计算精度问题
issue with calculating accuracy
我正在使用 Torch Metrics 来尝试计算我的模型的准确性。但是我收到了这个错误。我尝试使用 .to(device="cuda:0") 但出现 cuda 初始化错误。我也尝试使用 .cuda() 但这也没有用。我在 Titan Xp GPU 上使用 PyTorch 闪电。我在 Movie-lens 数据集上使用了 mish 激活函数。
代码：
# %% [markdown]
# # Data Preprocessing
#
# Before we start building and training our model, let's do some preprocessing to get the data in the required format.
# %% [code] {"_kg_hide-input":true,"_kg_hide-output":true}
import pandas as pd
import numpy as np
from tqdm.notebook import tqdm
import torch
import torch.nn as nn
from torch.utils.data import Dataset, DataLoader
import pytorch_lightning as pl
import torch.nn.functional as F
from pytorch_lightning.callbacks import EarlyStopping
import wandb
import torchmetrics
wandb.init(project="Mocean-Recommendor",entity="maxall4")
config = wandb.config
def mish(x):
return (x*torch.tanh(F.softplus(x)))
np.random.seed(123)
# %% [markdown]
# First, we import the ratings dataset.
# %% [code]
ratings = pd.read_csv('rating.csv',
parse_dates=['timestamp'])
# %% [markdown]
# In order to keep memory usage manageable within Kaggle's kernel, we will only use data from 30% of the users in this dataset. Let's randomly select 30% of the users and only use data from the selected users.
# %% [code]
rand_userIds = np.random.choice(ratings['userId'].unique(),
size=int(len(ratings['userId'].unique())*0.3),
replace=False)
ratings = ratings.loc[ratings['userId'].isin(rand_userIds)]
print('There are {} rows of data from {} users'.format(len(ratings), len(rand_userIds)))
# %% [code]
ratings.sample(5)
# %% [code]
ratings['rank_latest'] = ratings.groupby(['userId'])['timestamp'] \
.rank(method='first', ascending=False)
train_ratings = ratings[ratings['rank_latest'] != 1]
test_ratings = ratings[ratings['rank_latest'] == 1]
# drop columns that we no longer need
train_ratings = train_ratings[['userId', 'movieId', 'rating']]
test_ratings = test_ratings[['userId', 'movieId', 'rating']]
# %% [markdown]
# ### Converting the dataset into an implicit feedback dataset
# %% [code]
train_ratings.loc[:, 'rating'] = 1
train_ratings.sample(5)
# %% [markdown]
# The code below generates 4 negative samples for each row of data. In other words, the ratio of negative to positive samples is 4:1. This ratio is chosen arbitrarily but I found that it works rather well (feel free to find the best ratio yourself!)
# %% [code]
# Get a list of all movie IDs
all_movieIds = ratings['movieId'].unique()
# Placeholders that will hold the training data
users, items, labels = [], [], []
# This is the set of items that each user has interaction with
user_item_set = set(zip(train_ratings['userId'], train_ratings['movieId']))
# 4:1 ratio of negative to positive samples
num_negatives = 4
for (u, i) in tqdm(user_item_set):
users.append(u)
items.append(i)
labels.append(1) # items that the user has interacted with are positive
for _ in range(num_negatives):
# randomly select an item
negative_item = np.random.choice(all_movieIds)
# check that the user has not interacted with this item
while (u, negative_item) in user_item_set:
negative_item = np.random.choice(all_movieIds)
users.append(u)
items.append(negative_item)
labels.append(0) # items not interacted with are negative
# %% [code]
class MovieLensTrainDataset(Dataset):
"""MovieLens PyTorch Dataset for Training
Args:
ratings (pd.DataFrame): Dataframe containing the movie ratings
all_movieIds (list): List containing all movieIds
"""
def __init__(self, ratings, all_movieIds):
self.users, self.items, self.labels = self.get_dataset(ratings, all_movieIds)
def __len__(self):
return len(self.users)
def __getitem__(self, idx):
return self.users[idx], self.items[idx], self.labels[idx]
def get_dataset(self, ratings, all_movieIds):
users, items, labels = [], [], []
user_item_set = set(zip(ratings['userId'], ratings['movieId']))
num_negatives = 4
for u, i in user_item_set:
users.append(u)
items.append(i)
labels.append(1)
for _ in range(num_negatives):
negative_item = np.random.choice(all_movieIds)
while (u, negative_item) in user_item_set:
negative_item = np.random.choice(all_movieIds)
users.append(u)
items.append(negative_item)
