RESULTS = os.path.join('results', 'LENET5') # Training parameters SEED = 1 N_EPOCHS = 30 BATCH_SIZE = 8 LEARNING_RATE = 0.01 N_CLASSES = 10 # Define the properties of the neural network in terms of noise simulated during # the inference/training pass RPU_CONFIG = InferenceRPUConfig() RPU_CONFIG.forward.out_res = -1. # Turn off (output) ADC discretization. RPU_CONFIG.forward.w_noise_type = WeightNoiseType.ADDITIVE_CONSTANT RPU_CONFIG.forward.w_noise = 0.02 RPU_CONFIG.noise_model = PCMLikeNoiseModel(g_max=25.0) def load_images(): """Load images for train from torchvision datasets.""" transform = transforms.Compose([transforms.ToTensor()]) train_set = datasets.MNIST(TRAIN_DATASET, download=True, train=True, transform=transform) val_set = datasets.MNIST(TEST_DATASET, download=True, train=False, transform=transform) train_data = torch.utils.data.DataLoader(train_set, batch_size=BATCH_SIZE, shuffle=True) validation_data = torch.utils.data.DataLoader(val_set, batch_size=BATCH_SIZE, shuffle=False) return train_data, validation_data class LeNet5(AnalogSequential): """LeNet5 inspired analog model."""
# Define a single-layer network, using inference/hardware-aware training tile rpu_config = InferenceRPUConfig() rpu_config.forward.out_res = -1. # Turn off (output) ADC discretization. rpu_config.forward.w_noise_type = WeightNoiseType.ADDITIVE_CONSTANT rpu_config.forward.w_noise = 0.02 # Short-term w-noise. rpu_config.clip.type = WeightClipType.FIXED_VALUE rpu_config.clip.fixed_value = 1.0 rpu_config.modifier.pdrop = 0.03 # Drop connect. rpu_config.modifier.type = WeightModifierType.ADD_NORMAL # Fwd/bwd weight noise. rpu_config.modifier.std_dev = 0.1 rpu_config.modifier.rel_to_actual_wmax = True # Inference noise model. rpu_config.noise_model = PCMLikeNoiseModel(g_max=25.0) # drift compensation rpu_config.drift_compensation = GlobalDriftCompensation() model = AnalogLinear(4, 2, bias=True, rpu_config=rpu_config) # Move the model and tensors to cuda if it is available. if cuda.is_compiled(): x = x.cuda() y = y.cuda() model.cuda() # Define an analog-aware optimizer, preparing it for using the layers. opt = AnalogSGD(model.parameters(), lr=0.1) opt.regroup_param_groups(model)