The problem of the given code is:
line 25, in <module> privacy_engine = PrivacyEngine(model, batch_size=64,
sample_size=60000, alphas=range(2,32), noise_multiplier=1.3, max_grad_norm=1.0)
TypeError: __init__() got an unexpected keyword argument 'batch_size'
An image of the code is attached in this link .
The code is given below:
# Step 1: Importing PyTorch and Opacus
import torch
from torchvision import datasets, transforms
import numpy as np
from opacus import PrivacyEngine
from tqdm import tqdm
# Step 2: Loading MNIST Data
train_loader = torch.utils.data.DataLoader(datasets.MNIST('../mnist', train=True, download=True,
transform=transforms.Compose([transforms.ToTensor(), transforms.Normalize((0.1307,),
(0.3081,)),]),), batch_size=64, shuffle=True, num_workers=1, pin_memory=True)
test_loader = torch.utils.data.DataLoader(datasets.MNIST('../mnist', train=False,
transform=transforms.Compose([transforms.ToTensor(), transforms.Normalize((0.1307,),
(0.3081,)),]),), batch_size=1024, shuffle=True, num_workers=1, pin_memory=True)
# Step 3: Creating a PyTorch Neural Network Classification Model and Optimizer
model = torch.nn.Sequential(torch.nn.Conv2d(1, 16, 8, 2, padding=3), torch.nn.ReLU(), torch.nn.MaxPool2d(2, 1),
torch.nn.Conv2d(16, 32, 4, 2), torch.nn.ReLU(), torch.nn.MaxPool2d(2, 1), torch.nn.Flatten(),
torch.nn.Linear(32 * 4 * 4, 32), torch.nn.ReLU(), torch.nn.Linear(32, 10))
optimizer = torch.optim.SGD(model.parameters(), lr=0.05)
# Step 4: Attaching a Differential Privacy Engine to the Optimizer
privacy_engine = PrivacyEngine(model, batch_size=64, sample_size=60000, alphas=range(2,32),
noise_multiplier=1.3, max_grad_norm=1.0)
How do I fix this issue in the PrivacyEngine of Opacus for differential privacy?