labels.append(0)
return torch.tensor(users), torch.tensor(items), torch.tensor(labels)
# %% [code]
acc_metric = torchmetrics.Accuracy()
class NCF(pl.LightningModule):
""" Neural Collaborative Filtering (NCF)
Args:
num_users (int): Number of unique users
num_items (int): Number of unique items
ratings (pd.DataFrame): Dataframe containing the movie ratings for training
all_movieIds (list): List containing all movieIds (train + test)
"""
def __init__(self, num_users, num_items, ratings, all_movieIds):
super().__init__()
self.user_embedding = nn.Embedding(num_embeddings=num_users, embedding_dim=8)
self.item_embedding = nn.Embedding(num_embeddings=num_items, embedding_dim=8)
self.fc1 = nn.Linear(in_features=16, out_features=64)
self.fc2 = nn.Linear(in_features=64, out_features=32)
self.output = nn.Linear(in_features=32, out_features=1)
self.ratings = ratings
self.all_movieIds = all_movieIds
def on_validation_end(self,outputs):
loss = torch.stack([x['val_loss'] for x in outputs]).mean()
return { 'loss' : loss }
def forward(self, user_input, item_input):
# Pass through embedding layers
user_embedded = self.user_embedding(user_input)
item_embedded = self.item_embedding(item_input)
# Concat the two embedding layers
vector = torch.cat([user_embedded, item_embedded], dim=-1)
# Pass through dense layer
vector = mish(self.fc1(vector))
vector = mish(self.fc2(vector))
# Output layer
pred = nn.Sigmoid()(self.output(vector))
return pred
def training_step(self, batch, batch_idx):
user_input, item_input, labels = batch
predicted_labels = self(user_input, item_input)
loss = nn.BCELoss()(predicted_labels, labels.view(-1, 1).float())
acc = acc_metric(predicted_labels,labels)
wandb.log({"loss": loss,"acc":acc})
return loss
def configure_optimizers(self):
return torch.optim.Adam(self.parameters())
def train_dataloader(self):
return DataLoader(MovieLensTrainDataset(self.ratings, self.all_movieIds),
batch_size=512, num_workers=4)
# %% [markdown]
# We instantiate the NCF model using the class that we have defined above.
# %% [code]
num_users = ratings['userId'].max()+1
num_items = ratings['movieId'].max()+1
all_movieIds = ratings['movieId'].unique()
model = NCF(num_users, num_items, train_ratings, all_movieIds)
# %% [code]
wandb.watch(model)
early_stopping = EarlyStopping(
monitor='loss',
min_delta=0.00,
patience=3,
verbose=False,
mode='min',
)
trainer = pl.Trainer(max_epochs=100, gpus=1, reload_dataloaders_every_epoch=True,
progress_bar_refresh_rate=50, logger=False, checkpoint_callback=True,callbacks=[early_stopping])
trainer.fit(model)
# %% [markdown]
# ### Hit Ratio @ 10
# %% [code]
# User-item pairs for testing
test_user_item_set = set(zip(test_ratings['userId'], test_ratings['movieId']))
# Dict of all items that are interacted with by each user
user_interacted_items = ratings.groupby('userId')['movieId'].apply(list).to_dict()
hits = []
for (u,i) in tqdm(test_user_item_set):
interacted_items = user_interacted_items[u]
not_interacted_items = set(all_movieIds) - set(interacted_items)
selected_not_interacted = list(np.random.choice(list(not_interacted_items), 99))
test_items = selected_not_interacted + [i]
predicted_labels = np.squeeze(model(torch.tensor([u]*100),
torch.tensor(test_items)).detach().numpy())
top10_items = [test_items[i] for i in np.argsort(predicted_labels)[::-1][0:10].tolist()]
if i in top10_items:
hits.append(1)
else:
hits.append(0)
print("The Hit Ratio @ 10 is {:.2f}".format(np.average(hits)))
wandb.log({"hit ratio": np.average(hits)})
错误：
Traceback (most recent call last):
File "main.py", line 359, in <module>
trainer = pl.Trainer(max_epochs=100, gpus=1, reload_dataloaders_every_epoch=True,
File "/home/max/.local/lib/python3.8/site-packages/pytorch_lightning/trainer/trainer.py", line 499, in fit
self.dispatch()
File "/home/max/.local/lib/python3.8/site-packages/pytorch_lightning/trainer/trainer.py", line 546, in dispatch
self.accelerator.start_training(self)
File "/home/max/.local/lib/python3.8/site-packages/pytorch_lightning/accelerators/accelerator.py", line 73, in start_training
self.training_type_plugin.start_training(trainer)
