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
train_imgs = mnist_data[0][:500]
train_labels = mnist_data[1][:500]
test_imgs = mnist_data[0][500:]
test_labels = mnist_data[1][500:]
#Train the model
model.fit(train_data=(train_imgs, train_labels),
validation_data=(test_imgs, test_labels),
epochs=10,
batch_size=10)
test_data = test_data.sample(frac=1)
test_data = test_data.values
X = train_data[:, 1:] / 255.
y = train_data[:, 0]
X_test = test_data[:, 1:]
y_test = test_data[:, 0]
del train_data
n = len(X)
X_train = X[:int(n * 0.8)]
y_train = y[:int(n * 0.8)]
X_validation = X[int(n * 0.8):]
y_validation = y[int(n * 0.8):]
del X, y
model.fit(train_data=(X_train, y_train),
validation_data=(X_validation, y_validation),
epochs=5,
batch_size=32)
ev = model.evaluate(X=X_test, y=y_test, batch_size=32)
print(ev)
# 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]))