thomwolf

model.zero_grad()                                   # Reset gradients tensors
for i, (inputs, labels) in enumerate(training_set):
    predictions = model(inputs)                     # Forward pass
    loss = loss_function(predictions, labels)       # Compute loss function
    loss = loss / accumulation_steps                # Normalize our loss (if averaged)
    loss.backward()                                 # Backward pass
    if (i+1) % accumulation_steps == 0:             # Wait for several backward steps
        optimizer.step()                            # Now we can do an optimizer step
        model.zero_grad()                           # Reset gradients tensors
        if (i+1) % evaluation_steps == 0:           # Evaluate the model when we...

AlexanderFabisch

# Get the dataset here: http://www.gaussianprocess.org/gpml/data/
import scipy.io

# Load training set
train = scipy.io.loadmat("sarcos_inv.mat")
# Inputs  (7 joint positions, 7 joint velocities, 7 joint accelerations)
Xtrain = train["sarcos_inv"][:, :21]
# Outputs (7 joint torques)
Ytrain = train["sarcos_inv"][:, 21:]