File "/home/max/.local/lib/python3.8/site-packages/pytorch_lightning/plugins/training_type/training_type_plugin.py", line 114, in start_training
self._results = trainer.run_train()
File "/home/max/.local/lib/python3.8/site-packages/pytorch_lightning/trainer/trainer.py", line 637, in run_train
self.train_loop.run_training_epoch()
File "/home/max/.local/lib/python3.8/site-packages/pytorch_lightning/trainer/training_loop.py", line 492, in run_training_epoch
batch_output = self.run_training_batch(batch, batch_idx, dataloader_idx)
File "/home/max/.local/lib/python3.8/site-packages/pytorch_lightning/trainer/training_loop.py", line 654, in run_training_batch
self.optimizer_step(optimizer, opt_idx, batch_idx, train_step_and_backward_closure)
File "/home/max/.local/lib/python3.8/site-packages/pytorch_lightning/trainer/training_loop.py", line 425, in optimizer_step
model_ref.optimizer_step(
File "/home/max/.local/lib/python3.8/site-packages/pytorch_lightning/core/lightning.py", line 1390, in optimizer_step
optimizer.step(closure=optimizer_closure)
File "/home/max/.local/lib/python3.8/site-packages/pytorch_lightning/core/optimizer.py", line 214, in step
self.__optimizer_step(*args, closure=closure, profiler_name=profiler_name, **kwargs)
File "/home/max/.local/lib/python3.8/site-packages/pytorch_lightning/core/optimizer.py", line 134, in __optimizer_step
trainer.accelerator.optimizer_step(optimizer, self._optimizer_idx, lambda_closure=closure, **kwargs)
File "/home/max/.local/lib/python3.8/site-packages/pytorch_lightning/accelerators/accelerator.py", line 277, in optimizer_step
self.run_optimizer_step(optimizer, opt_idx, lambda_closure, **kwargs)
File "/home/max/.local/lib/python3.8/site-packages/pytorch_lightning/accelerators/accelerator.py", line 282, in run_optimizer_step
self.training_type_plugin.optimizer_step(optimizer, lambda_closure=lambda_closure, **kwargs)
File "/home/max/.local/lib/python3.8/site-packages/pytorch_lightning/plugins/training_type/training_type_plugin.py", line 163, in optimizer_step
optimizer.step(closure=lambda_closure, **kwargs)
File "/home/max/.local/lib/python3.8/site-packages/torch/optim/optimizer.py", line 89, in wrapper
return func(*args, **kwargs)
File "/home/max/.local/lib/python3.8/site-packages/torch/autograd/grad_mode.py", line 27, in decorate_context
return func(*args, **kwargs)
File "/home/max/.local/lib/python3.8/site-packages/torch/optim/adam.py", line 66, in step
loss = closure()
File "/home/max/.local/lib/python3.8/site-packages/pytorch_lightning/trainer/training_loop.py", line 648, in train_step_and_backward_closure
result = self.training_step_and_backward(
File "/home/max/.local/lib/python3.8/site-packages/pytorch_lightning/trainer/training_loop.py", line 742, in training_step_and_backward
result = self.training_step(split_batch, batch_idx, opt_idx, hiddens)
File "/home/max/.local/lib/python3.8/site-packages/pytorch_lightning/trainer/training_loop.py", line 293, in training_step
training_step_output = self.trainer.accelerator.training_step(args)
File "/home/max/.local/lib/python3.8/site-packages/pytorch_lightning/accelerators/accelerator.py", line 156, in training_step
return self.training_type_plugin.training_step(*args)
File "/home/max/.local/lib/python3.8/site-packages/pytorch_lightning/plugins/training_type/training_type_plugin.py", line 125, in training_step
return self.lightning_module.training_step(*args, **kwargs)
File "main.py", line 318, in training_step
print(type(labels))
File "/home/max/.local/lib/python3.8/site-packages/torch/nn/modules/module.py", line 889, in _call_impl
result = self.forward(*input, **kwargs)
File "/home/max/.local/lib/python3.8/site-packages/torchmetrics/metric.py", line 152, in forward
self.update(*args, **kwargs)
File "/home/max/.local/lib/python3.8/site-packages/torchmetrics/metric.py", line 199, in wrapped_func
return update(*args, **kwargs)
File "/home/max/.local/lib/python3.8/site-packages/torchmetrics/classification/accuracy.py", line 142, in update
self.correct += correct
RuntimeError: Expected all tensors to be on the same device, but found at least two devices, cuda:0 and cpu!
