Skorch RuntimeError:输入类型(torch.cuda.ByteTensor)和权重类型(torch.cuda.FloatTensor)应该相同

Question

我在尝试开发一个图像分割模型。在下面的代码中，我一直点击一个RuntimeError:输入类型(torch.cuda.ByteTensor)和权重类型(torch.cuda.FloatTensor)应该是相同的。我不知道为什么，因为我尝试使用UNet ()将数据和.cuda模型加载到GPU (虽然不是skorch模型--不确定如何做到这一点)。我使用一个用于主动学习的库，modAL，它封装了skorch。

from modAL.models import ActiveLearner
import numpy as np
import torch

from torch import nn
from torch import Tensor
from torch.utils.data import DataLoader
from torch.utils.data import Dataset

from skorch.net import NeuralNet

from modAL.models import ActiveLearner
from modAL.uncertainty import classifier_uncertainty, classifier_margin
from modAL.utils.combination import make_linear_combination, make_product
from modAL.utils.selection import multi_argmax
from modAL.uncertainty import uncertainty_sampling

from model import UNet
from skorch.net import NeuralNet
from skorch.helper import predefined_split
from torch.optim import SGD

import cv2


# Map style dataset, 
class ImagesDataset(Dataset):
    """Constructs dataset of satellite images + masks"""
    def __init__(self, image_paths):
        super().__init__()
        self.image_paths = image_paths

    def __len__(self):
        return len(self.image_paths)

    def __getitem__(self, idx):  
        if torch.is_tensor(idx):
            idx = idx.tolist()
        print("idx:", idx)
        sample_dir = self.image_paths[idx]
        img_path = sample_dir +"/images/"+ Path(sample_dir).name +'.png'
        mask_path = sample_dir +'/mask.png'
        img, mask = cv2.imread(img_path), cv2.imread(mask_path)
        print("shape of img", img.shape)
        return img, mask

# turn data into dataset
train_ds = ImagesDataset(train_dirs)
val_ds = ImagesDataset(valid_dirs)

train_loader = torch.utils.data.DataLoader(train_ds, batch_size=3, shuffle=True, pin_memory=True)
val_loader = torch.utils.data.DataLoader(val_ds, batch_size=1, shuffle=True, pin_memory=True)

# make sure data loaded in cuda for train, validation
for i, (tr, val) in enumerate(train_loader):
    tr, val = tr.cuda(), val.cuda()

for i, (tr2, val2) in enumerate(val_loader):
    tr2, val2 = tr2.cuda(), val2.cuda()

X, y = next(iter(train_loader))
X_train = np.array(X.reshape(3,3,1024,1024))
y_train = np.array(y.reshape(3,3,1024,1024))

X2, y2 = next(iter(val_loader))
X_test = np.array(X2.reshape(1,3,1024,1024))
y_test = np.array(y2.reshape(1,3,1024,1024))


module = UNet(pretrained=True)
if torch.cuda.is_available():
    module = module.cuda()
    
# create the classifier

net = NeuralNet(
    module,
    criterion=torch.nn.NLLLoss,
    batch_size=32,
    max_epochs=20,
    optimizer=SGD,
    optimizer__momentum=0.9,
    iterator_train__shuffle=True,
    iterator_train__num_workers=4,
    iterator_valid__shuffle=False,
    iterator_valid__num_workers=4,
    train_split=predefined_split(val_ds),
    device='cuda',
)

# assemble initial data
n_initial = 1
initial_idx = np.random.choice(range(len(X_train)), size=n_initial, replace=False)
X_initial = X_train[initial_idx]
y_initial = y_train[initial_idx]

# generate the pool, remove the initial data from the training dataset
X_pool = np.delete(X_train, initial_idx, axis=0)
y_pool = np.delete(y_train, initial_idx, axis=0)

# train the activelearner
# shape of 4D matrix is 'batch', 'channel', 'width', 'height')
learner = ActiveLearner(
    estimator= net,
    X_training=X_initial, y_training=y_initial,
)

