371 lines
14 KiB
Python
371 lines
14 KiB
Python
import numpy as np
|
|
import torch
|
|
from tqdm import tqdm
|
|
from sklearn.metrics import roc_auc_score, accuracy_score
|
|
import copy
|
|
import torch.nn.functional as F
|
|
import random
|
|
|
|
|
|
def train_deepmodel(device, model, loader, optimizer, criterion, epoch, model_name):
|
|
model.train()
|
|
running_loss = 0.0
|
|
corrects = 0.0
|
|
alpha = 1
|
|
beta = 0.1
|
|
for inputs, labels in tqdm(loader, desc=f'Training {model_name} Epoch {epoch + 1}', unit='batch'):
|
|
inputs, labels = inputs.float().to(device), labels.to(device) # 确保数据在 device 上
|
|
optimizer.zero_grad()
|
|
|
|
outputs, re_img = model(inputs)
|
|
loss = criterion(outputs.squeeze(), labels.float())
|
|
loss_F1 = F.l1_loss(re_img, inputs)
|
|
loss = alpha * loss + beta * loss_F1
|
|
loss.backward()
|
|
optimizer.step()
|
|
|
|
running_loss += loss.item()
|
|
|
|
avg_loss = running_loss / len(loader)
|
|
print(f'{model_name} Training Loss: {avg_loss:.4f}')
|
|
return avg_loss
|
|
|
|
|
|
def validate_deepmodel(device, model, loader, criterion, epoch, model_name):
|
|
model.eval()
|
|
running_loss = 0.0
|
|
correct, total = 0, 0
|
|
all_labels, all_preds = [], []
|
|
val_corrects = 0.0
|
|
alpha = 1
|
|
beta = 0.1
|
|
|
|
with torch.no_grad():
|
|
for inputs, labels in tqdm(loader, desc=f'Validating {model_name} Epoch {epoch + 1}', unit='batch'):
|
|
inputs, labels = inputs.float().to(device), labels.to(device) # 确保数据在 device 上
|
|
|
|
outputs, re_img = model(inputs)
|
|
|
|
# 将 logits 转换为预测
|
|
predicted = torch.sigmoid(outputs).data
|
|
all_preds.extend(predicted.cpu().numpy())
|
|
all_labels.extend(labels.cpu().numpy())
|
|
|
|
# loss = criterion(outputs.squeeze(), labels.float())
|
|
loss = criterion(outputs.squeeze(), labels.float())
|
|
loss_F1 = F.l1_loss(re_img, inputs)
|
|
loss = alpha * loss + beta * loss_F1
|
|
running_loss += loss.item()
|
|
|
|
auc = roc_auc_score(all_labels, all_preds)
|
|
predicted_labels = (np.array(all_preds) >= 0.5).astype(int) # 确保转换为 NumPy 数组
|
|
acc = accuracy_score(all_labels, predicted_labels)
|
|
avg_loss = running_loss / len(loader)
|
|
print(f'{model_name} Validation Loss: {avg_loss:.4f}, Accuracy: {acc:.4f}, AUC: {auc:.4f}')
|
|
return avg_loss, acc, auc
|
|
|
|
|
|
def test_deepmodel(device, model, loader):
|
|
model.eval()
|
|
all_labels, all_preds = [], []
|
|
|
|
with torch.no_grad():
|
|
for inputs, labels in tqdm(loader, desc=f'Testing', unit='batch'):
|
|
inputs, labels = inputs.float().to(device), labels.to(device) # 确保数据在 device 上
|
|
outputs, re_img = model(inputs)
|
|
predicted = torch.sigmoid(outputs).data # 将 logits 转换为预测
|
|
|
|
# 收集预测值和真实标签
|
|
all_preds.extend(predicted.cpu().numpy())
|
|
all_labels.extend(labels.cpu().numpy())
|
|
|
|
# 将预测值转换为二值标签
|
|
predicted_labels = (np.array(all_preds) >= 0.5).astype(int)
|
|
|
|
# 计算准确率和AUC
|
|
acc = accuracy_score(all_labels, predicted_labels)
|
|
auc = roc_auc_score(all_labels, all_preds)