我在这里解释一下，
这个命令：
print(next(model.parameters()).device)
它将打印加载模型参数的设备。
要检查它们是否加载到 GPU 上，您可以这样做：
print(next(model.parameters()).is_cuda)
它将return一个布尔值，
看到你的代码后，正如你提到的那样，打印时 returning "CPU"：
下一个(model.parameters()).device
表示你的模型参数是在CPU上加载的，但是这一行
trainer = pl.Trainer(max_epochs=100, gpus=1, reload_dataloaders_every_epoch=True,
progress_bar_refresh_rate=50, logger=False, checkpoint_callback=True,callbacks=[early_stopping])
这里gpus=1表示会设置要训练的gpus个数，
因为你所有的张量都默认加载 CPU，你得到了那个错误。
设置gpus=None后，不再使用gpus进行训练
在 GPU 上 运行：
您必须将张量从 CPU 移动到 GPU，
例如：
ex_tensor=torch.zeros((7,7))
ex_tensor = ex_tensor.cuda()
还有你的模型参数，
model = model.cuda()
我正在使用 Torch Metrics 来尝试计算我的模型的准确性。但是我收到了这个错误。我尝试使用 .to(device="cuda:0") 但出现 cuda 初始化错误。我也尝试使用 .cuda() 但这也没有用。我在 Titan Xp GPU 上使用 PyTorch 闪电。我在 Movie-lens 数据集上使用了 mish 激活函数。
代码：
# %% [markdown]
# # Data Preprocessing
#
# Before we start building and training our model, let's do some preprocessing to get the data in the required format.
# %% [code] {"_kg_hide-input":true,"_kg_hide-output":true}
import pandas as pd
import numpy as np
from tqdm.notebook import tqdm
import torch
import torch.nn as nn
from torch.utils.data import Dataset, DataLoader
import pytorch_lightning as pl
import torch.nn.functional as F
from pytorch_lightning.callbacks import EarlyStopping
import wandb
import torchmetrics
wandb.init(project="Mocean-Recommendor",entity="maxall4")
config = wandb.config
def mish(x):
return (x*torch.tanh(F.softplus(x)))
np.random.seed(123)
# %% [markdown]
# First, we import the ratings dataset.
# %% [code]
ratings = pd.read_csv('rating.csv',
parse_dates=['timestamp'])
# %% [markdown]
# In order to keep memory usage manageable within Kaggle's kernel, we will only use data from 30% of the users in this dataset. Let's randomly select 30% of the users and only use data from the selected users.
# %% [code]
rand_userIds = np.random.choice(ratings['userId'].unique(),
size=int(len(ratings['userId'].unique())*0.3),
replace=False)
ratings = ratings.loc[ratings['userId'].isin(rand_userIds)]
print('There are {} rows of data from {} users'.format(len(ratings), len(rand_userIds)))
# %% [code]
ratings.sample(5)
# %% [code]
ratings['rank_latest'] = ratings.groupby(['userId'])['timestamp'] \
.rank(method='first', ascending=False)
train_ratings = ratings[ratings['rank_latest'] != 1]
test_ratings = ratings[ratings['rank_latest'] == 1]
# drop columns that we no longer need
train_ratings = train_ratings[['userId', 'movieId', 'rating']]
test_ratings = test_ratings[['userId', 'movieId', 'rating']]
# %% [markdown]
# ### Converting the dataset into an implicit feedback dataset
# %% [code]
train_ratings.loc[:, 'rating'] = 1
train_ratings.sample(5)
# %% [markdown]
# The code below generates 4 negative samples for each row of data. In other words, the ratio of negative to positive samples is 4:1. This ratio is chosen arbitrarily but I found that it works rather well (feel free to find the best ratio yourself!)
