def set_up_experiment(args, input_, probs, labels): # Set up objective function cross_entropy = lbann.CrossEntropy([probs, labels]) layers = list(lbann.traverse_layer_graph(input_)) weights = set() for l in layers: weights.update(l.weights) # scale = weight decay l2_reg = lbann.L2WeightRegularization(weights=weights, scale=1e-4) objective_function = lbann.ObjectiveFunction([cross_entropy, l2_reg]) # Set up model top1 = lbann.CategoricalAccuracy([probs, labels]) top5 = lbann.TopKCategoricalAccuracy([probs, labels], k=5) metrics = [lbann.Metric(top1, name='top-1 accuracy', unit='%'), lbann.Metric(top5, name='top-5 accuracy', unit='%')] callbacks = [lbann.CallbackPrint(), lbann.CallbackTimer(), lbann.CallbackDropFixedLearningRate( drop_epoch=[30, 60], amt=0.1)] model = lbann.Model(args.mini_batch_size, args.num_epochs, layers=layers, weights=weights, objective_function=objective_function, metrics=metrics, callbacks=callbacks) # Load data reader from prototext data_reader_proto = lbann.lbann_pb2.LbannPB() with open(args.data_reader, 'r') as f: txtf.Merge(f.read(), data_reader_proto) data_reader_proto = data_reader_proto.data_reader # Set up optimizer if args.optimizer == 'sgd': print('Creating sgd optimizer') optimizer = lbann.optimizer.SGD( learn_rate=args.optimizer_learning_rate, momentum=0.9, nesterov=True ) else: optimizer = lbann.contrib.args.create_optimizer(args) # Save prototext to args.prototext if args.prototext: lbann.proto.save_prototext(args.prototext, model=model, optimizer=optimizer, data_reader=data_reader_proto) return model, data_reader_proto, optimizer
def set_up_experiment(args, input_, probs, labels): # Set up objective function cross_entropy = lbann.CrossEntropy([probs, labels]) layers = list(lbann.traverse_layer_graph(input_)) l2_reg_weights = set() for l in layers: if type(l) == lbann.Convolution or type(l) == lbann.FullyConnected: l2_reg_weights.update(l.weights) # scale = weight decay l2_reg = lbann.L2WeightRegularization(weights=l2_reg_weights, scale=1e-4) objective_function = lbann.ObjectiveFunction([cross_entropy, l2_reg]) # Set up model top1 = lbann.CategoricalAccuracy([probs, labels]) top5 = lbann.TopKCategoricalAccuracy([probs, labels], k=5) metrics = [ lbann.Metric(top1, name='top-1 accuracy', unit='%'), lbann.Metric(top5, name='top-5 accuracy', unit='%') ] callbacks = [ lbann.CallbackPrint(), lbann.CallbackTimer(), lbann.CallbackDropFixedLearningRate(drop_epoch=[30, 60], amt=0.1) ] model = lbann.Model(args.num_epochs, layers=layers, objective_function=objective_function, metrics=metrics, callbacks=callbacks) # Set up data reader data_reader = data.imagenet.make_data_reader(num_classes=args.num_classes) # Set up optimizer if args.optimizer == 'sgd': print('Creating sgd optimizer') optimizer = lbann.optimizer.SGD( learn_rate=args.optimizer_learning_rate, momentum=0.9, nesterov=True) else: optimizer = lbann.contrib.args.create_optimizer(args) # Setup trainer trainer = lbann.Trainer(mini_batch_size=args.mini_batch_size) return trainer, model, data_reader, optimizer
else: # Some other Wide ResNet. resnet = resnet_variant_dict[args.resnet]( imagenet_labels, bn_statistics_group_size=args.bn_statistics_group_size, width=args.width) # Construct layer graph input_ = lbann.Input(target_mode='classification') images = lbann.Identity(input_) labels = lbann.Identity(input_) preds = resnet(images) probs = lbann.Softmax(preds) cross_entropy = lbann.CrossEntropy(probs, labels) top1 = lbann.CategoricalAccuracy(probs, labels) top5 = lbann.TopKCategoricalAccuracy(probs, labels, k=5) layers = list(lbann.traverse_layer_graph(input_)) # Setup tensor core operations (just to demonstrate enum usage) tensor_ops_mode = lbann.ConvTensorOpsMode.NO_TENSOR_OPS for l in layers: if type(l) == lbann.Convolution: l.conv_tensor_op_mode = tensor_ops_mode # Setup objective function l2_reg_weights = set() for l in layers: if type(l) == lbann.Convolution or type(l) == lbann.FullyConnected: l2_reg_weights.update(l.weights) l2_reg = lbann.L2WeightRegularization(weights=l2_reg_weights, scale=1e-4) obj = lbann.ObjectiveFunction([cross_entropy, l2_reg])