|
|
|
|
print(f'Test Accuracy: {acc:.4f}, Test AUC: {auc:.4f}')
|
|
return acc, auc
|
|
|
|
|
|
# def train_model(device, model, loader, optimizer, criterion, epoch, model_name):
|
|
# model.train()
|
|
# running_loss = 0.0
|
|
# for i, (inputs, labels) in enumerate(tqdm(loader, desc=f'Training {model_name} Epoch {epoch + 1}', unit='batch')):
|
|
# inputs, labels = inputs.float().to(device), labels.float().to(device) # 确保数据格式正确
|
|
# optimizer.zero_grad()
|
|
#
|
|
# outputs = model(inputs)
|
|
# loss = criterion(outputs.squeeze(), labels)
|
|
#
|
|
# # 随机打印部分输出和标签，检查格式
|
|
# if i % 10 == 0: # 每100个批次打印一次
|
|
# print(f"Batch {i} - Sample Output: {outputs[0].item():.4f}, Sample Label: {labels[0].item()}")
|
|
#
|
|
# # 检查损失值是否异常
|
|
# if loss.item() < 0:
|
|
# print(f"Warning: Negative loss detected at batch {i}. Loss: {loss.item()}")
|
|
#
|
|
# loss.backward()
|
|
# optimizer.step()
|
|
#
|
|
# running_loss += loss.item()
|
|
#
|
|
# avg_loss = running_loss / len(loader)
|
|
# print(f'{model_name} Training Loss: {avg_loss:.4f}')
|
|
# return avg_loss
|
|
|
|
def train_model(device, model, loader, optimizer, criterion, epoch, model_name):
|
|
model.train()
|
|
running_loss = 0.0
|
|
for inputs, labels in tqdm(loader, desc=f'Training {model_name} Epoch {epoch + 1}', unit='batch'):
|
|
inputs, labels = inputs.float().to(device), labels.to(device) # 确保数据在 device 上
|
|
optimizer.zero_grad()
|
|
|
|
outputs = model(inputs)
|
|
loss = criterion(outputs.squeeze(), labels.float())
|
|
loss.backward()
|
|
optimizer.step()
|
|
|
|
running_loss += loss.item()
|
|
|
|
avg_loss = running_loss / len(loader)
|
|
print(f'{model_name} Training Loss: {avg_loss:.4f}')
|
|
return avg_loss
|
|
|
|
|
|
def validate_model(device, model, loader, criterion, epoch, model_name):
|
|
model.eval()
|
|
running_loss = 0.0
|
|
correct, total = 0, 0
|
|
all_labels, all_preds = [], []
|
|
|
|
with torch.no_grad():
|
|
for inputs, labels in tqdm(loader, desc=f'Validating {model_name} Epoch {epoch + 1}', unit='batch'):
|
|
inputs, labels = inputs.float().to(device), labels.to(device) # 确保数据在 device 上
|
|
|
|
outputs = model(inputs)
|
|
|
|
# 将 logits 转换为预测
|
|
predicted = torch.sigmoid(outputs).data
|
|
all_preds.extend(predicted.cpu().numpy())
|
|
all_labels.extend(labels.cpu().numpy())
|
|
|
|
# loss = criterion(outputs.squeeze(), labels.float())
|
|
loss = criterion(outputs.squeeze(), labels.float())
|
|
running_loss += loss.item()
|
|
auc = roc_auc_score(all_labels, all_preds)
|
|
predicted_labels = (np.array(all_preds) >= 0.5).astype(int) # 确保转换为 NumPy 数组
|
|
acc = accuracy_score(all_labels, predicted_labels)
|
|
avg_loss = running_loss / len(loader)
|
|
print(f'{model_name} Validation Loss: {avg_loss:.4f}, Accuracy: {acc:.4f}, AUC: {auc:.4f}')
|
|
return avg_loss, acc, auc
|
|
|
|
|
|
# 权重聚合函数
|
|
def aggregate_weights(weights_list, alpha=1 / 3, beta=1 / 3, gamma=1 / 3):
|
|
new_state_dict = copy.deepcopy(weights_list[0]) # 从模型a复制权重结构
|
|