# %% [code]
# Get a list of all movie IDs
all_movieIds = ratings['movieId'].unique()
# Placeholders that will hold the training data
users, items, labels = [], [], []
# This is the set of items that each user has interaction with
user_item_set = set(zip(train_ratings['userId'], train_ratings['movieId']))
# 4:1 ratio of negative to positive samples
num_negatives = 4
for (u, i) in tqdm(user_item_set):
users.append(u)
items.append(i)
labels.append(1) # items that the user has interacted with are positive
for _ in range(num_negatives):
# randomly select an item
negative_item = np.random.choice(all_movieIds)
# check that the user has not interacted with this item
while (u, negative_item) in user_item_set:
negative_item = np.random.choice(all_movieIds)
users.append(u)
items.append(negative_item)
labels.append(0) # items not interacted with are negative
# %% [code]
class MovieLensTrainDataset(Dataset):
"""MovieLens PyTorch Dataset for Training
Args:
ratings (pd.DataFrame): Dataframe containing the movie ratings
all_movieIds (list): List containing all movieIds
"""
def __init__(self, ratings, all_movieIds):
self.users, self.items, self.labels = self.get_dataset(ratings, all_movieIds)
def __len__(self):
return len(self.users)
def __getitem__(self, idx):
return self.users[idx], self.items[idx], self.labels[idx]
def get_dataset(self, ratings, all_movieIds):
users, items, labels = [], [], []
user_item_set = set(zip(ratings['userId'], ratings['movieId']))
num_negatives = 4
for u, i in user_item_set:
users.append(u)
items.append(i)
labels.append(1)
for _ in range(num_negatives):
negative_item = np.random.choice(all_movieIds)
while (u, negative_item) in user_item_set:
negative_item = np.random.choice(all_movieIds)
users.append(u)
items.append(negative_item)
labels.append(0)
return torch.tensor(users), torch.tensor(items), torch.tensor(labels)
# %% [code]
acc_metric = torchmetrics.Accuracy()
class NCF(pl.LightningModule):
""" Neural Collaborative Filtering (NCF)
Args:
num_users (int): Number of unique users
num_items (int): Number of unique items
ratings (pd.DataFrame): Dataframe containing the movie ratings for training
all_movieIds (list): List containing all movieIds (train + test)
"""
def __init__(self, num_users, num_items, ratings, all_movieIds):
super().__init__()
self.user_embedding = nn.Embedding(num_embeddings=num_users, embedding_dim=8)
self.item_embedding = nn.Embedding(num_embeddings=num_items, embedding_dim=8)
self.fc1 = nn.Linear(in_features=16, out_features=64)
self.fc2 = nn.Linear(in_features=64, out_features=32)
self.output = nn.Linear(in_features=32, out_features=1)
self.ratings = ratings
self.all_movieIds = all_movieIds
def on_validation_end(self,outputs):
loss = torch.stack([x['val_loss'] for x in outputs]).mean()
return { 'loss' : loss }
def forward(self, user_input, item_input):
# Pass through embedding layers
user_embedded = self.user_embedding(user_input)
item_embedded = self.item_embedding(item_input)
# Concat the two embedding layers
vector = torch.cat([user_embedded, item_embedded], dim=-1)
# Pass through dense layer
vector = mish(self.fc1(vector))
vector = mish(self.fc2(vector))
# Output layer
pred = nn.Sigmoid()(self.output(vector))
return pred
def training_step(self, batch, batch_idx):
user_input, item_input, labels = batch
predicted_labels = self(user_input, item_input)
loss = nn.BCELoss()(predicted_labels, labels.view(-1, 1).float())
acc = acc_metric(predicted_labels,labels)
wandb.log({"loss": loss,"acc":acc})
return loss
def configure_optimizers(self):
return torch.optim.Adam(self.parameters())
def train_dataloader(self):
return DataLoader(MovieLensTrainDataset(self.ratings, self.all_movieIds),
batch_size=512, num_workers=4)
