142 lines
4.8 KiB
Python
142 lines
4.8 KiB
Python
import os
|
|
import sys
|
|
import torch
|
|
import torch.nn as nn
|
|
import torch.nn.functional as F # Add this line
|
|
import torchvision
|
|
import torchvision.transforms as transforms
|
|
|
|
sys.path.append("..")
|
|
from tools import show
|
|
|
|
seed = 4321
|
|
torch.manual_seed(seed)
|
|
torch.cuda.manual_seed_all(seed)
|
|
|
|
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
|
|
# device = torch.device("mps")
|
|
|
|
# Hyper-parameters
|
|
num_epochs = 1
|
|
batch_size = 64
|
|
learning_rate = 0.2
|
|
|
|
transform = transforms.Compose([transforms.ToTensor()])
|
|
|
|
train_dataset = torchvision.datasets.MNIST(root="./data", train=True, download=True, transform=transform)
|
|
test_dataset = torchvision.datasets.MNIST(root="./data", train=False, download=True, transform=transform)
|
|
train_loader = torch.utils.data.DataLoader(train_dataset, batch_size=batch_size, shuffle=True)
|
|
test_loader = torch.utils.data.DataLoader(test_dataset, batch_size=batch_size, shuffle=False)
|
|
|
|
|
|
class ConvNet(nn.Module):
|
|
def __init__(self):
|
|
super(ConvNet, self).__init__()
|
|
self.conv1 = nn.Conv2d(1, 8, 5, 1, 0)
|
|
self.pool = nn.MaxPool2d(2, 2)
|
|
self.conv2 = nn.Conv2d(8, 1, 5, 1, 0)
|
|
self.fc1 = nn.Linear(1 * 4 * 4, 10)
|
|
# self.fc2 = nn.Linear(120, 84)
|
|
# self.fc3 = nn.Linear(84, 10)
|
|
|
|
def forward(self, x):
|
|
x = self.pool(F.relu(self.conv1(x)))
|
|
x = self.pool(F.relu(self.conv2(x)))
|
|
x = x.view(x.shape[0], -1)
|
|
# x = F.relu(self.fc1(x))
|
|
# x = F.relu(self.fc2(x))
|
|
# x = self.fc3(x)
|
|
|
|
x = self.fc1(x)
|
|
return x
|
|
|
|
def printFector(self, x, label):
|
|
show.DumpTensorToImage(x.view(-1, x.shape[2], x.shape[3]), "input_image.png", Contrast=[0, 1.0])
|
|
# show.DumpTensorToLog(x, "input_image.log")
|
|
x = self.conv1(x)
|
|
w = self.conv1.weight
|
|
show.DumpTensorToImage(w.view(-1, w.shape[2], w.shape[3]), "conv1_weight.png", Contrast=[-1.0, 1.0])
|
|
# show.DumpTensorToLog(w, "conv1_weight.log")
|
|
|
|
show.DumpTensorToImage(x.view(-1, x.shape[2], x.shape[3]), "conv1_output.png", Contrast=[-1.0, 1.0])
|
|
# show.DumpTensorToLog(x, "conv1_output.png")
|
|
|
|
x = self.pool(F.relu(x))
|
|
x = self.conv2(x)
|
|
w = self.conv2.weight
|
|
show.DumpTensorToImage(w.view(-1, w.shape[2], w.shape[3]).cpu(), "conv2_weight.png", Contrast=[-1.0, 1.0])
|
|
|
|
show.DumpTensorToImage(x.view(-1, x.shape[2], x.shape[3]).cpu(), "conv2_output.png", Contrast=[-1.0, 1.0])
|
|
x = self.pool(F.relu(x))
|
|
show.DumpTensorToImage(x.view(-1, x.shape[2], x.shape[3]).cpu(), "pool_output.png", Contrast=[-1.0, 1.0])
|
|
pool_shape = x.shape
|
|
x = x.view(x.shape[0], -1)
|
|
x = self.fc1(x)
|
|
show.DumpTensorToImage(
|
|
self.fc1.weight.view(-1, pool_shape[2], pool_shape[3]), "fc_weight.png", Contrast=[-1.0, 1.0]
|
|
)
|
|
show.DumpTensorToImage(x.view(-1).cpu(), "fc_output.png")
|
|
|
|
criterion = nn.CrossEntropyLoss()
|
|
loss = criterion(x, label)
|
|
optimizer.zero_grad()
|
|
loss.backward()
|
|
|
|
w = self.conv1.weight.grad
|
|
show.DumpTensorToImage(w.view(-1, w.shape[2], w.shape[3]).cpu(), "conv1_weight_grad.png")
|
|
w = self.conv2.weight.grad
|
|
show.DumpTensorToImage(w.view(-1, w.shape[2], w.shape[3]), "conv2_weight_grad.png")
|
|
show.DumpTensorToImage(self.fc1.weight.grad.view(-1, pool_shape[2], pool_shape[3]), "fc_weight_grad.png")
|
|
|
|
|
|
model = ConvNet().to(device)
|
|
|
|
criterion = nn.CrossEntropyLoss()
|
|
optimizer = torch.optim.SGD(model.parameters(), lr=learning_rate)
|
|
|
|
|
|
# Train the model
|
|
n_total_steps = len(train_loader)
|
|
for epoch in range(num_epochs):
|
|
for i, (images, labels) in enumerate(train_loader):
|
|
images = images.to(device)
|
|
labels = labels.to(device)
|
|
|
|
# Forward pass
|
|
outputs = model(images)
|
|
loss = criterion(outputs, labels)
|
|
|
|
# Backward and optimize
|
|
optimizer.zero_grad()
|
|
loss.backward()
|
|
optimizer.step()
|
|
|
|
if (i + 1) % 100 == 0:
|
|
print(f"Epoch [{epoch+1}/{num_epochs}], Step [{i+1}/{n_total_steps}], Loss: {loss.item():.4f}")
|
|
|
|
test_loader = torch.utils.data.DataLoader(test_dataset, batch_size=1, shuffle=False)
|
|
for images, labels in test_loader:
|
|
images = images.to(device)
|
|
labels = labels.to(device)
|
|
model.printFector(images, labels)
|
|
break
|
|
|
|
print("Finished Training")
|
|
|
|
# Test the model
|
|
with torch.no_grad():
|
|
n_correct = 0
|
|
n_samples = 0
|
|
for images, labels in test_loader:
|
|
images = images.to(device)
|
|
labels = labels.to(device)
|
|
outputs = model(images)
|
|
|
|
# max returns (value ,index)
|
|
_, predicted = torch.max(outputs.data, 1)
|
|
n_samples += labels.size(0)
|
|
n_correct += (predicted == labels).sum().item()
|
|
|
|
acc = 100.0 * n_correct / n_samples
|
|
print(f"Accuracy of the network on the 10000 test images: {acc} %")
|