for key in new_state_dict.keys():
|
|
new_state_dict[key] = (alpha * weights_list[0][key] +
|
|
beta * weights_list[1][key] +
|
|
gamma * weights_list[2][key])
|
|
return new_state_dict
|
|
|
|
|
|
def v3_update_model_weights(
|
|
epoch,
|
|
model_to_update,
|
|
other_models,
|
|
global_model,
|
|
losses,
|
|
val_loader,
|
|
device,
|
|
val_auc_threshold, # 当前需要更新模型的验证 AUC 阈值
|
|
validate_model,
|
|
criterion,
|
|
update_frequency
|
|
):
|
|
"""
|
|
根据给定的条件更新模型的权重。
|
|
|
|
参数:
|
|
epoch (int): 当前训练轮次。
|
|
model_to_update: 需要更新的模型。
|
|
other_models (list): 其他模型列表，用于计算全局模型权重。
|
|
global_model: 全局模型。
|
|
losses (list): 各模型的损失值列表。
|
|
val_loader: 验证数据的 DataLoader。
|
|
device: 设备 ('cuda' 或 'cpu')。
|
|
val_auc_threshold (float): 当前需要更新模型的验证 AUC。
|
|
aggregate_weights (function): 权重聚合函数。
|
|
validate_model (function): 验证模型的函数。
|
|
update_frequency (int): 权重更新的频率。
|
|
|
|
返回:
|
|
val_acc (float): 全局模型的验证精度。
|
|
val_auc (float): 全局模型的验证 AUC。
|
|
updated_val_auc_threshold (float): 更新后的验证 AUC。
|
|
"""
|
|
if (epoch + 1) % update_frequency == 0:
|
|
# 获取所有模型的权重
|
|
all_weights = [model.state_dict() for model in other_models]
|
|
avg_weights = aggregate_weights(all_weights) # 聚合权重
|
|
|
|
# 更新全局模型权重
|
|
global_model.load_state_dict(avg_weights)
|
|
|
|
# 计算加权平均损失
|
|
weighted_loss = sum(loss * 0.33 for loss in losses)
|
|
print(f"Weighted Average Loss: {weighted_loss:.4f}")
|
|
|
|
# 验证全局模型
|
|
val_loss, val_acc, val_auc = validate_model(device, global_model, val_loader, criterion, epoch, 'global_model')
|
|
print(f'global_model Validation Accuracy: {val_acc:.4f}, global_model Validation AUC: {val_auc:.4f}')
|
|
|
|
# 如果全局模型的 AUC 更高，则更新目标模型
|
|
if val_auc > val_auc_threshold:
|
|
print(f'Updating model at epoch {epoch + 1}')
|
|
model_to_update.load_state_dict(global_model.state_dict())
|
|
val_auc_threshold = val_auc # 更新 AUC 阈值
|
|
|
|
return val_acc, val_auc, val_auc_threshold
|
|
return None, None, val_auc_threshold
|
|
|
|
|
|
def update_model_weights(
|
|
epoch,
|
|
model_to_update,
|
|
other_models,
|
|
global_model,
|
|
losses,
|
|
val_loader,
|
|
device,
|
|
val_auc_threshold, # 当前需要更新模型的验证 AUC 阈值
|
|
validate_model,
|
|
criterion,
|
|
update_frequency
|
|
):
|
|
"""
|
|
根据给定的条件更新模型的权重。
|
|
|
|
参数:
|
|
epoch (int): 当前训练轮次。
|
|
model_to_update: 需要更新的模型。
|
|
other_models (list): 其他模型列表，用于计算全局模型权重。
|
|
global_model: 全局模型。
|
|
losses (list): 各模型的损失值列表。
|
|
val_loader: 验证数据的 DataLoader。
|
|
device: 设备 ('cuda' 或 'cpu')。
|
|
val_auc_threshold (float): 当前需要更新模型的验证 AUC。
|
|
aggregate_weights (function): 权重聚合函数。
|
|
validate_model (function): 验证模型的函数。
|
|
update_frequency (int): 权重更新的频率。
|
|
|
|
返回:
|
|
val_acc (float): 全局模型的验证精度。
|
|
val_auc (float): 全局模型的验证 AUC。
|
|
updated_val_auc_threshold (float): 更新后的验证 AUC。
|
|
"""
|
|
if (epoch + 1) % update_frequency == 0:
|
|
# 获取所有模型的权重
|
|
all_weights = [model.state_dict() for model in other_models]
|
|
avg_weights = aggregate_weights(all_weights) # 聚合权重
|
|
|
|
# 更新全局模型权重
|
|