# %% [markdown]
# We instantiate the NCF model using the class that we have defined above.
# %% [code]
num_users = ratings['userId'].max()+1
num_items = ratings['movieId'].max()+1
all_movieIds = ratings['movieId'].unique()
model = NCF(num_users, num_items, train_ratings, all_movieIds)
# %% [code]
wandb.watch(model)
early_stopping = EarlyStopping(
monitor='loss',
min_delta=0.00,
patience=3,
verbose=False,
mode='min',
)
trainer = pl.Trainer(max_epochs=100, gpus=1, reload_dataloaders_every_epoch=True,
progress_bar_refresh_rate=50, logger=False, checkpoint_callback=True,callbacks=[early_stopping])
trainer.fit(model)
# %% [markdown]
# ### Hit Ratio @ 10
# %% [code]
# User-item pairs for testing
test_user_item_set = set(zip(test_ratings['userId'], test_ratings['movieId']))
# Dict of all items that are interacted with by each user
user_interacted_items = ratings.groupby('userId')['movieId'].apply(list).to_dict()
hits = []
for (u,i) in tqdm(test_user_item_set):
interacted_items = user_interacted_items[u]
not_interacted_items = set(all_movieIds) - set(interacted_items)
selected_not_interacted = list(np.random.choice(list(not_interacted_items), 99))
test_items = selected_not_interacted + [i]
predicted_labels = np.squeeze(model(torch.tensor([u]*100),
torch.tensor(test_items)).detach().numpy())
top10_items = [test_items[i] for i in np.argsort(predicted_labels)[::-1][0:10].tolist()]
if i in top10_items:
hits.append(1)
else:
hits.append(0)
print("The Hit Ratio @ 10 is {:.2f}".format(np.average(hits)))
wandb.log({"hit ratio": np.average(hits)})
错误：
Traceback (most recent call last):
File "main.py", line 359, in <module>
trainer = pl.Trainer(max_epochs=100, gpus=1, reload_dataloaders_every_epoch=True,
File "/home/max/.local/lib/python3.8/site-packages/pytorch_lightning/trainer/trainer.py", line 499, in fit
self.dispatch()
File "/home/max/.local/lib/python3.8/site-packages/pytorch_lightning/trainer/trainer.py", line 546, in dispatch
self.accelerator.start_training(self)
File "/home/max/.local/lib/python3.8/site-packages/pytorch_lightning/accelerators/accelerator.py", line 73, in start_training
self.training_type_plugin.start_training(trainer)
File "/home/max/.local/lib/python3.8/site-packages/pytorch_lightning/plugins/training_type/training_type_plugin.py", line 114, in start_training
self._results = trainer.run_train()
File "/home/max/.local/lib/python3.8/site-packages/pytorch_lightning/trainer/trainer.py", line 637, in run_train
self.train_loop.run_training_epoch()
File "/home/max/.local/lib/python3.8/site-packages/pytorch_lightning/trainer/training_loop.py", line 492, in run_training_epoch
batch_output = self.run_training_batch(batch, batch_idx, dataloader_idx)
File "/home/max/.local/lib/python3.8/site-packages/pytorch_lightning/trainer/training_loop.py", line 654, in run_training_batch
self.optimizer_step(optimizer, opt_idx, batch_idx, train_step_and_backward_closure)
File "/home/max/.local/lib/python3.8/site-packages/pytorch_lightning/trainer/training_loop.py", line 425, in optimizer_step
model_ref.optimizer_step(
File "/home/max/.local/lib/python3.8/site-packages/pytorch_lightning/core/lightning.py", line 1390, in optimizer_step
optimizer.step(closure=optimizer_closure)
File "/home/max/.local/lib/python3.8/site-packages/pytorch_lightning/core/optimizer.py", line 214, in step
self.__optimizer_step(*args, closure=closure, profiler_name=profiler_name, **kwargs)
