))
model.build()
model.compile(optimizer=Adam(learning_rate=0.001,
betas=(0.9, 0.999),
eps=1e-08,
weight_decay=0.0,
amsgrad=False),
loss_function=CrossEntropyLoss(),
metrics=["accuracy"])
print(model.summary())
# Reading data
train_data = pd.read_csv("./data/mnist_train.csv")
test_data = pd.read_csv("./data/mnist_test.csv")
train_data = train_data.sample(frac=1)
train_data = train_data.values
test_data = test_data.sample(frac=1)
test_data = test_data.values
# Generating the data X_train = np.random.rand(100, 1) * 10 y_train = X_train + 5 *np.random.rand(100, 1) X_validation = np.random.rand(100, 1) * 10 y_validation = X_validation + 5 * np.random.rand(100, 1) X_test = np.random.rand(10, 1) * 10 y_test = X_test + 5 * np.random.rand(10, 1) # Making the model model = Sequential() model.add(Dense(n_nodes=1, n_inputs=1)) # Building the model model.build() # Compiling the model model.compile(optimizer=Adam(), loss_function=MSELoss()) # Printing model summary model.summary() # Training the model history = model.fit(train_data=(X_train, y_train), validation_data=(X_validation, y_validation), epochs=300, batch_size=4) # Predicting some values evaluated = model.evaluate(test_data=(X_test, y_test), batch_size=4) print(evaluated)
''' model = Sequential() model.add(Dense(n_nodes=1, n_inputs=3)) model.add(ReLU()) model.add(Dense(n_nodes=2)) model.add(ReLU()) model.add(Dense(n_nodes=1)) model.add(ReLU()) # Building the Model model.build() # Compiling model.compile(optimizer=Adam(), loss_function=MSELoss(), metrics=["accuracy"]) print(model.summary()) # Data for XOR x_train = np.array([[0, 0, 1], [0, 1, 1], [1, 0, 1]]) x_test = np.array([[1, 1, 1]]) y_train = np.array([[0], [1], [1]], dtype=np.float32) y_test = np.array([[0]], dtype=np.float32) # Training the model model.fit(train_data=(x_train, y_train), epochs=20, batch_size=1) # Prediction print(model.predict(x_test[0]))