global_model.load_state_dict(avg_weights)
|
|
|
|
# 计算加权平均损失
|
|
weighted_loss = sum(loss * 0.33 for loss in losses)
|
|
print(f"Weighted Average Loss: {weighted_loss:.4f}")
|
|
|
|
# 验证全局模型
|
|
val_loss, val_acc, val_auc = validate_deepmodel(device, global_model, val_loader, criterion, epoch,
|
|
'global_model')
|
|
print(f'global_model Validation Accuracy: {val_acc:.4f}, global_model Validation AUC: {val_auc:.4f}')
|
|
|
|
# 如果全局模型的 AUC 更高，则更新目标模型
|
|
if val_auc > val_auc_threshold:
|
|
print(f'Updating model at epoch {epoch + 1}')
|
|
model_to_update.load_state_dict(global_model.state_dict())
|
|
val_auc_threshold = val_auc # 更新 AUC 阈值
|
|
|
|
return val_acc, val_auc, val_auc_threshold
|
|
return None, None, val_auc_threshold
|
|
|
|
|
|
def f_update_model_weights(
|
|
epoch,
|
|
model_to_update,
|
|
other_models,
|
|
global_model,
|
|
losses,
|
|
val_loader,
|
|
device,
|
|
val_auc_threshold, # 当前需要更新模型的验证 AUC 阈值
|
|
aggregate_weights, # 权重聚合函数
|
|
validate_model,
|
|
criterion,
|
|
update_frequency
|
|
):
|
|
"""
|
|
根据给定的条件更新模型的权重。
|
|
|
|
参数:
|
|
epoch (int): 当前训练轮次。
|
|
model_to_update: 需要更新的模型。
|
|
other_models (list): 其他模型列表，用于计算全局模型权重。
|
|
global_model: 全局模型。
|
|
losses (list): 各模型的损失值列表。
|
|
val_loader: 验证数据的 DataLoader。
|
|
device: 设备 ('cuda' 或 'cpu')。
|
|
val_auc_threshold (float): 当前需要更新模型的验证 AUC 阈值。
|
|
aggregate_weights (function): 权重聚合函数。
|
|
validate_model (function): 验证模型的函数。
|
|
criterion: 损失函数。
|
|
update_frequency (int): 权重更新的频率。
|
|
|
|
返回:
|
|
val_acc (float): 全局模型的验证精度。
|
|
val_auc (float): 全局模型的验证 AUC。
|
|
updated_val_auc_threshold (float): 更新后的验证 AUC 阈值。
|
|
"""
|
|
# 每隔指定的 epoch 更新一次模型权重
|
|
|
|
if (epoch + 1) % update_frequency == 0:
|
|
print(f"\n[Epoch {epoch + 1}] Updating global model weights...")
|
|
|
|
# 获取其他模型的权重
|
|
all_weights = [model.state_dict() for model in other_models]
|
|
|
|
# 使用聚合函数计算全局权重
|
|
avg_weights = aggregate_weights(all_weights)
|
|
print("Global model weights aggregated.")
|
|
|
|
# 更新全局模型权重
|
|
global_model.load_state_dict(avg_weights)
|
|
|
|
# 计算加权平均损失
|
|
weighted_loss = sum(loss * (1 / len(losses)) for loss in losses) # 平均加权
|
|
print(f"Weighted Average Loss: {weighted_loss:.4f}")
|
|
|
|
# 验证全局模型性能
|
|
val_loss, val_acc, val_auc = validate_deepmodel(device, global_model, val_loader, criterion, epoch,
|
|
'global_model')
|
|
print(f"[Global Model] Validation Loss: {val_loss:.4f}, Accuracy: {val_acc:.4f}, AUC: {val_auc:.4f}")
|
|
|
|
# 如果全局模型 AUC 高于阈值，则更新目标模型权重
|
|
if val_auc > val_auc_threshold:
|
|
print(f"Global model AUC improved ({val_auc:.4f} > {val_auc_threshold:.4f}). Updating target model.")
|
|
model_to_update.load_state_dict(global_model.state_dict())
|
|
val_auc_threshold = val_auc # 更新 AUC 阈值
|
|
else:
|
|
print(
|
|
f"Global model AUC did not improve ({val_auc:.4f} <= {val_auc_threshold:.4f}). No update to target model.")
|
|
|
|
return val_acc, val_auc, val_auc_threshold
|
|
|
|
# 如果未到达更新频率，返回当前的 AUC 阈值
|
|
return None, None, val_auc_threshold
|