Я пытаюсь отредактируйте приведенный выше код для работы с моим пользовательским набором данных для двоичной классификации. Я ценю вашу помощь!
Код: Выделить всё
from google.colab import drive
drive.mount('/content/drive')
%%writefile get_data.py
import os
import zipfile
from pathlib import Path
import requests
# Setup path to data folder
data_path = Path("/content/drive/MyDrive/Dataset/")
image_path = data_path / "/content/drive/MyDrive/Dataset/Datas"
# If the image folder doesn't exist, download it and prepare it...
if image_path.is_dir():
print(f"{image_path} directory exists.")
else:
print(f"Did not find {image_path} directory, creating one...")
image_path.mkdir(parents=True, exist_ok=True)
%%writefile data_setup.py
"""
Contains functionality for creating PyTorch DataLoaders for
image classification data.
"""
import os
from torchvision import datasets, transforms
from torch.utils.data import DataLoader
NUM_WORKERS = os.cpu_count()
def create_dataloaders(
train_dir: str,
test_dir: str,
transform: transforms.Compose,
batch_size: int,
num_workers: int=NUM_WORKERS
):
# Use ImageFolder to create dataset(s)
train_data = datasets.ImageFolder(train_dir, transform=transform)
test_data = datasets.ImageFolder(test_dir, transform=transform)
# Get class names
class_names = train_data.classes
# Turn images into data loaders
train_dataloader = DataLoader(
train_data,
batch_size=batch_size,
shuffle=True,
num_workers=num_workers,
pin_memory=True,
)
test_dataloader = DataLoader(
test_data,
batch_size=batch_size,
shuffle=False,
num_workers=num_workers,
pin_memory=True,
)
return train_dataloader, test_dataloader, class_names
%%writefile engine.py
"""
Contains functions for training and testing a PyTorch model.
"""
import torch
from tqdm.auto import tqdm
from typing import Dict, List, Tuple
def train_step(model: torch.nn.Module,
dataloader: torch.utils.data.DataLoader,
loss_fn: torch.nn.Module,
optimizer: torch.optim.Optimizer,
device: torch.device) -> Tuple[float, float]:
# Put model in train mode
model.train()
# Setup train loss and train accuracy values
train_loss, train_acc = 0, 0
# Loop through data loader data batches
for batch, (X, y) in enumerate(dataloader):
# Send data to target device
X, y = X.to(device), y.to(device)
y=y.unsqueeze(1).float()
# 1. Forward pass
y_pred = model(X)
# 2. Calculate and accumulate loss
loss = loss_fn(y_pred, y)
train_loss += loss.item()
# 3. Optimizer zero grad
optimizer.zero_grad()
# 4. Loss backward
loss.backward()
# 5. Optimizer step
optimizer.step()
# Calculate and accumulate accuracy metric across all batches
y_pred_class = torch.round(torch.sigmoid(y_pred))
train_acc += (y_pred_class == y).sum().item()/len(y_pred)
# Adjust metrics to get average loss and accuracy per batch
train_loss = train_loss / len(dataloader)
train_acc = train_acc / len(dataloader)
return train_loss, train_acc
def test_step(model: torch.nn.Module,
dataloader: torch.utils.data.DataLoader,
loss_fn: torch.nn.Module,
device: torch.device) -> Tuple[float, float]:
# Put model in eval mode
model.eval()
# Setup test loss and test accuracy values
test_loss, test_acc = 0, 0
# Turn on inference context manager
with torch.inference_mode():
# Loop through DataLoader batches
for batch, (X, y) in enumerate(dataloader):
# Send data to target device
X, y = X.to(device), y.to(device)
y=y.unsqueeze(1).float()
# 1. Forward pass
test_pred_logits = model(X)
# 2. Calculate and accumulate loss
loss = loss_fn(test_pred_logits, y)
test_loss += loss.item()
# Calculate and accumulate accuracy
test_pred_labels = torch.round(torch.sigmoid(test_pred_logits))
test_acc += ((test_pred_labels == y).sum().item()/len(test_pred_labels))
# Adjust metrics to get average loss and accuracy per batch
test_loss = test_loss / len(dataloader)
test_acc = test_acc / len(dataloader)
return test_loss, test_acc
def train(model: torch.nn.Module,
train_dataloader: torch.utils.data.DataLoader,
test_dataloader: torch.utils.data.DataLoader,
optimizer: torch.optim.Optimizer,
loss_fn: torch.nn.Module,
epochs: int,
device: torch.device) -> Dict[str, List]:
# Create empty results dictionary
results = {"train_loss": [],
"train_acc": [],
"test_loss": [],
"test_acc": []
}
# Loop through training and testing steps for a number of epochs
for epoch in tqdm(range(epochs)):
train_loss, train_acc = train_step(model=model,
dataloader=train_dataloader,
loss_fn=loss_fn,
optimizer=optimizer,
device=device)
test_loss, test_acc = test_step(model=model,
dataloader=test_dataloader,
loss_fn=loss_fn,
device=device)
# Print out what's happening
print(
f"Epoch: {epoch+1} | "
f"train_loss: {train_loss:.4f} | "
f"train_acc: {train_acc:.4f} | "
f"test_loss: {test_loss:.4f} | "
f"test_acc: {test_acc:.4f}"
)
# Update results dictionary
results["train_loss"].append(train_loss)
results["train_acc"].append(train_acc)
results["test_loss"].append(test_loss)
results["test_acc"].append(test_acc)
# Return the filled results at the end of the epochs
return results
%%writefile model_builder.py
"""
Contains PyTorch model code to instantiate a TinyVGG model.
"""
import torch
from torch import nn
class TinyVGG(nn.Module):
def __init__(self, input_shape: int, hidden_units: int, output_shape: int) -> None:
super().__init__()
self.conv_block_1 = nn.Sequential(
nn.Conv2d(in_channels=input_shape,
out_channels=hidden_units,
kernel_size=3,
stride=1,
padding=0),
nn.ReLU(),
nn.Conv2d(in_channels=hidden_units,
out_channels=hidden_units,
kernel_size=3,
stride=1,
padding=0),
nn.ReLU(),
nn.MaxPool2d(kernel_size=2,
stride=2)
)
self.conv_block_2 = nn.Sequential(
nn.Conv2d(hidden_units, hidden_units, kernel_size=3, padding=0),
nn.ReLU(),
nn.Conv2d(hidden_units, hidden_units, kernel_size=3, padding=0),
nn.ReLU(),
nn.MaxPool2d(2)
)
self.classifier = nn.Sequential(
nn.Flatten(),
# Where did this in_features shape come from?
# It's because each layer of our network compresses and changes the shape of our inputs data.
nn.Linear(in_features=hidden_units*13*13,
out_features=1)
)
def forward(self, x: torch.Tensor):
x = self.conv_block_1(x)
x = self.conv_block_2(x)
x = self.classifier(x)
return x
# return self.classifier(self.block_2(self.block_1(x))) #
Подробнее здесь: [url]https://stackoverflow.com/questions/79014942/how-can-i-convert-this-code-into-binary-classification[/url]