File "/home/max/.local/lib/python3.8/site-packages/pytorch_lightning/core/optimizer.py", line 134, in __optimizer_step
trainer.accelerator.optimizer_step(optimizer, self._optimizer_idx, lambda_closure=closure, **kwargs)
File "/home/max/.local/lib/python3.8/site-packages/pytorch_lightning/accelerators/accelerator.py", line 277, in optimizer_step
self.run_optimizer_step(optimizer, opt_idx, lambda_closure, **kwargs)
File "/home/max/.local/lib/python3.8/site-packages/pytorch_lightning/accelerators/accelerator.py", line 282, in run_optimizer_step
self.training_type_plugin.optimizer_step(optimizer, lambda_closure=lambda_closure, **kwargs)
File "/home/max/.local/lib/python3.8/site-packages/pytorch_lightning/plugins/training_type/training_type_plugin.py", line 163, in optimizer_step
optimizer.step(closure=lambda_closure, **kwargs)
File "/home/max/.local/lib/python3.8/site-packages/torch/optim/optimizer.py", line 89, in wrapper
return func(*args, **kwargs)
File "/home/max/.local/lib/python3.8/site-packages/torch/autograd/grad_mode.py", line 27, in decorate_context
return func(*args, **kwargs)
File "/home/max/.local/lib/python3.8/site-packages/torch/optim/adam.py", line 66, in step
loss = closure()
File "/home/max/.local/lib/python3.8/site-packages/pytorch_lightning/trainer/training_loop.py", line 648, in train_step_and_backward_closure
result = self.training_step_and_backward(
File "/home/max/.local/lib/python3.8/site-packages/pytorch_lightning/trainer/training_loop.py", line 742, in training_step_and_backward
result = self.training_step(split_batch, batch_idx, opt_idx, hiddens)
File "/home/max/.local/lib/python3.8/site-packages/pytorch_lightning/trainer/training_loop.py", line 293, in training_step
training_step_output = self.trainer.accelerator.training_step(args)
File "/home/max/.local/lib/python3.8/site-packages/pytorch_lightning/accelerators/accelerator.py", line 156, in training_step
return self.training_type_plugin.training_step(*args)
File "/home/max/.local/lib/python3.8/site-packages/pytorch_lightning/plugins/training_type/training_type_plugin.py", line 125, in training_step
return self.lightning_module.training_step(*args, **kwargs)
File "main.py", line 318, in training_step
print(type(labels))
File "/home/max/.local/lib/python3.8/site-packages/torch/nn/modules/module.py", line 889, in _call_impl
result = self.forward(*input, **kwargs)
File "/home/max/.local/lib/python3.8/site-packages/torchmetrics/metric.py", line 152, in forward
self.update(*args, **kwargs)
File "/home/max/.local/lib/python3.8/site-packages/torchmetrics/metric.py", line 199, in wrapped_func
return update(*args, **kwargs)
File "/home/max/.local/lib/python3.8/site-packages/torchmetrics/classification/accuracy.py", line 142, in update
self.correct += correct
RuntimeError: Expected all tensors to be on the same device, but found at least two devices, cuda:0 and cpu!
我在这里解释一下，
这个命令：
print(next(model.parameters()).device)
它将打印加载模型参数的设备。
要检查它们是否加载到 GPU 上，您可以这样做：
print(next(model.parameters()).is_cuda)
它将return一个布尔值，
看到你的代码后，正如你提到的那样，打印时 returning "CPU"： 下一个(model.parameters()).device
表示你的模型参数是在CPU上加载的，但是这一行
trainer = pl.Trainer(max_epochs=100, gpus=1, reload_dataloaders_every_epoch=True,
progress_bar_refresh_rate=50, logger=False, checkpoint_callback=True,callbacks=[early_stopping])
这里gpus=1表示会设置要训练的gpus个数， 因为你所有的张量都默认加载 CPU，你得到了那个错误。
设置gpus=None后，不再使用gpus进行训练
在 GPU 上 运行：
您必须将张量从 CPU 移动到 GPU，
例如：
ex_tensor=torch.zeros((7,7))
ex_tensor = ex_tensor.cuda()
还有你的模型参数，
model = model.cuda()