Created
July 1, 2017 08:56
-
-
Save tdeboissiere/27660736ca897025c80fd43674e69750 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
import numpy as np | |
import torch | |
import torch.nn as nn | |
import torch.nn.functional as F | |
from torch.autograd import Variable | |
import torch.optim as optim | |
from yellowfin_tuner import YFOptimizer | |
from tqdm import tqdm | |
# Load data | |
iteration = 0 | |
npts = 10000 | |
X_train = np.ones((npts, 2016)).astype(np.float32) | |
y_train = np.ones((npts, 42)).astype(np.float32) | |
# Parameters | |
learning_rate = 1E-3 | |
training_epochs = 1000 | |
n_batch_per_epoch = 1000 | |
batch_size = 4096 | |
# network | |
class MLPNet(nn.Module): | |
def __init__(self, input_dim, output_dim): | |
super(MLPNet, self).__init__() | |
self.fc1 = nn.Linear(input_dim, 256) | |
self.fc2 = nn.Linear(256, 256) | |
self.fc3 = nn.Linear(256, 256) | |
self.fc4 = nn.Linear(256, output_dim) | |
def forward(self, x): | |
x = F.relu(self.fc1(x)) | |
x = F.relu(self.fc2(x)) | |
x = F.relu(self.fc3(x)) | |
x = self.fc4(x) | |
return x | |
model = MLPNet(X_train.shape[-1], y_train.shape[-1]).cuda() | |
optimizer = optim.Adam(model.parameters(), lr=1E-4) | |
optimizer = YFOptimizer(model.parameters(), lr=1.0, mu=0, weight_decay=5e-4) | |
loss_fn = torch.nn.MSELoss(size_average=True).cuda() | |
# Train | |
for epoch in range(training_epochs): | |
for i in tqdm(range(n_batch_per_epoch)): | |
# Sample a start index | |
start = np.random.randint(0, X_train.shape[0] - batch_size) | |
# Get the batch | |
batch_x, batch_y = X_train[start:start + batch_size], y_train[start:start + batch_size] | |
# Convert to FloatTensor | |
batch_x, batch_y = torch.FloatTensor(batch_x), torch.FloatTensor(batch_y) | |
# Wrap to Variable | |
x, y_true = Variable(batch_x.cuda()), Variable(batch_y.cuda()) | |
# Forward pass | |
y_pred = model(x) | |
# loss = loss_fn(y_pred, y_true) | |
loss = torch.mean(torch.pow(y_true - y_pred, 2)) | |
# Backward pass | |
optimizer.zero_grad() | |
loss.backward() | |
optimizer.step() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment