Created
April 6, 2019 04:01
-
-
Save lbadams2/21dfa1b83f6bedea9bef3c4dbb660c59 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
class GRU(nn.Module): | |
INPUT_SIZE = 603 | |
HIDDEN_SIZE = 100 | |
OUTPUT_SIZE = 1 | |
def __init__(self): | |
super(GRU, self).__init__() | |
self.gru = nn.GRU(self.INPUT_SIZE, self.HIDDEN_SIZE) | |
self.linear = nn.Linear(self.HIDDEN_SIZE, self.OUTPUT_SIZE) | |
self.sm = nn.Sigmoid() | |
if torch.cuda.is_available(): | |
self.device = 'cuda' | |
else: | |
self.device = 'cpu' | |
def forward(self, input, hidden): | |
_, hn = self.gru(input, hidden) | |
# reduce from 3 to 2 dimensions | |
rearranged = hn.view(hn.size()[1], hn.size(2)) | |
out1 = self.linear(rearranged) | |
out2 = self.sm(out1) | |
return out2 | |
def initHidden(self, N): | |
return Variable(torch.randn(1, N, self.HIDDEN_SIZE)) | |
class CandidateDataset(Dataset): | |
def __init__(self, x, y): | |
self.len = x.shape[0] | |
if torch.cuda.is_available(): | |
device = 'cuda' | |
else: | |
device = 'cpu' | |
self.x_data = torch.as_tensor(x, device=device, dtype=torch.float) | |
self.y_data = torch.as_tensor(y, device=device, dtype=torch.float) | |
def __getitem__(self, index): | |
return self.x_data[index], self.y_data[index] | |
def __len__(self): | |
return self.len | |
class NeuralModel(): | |
N_EPOCHS = 20 | |
BATCH_SIZE = 50 | |
INPUT_SIZE = 603 | |
def __init__(self, model): | |
self.model = model | |
self.optimizer = torch.optim.Adam(model.parameters(), lr=1e-4) | |
self.loss_f = nn.BCELoss() | |
if torch.cuda.is_available(): | |
self.device = 'cuda' | |
else: | |
self.device = 'cpu' | |
def fit(self, candidate_count): | |
candidate_ds = self.get_ds(candidate_count) | |
train_loader = DataLoader(dataset = candidate_ds, batch_size = self.BATCH_SIZE, shuffle = True) | |
self.model.train() | |
for epoch in range(self.N_EPOCHS): | |
running_loss = 0.0 | |
for batch_idx, (inputs, labels) in enumerate(train_loader): | |
inputs, labels = Variable(inputs), Variable(labels) | |
self.optimizer.zero_grad() | |
inputs = inputs.view(-1, inputs.size()[0], self.INPUT_SIZE) | |
# init hidden with number of rows in input | |
y_pred = self.model(inputs, self.model.initHidden(inputs.size()[1])) | |
loss = self.loss_f(y_pred, labels) | |
loss.backward() | |
self.optimizer.step() | |
running_loss += loss.item() | |
if batch_idx % 500 == 499: | |
print('[%d, %5d] loss: %.3f' % (epoch + 1, batch_idx + 1, running_loss / 500)) | |
running_loss = 0.0 | |
def predict(self): | |
feature_matrix = np.random.rand(10, self.INPUT_SIZE) | |
x_data = torch.as_tensor(feature_matrix, device='cpu', dtype=torch.float) | |
x_data = x_data.view(1, x_data.size()[0], self.INPUT_SIZE) | |
y_pred = self.model(x_data, self.model.initHidden(x_data.size()[1])) | |
# this gets max class and its energy for each candidate | |
max_cand_class = torch.max(y_pred, 1) | |
max_energy = 0 | |
max_index = -1 | |
for idx, class_label in enumerate(max_cand_class[1]): | |
class_label = class_label.item() | |
max_e = max_cand_class[0][idx].item() | |
# choose test sample with max energy | |
if class_label == 1 and max_e > max_energy: | |
max_index = idx | |
max_energy = max_e | |
# this gets the index for the single candidate with max energy | |
values, indices = torch.max(max_cand_class[0], 0) | |
# this gets the class (0 or 1) for the candidate with max energy | |
max_energy_class = max_cand_class[1][max_index] | |
def get_ds(self, candidate_count): | |
feature_matrix = np.random.rand(candidate_count, self.INPUT_SIZE) | |
target_matrix = np.zeros((candidate_count, 1), dtype=int) | |
for i in range(candidate_count): | |
if i % 5 == 0: | |
target_matrix[i] = 1 | |
candidate_ds = CandidateDataset(feature_matrix, target_matrix) | |
return candidate_ds | |
if __name__ == '__main__': | |
gru = models.GRU() | |
model = NeuralModel(gru) | |
model.fit(5000) | |
model.predict() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment