def model_fn(model_dir):
"""Load the PyTorch model from the `model_dir` directory."""
print("Loading model.")
# First, load the parameters used to create the model.
model_info = {}
model_info_path = os.path.join(model_dir, 'model_info.pth')
with open(model_info_path, 'rb') as f:
model_info = torch.load(f)
print("model_info: {}".format(model_info))
# Determine the device and construct the model.
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
model = BinaryClassifier(model_info['input_features'],
model_info['hidden_dim'],
model_info['output_dim'])
# Load the stored model parameters.
model_path = os.path.join(model_dir, 'model.pth')
with open(model_path, 'rb') as f:
model.load_state_dict(torch.load(f))
# set to eval mode, could use no_grad
model.to(device).eval()
print("Done loading model.")
return model
def model_fn(model_dir):
"""Load the PyTorch model from the `model_dir` directory."""
print("Loading model.")
model_info = {}
model_info_path = os.path.join(model_dir, 'model_info.pth')
with open(model_info_path, 'rb') as f:
model_info = torch.load(f)
print("model_info: {}".format(model_info))
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
model = BinaryClassifier(model_info['input_features'],
model_info['hidden_dim'],
model_info['output_dim'])
model_path = os.path.join(model_dir, 'model.pth')
with open(model_path, 'rb') as f:
model.load_state_dict(torch.load(f))
model.to(device).eval()
print("Done loading model.")
return model
def model_fn(model_dir):
"""Load the PyTorch model from the `model_dir` directory."""
print("Loading model.")
# First, load the parameters used to create the model.
model_info = {}
model_info_path = os.path.join(model_dir, "model_info.pth")
with open(model_info_path, "rb") as f:
model_info = torch.load(f)
print("model_info: {}".format(model_info))
# Determine the device and construct the model.
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
model = BinaryClassifier(
model_info["input_features"],
model_info["hidden_dim"],
model_info["output_dim"],
model_info["momentum"],
model_info["dropout_rate"],
model_info["num_layers"],
)
# Load the store model parameters.
model_path = os.path.join(model_dir, "model.pth")
with open(model_path, "rb") as f:
model.load_state_dict(torch.load(f))
# Prep for testing
model.to(device).eval()
print("Done loading model.")
return model
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
print("Using device {}.".format(device))
torch.manual_seed(args.seed)
# Load the training data.
train_loader = _get_train_data_loader(args.batch_size, args.data_dir)
## --- Your code here --- ##
## TODO: Build the model by passing in the input params
# To get params from the parser, call args.argument_name, ex. args.epochs or ards.hidden_dim
# Don't forget to move your model .to(device) to move to GPU , if appropriate
model = BinaryClassifier(args.input_features, args.hidden_dim,
args.output_dim)
model = model.to(device)
## TODO: Define an optimizer and loss function for training
optimizer = optim.Adam(model.parameters())
criterion = torch.nn.BCELoss()
# Trains the model (given line of code, which calls the above training function)
train(model, train_loader, args.epochs, criterion, optimizer, device)
## TODO: complete in the model_info by adding three argument names, the first is given
# Keep the keys of this dictionary as they are
model_info_path = os.path.join(args.model_dir, 'model_info.pth')
with open(model_info_path, 'wb') as f:
model_info = {
'input_features': args.input_features,
'hidden_dim': args.hidden_dim,
'output_dim': args.output_dim,
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
print("Using device {}.".format(device))
torch.manual_seed(args.seed)
# Load the training data.
train_loader = _get_train_data_loader(args.batch_size, args.data_dir)
## --- Your code here --- ##
## TODO: Build the model by passing in the input params
# To get params from the parser, call args.argument_name, ex. args.epochs or ards.hidden_dim
# Don't forget to move your model .to(device) to move to GPU , if appropriate
model = BinaryClassifier(input_features = args.input_features, hidden_dim = args.hidden_dim, output_dim = args.output_dim)
model.to(device)
## TODO: Define an optimizer and loss function for training
optimizer = optim.Adam(model.parameters(), lr= args.lr)
criterion = nn.BCELoss()
# Trains the model (given line of code, which calls the above training function)
train(model, train_loader, args.epochs, criterion, optimizer, device)
## TODO: complete in the model_info by adding three argument names, the first is given
# Keep the keys of this dictionary as they are
model_info_path = os.path.join(args.model_dir, 'model_info.pth')
with open(model_info_path, 'wb') as f:
model_info = {
'input_features': args.input_features,
'hidden_dim': args.hidden_dim,