完整的错误跟踪是：

    ---------------------------------------------------------------------------
RuntimeError                              Traceback (most recent call last)
<ipython-input-83-0af6007b6b72> in <module>
      8 learner = ActiveLearner(
      9     estimator= net,
---> 10     X_training=X_initial, y_training=y_initial,
     11     # X_training=X_initial, y_training=y_initial,
     12 )

~/.local/lib/python3.7/site-packages/modAL/models/learners.py in __init__(self, estimator, query_strategy, X_training, y_training, bootstrap_init, on_transformed, **fit_kwargs)
     80                  ) -> None:
     81         super().__init__(estimator, query_strategy,
---> 82                          X_training, y_training, bootstrap_init, on_transformed, **fit_kwargs)
     83 
     84     def teach(self, X: modALinput, y: modALinput, bootstrap: bool = False, only_new: bool = False, **fit_kwargs) -> None:

~/.local/lib/python3.7/site-packages/modAL/models/base.py in __init__(self, estimator, query_strategy, X_training, y_training, bootstrap_init, on_transformed, force_all_finite, **fit_kwargs)
     70         self.y_training = y_training
     71         if X_training is not None:
---> 72             self._fit_to_known(bootstrap=bootstrap_init, **fit_kwargs)
     73             self.Xt_training = self.transform_without_estimating(self.X_training) if self.on_transformed else None
     74 

~/.local/lib/python3.7/site-packages/modAL/models/base.py in _fit_to_known(self, bootstrap, **fit_kwargs)
    160         """
    161         if not bootstrap:
--> 162             self.estimator.fit(self.X_training, self.y_training, **fit_kwargs)
    163         else:
    164             n_instances = self.X_training.shape[0]

~/.local/lib/python3.7/site-packages/skorch/net.py in fit(self, X, y, **fit_params)
    901             self.initialize()
    902 
--> 903         self.partial_fit(X, y, **fit_params)
    904         return self
    905 

~/.local/lib/python3.7/site-packages/skorch/net.py in partial_fit(self, X, y, classes, **fit_params)
    860         self.notify('on_train_begin', X=X, y=y)
    861         try:
--> 862             self.fit_loop(X, y, **fit_params)
    863         except KeyboardInterrupt:
    864             pass

~/.local/lib/python3.7/site-packages/skorch/net.py in fit_loop(self, X, y, epochs, **fit_params)
    774 
    775             self.run_single_epoch(dataset_train, training=True, prefix="train",
--> 776                                   step_fn=self.train_step, **fit_params)
    777 
    778             if dataset_valid is not None:

~/.local/lib/python3.7/site-packages/skorch/net.py in run_single_epoch(self, dataset, training, prefix, step_fn, **fit_params)
    810             yi_res = yi if not is_placeholder_y else None
    811             self.notify("on_batch_begin", X=Xi, y=yi_res, training=training)
--> 812             step = step_fn(Xi, yi, **fit_params)
    813             self.history.record_batch(prefix + "_loss", step["loss"].item())
    814             self.history.record_batch(prefix + "_batch_size", get_len(Xi))

~/.local/lib/python3.7/site-packages/skorch/net.py in train_step(self, Xi, yi, **fit_params)
    707             return step['loss']
    708 
--> 709         self.optimizer_.step(step_fn)
    710         return step_accumulator.get_step()
    711 

~/.local/lib/python3.7/site-packages/torch/autograd/grad_mode.py in decorate_context(*args, **kwargs)
     24         def decorate_context(*args, **kwargs):
     25             with self.__class__():
---> 26                 return func(*args, **kwargs)
     27         return cast(F, decorate_context)
     28 

~/.local/lib/python3.7/site-packages/torch/optim/sgd.py in step(self, closure)
     84         if closure is not None:
     85             with torch.enable_grad():
---> 86                 loss = closure()
     87 
     88         for group in self.param_groups:

~/.local/lib/python3.7/site-packages/skorch/net.py in step_fn()
    703         def step_fn():
    704             self.optimizer_.zero_grad()
--> 705             step = self.train_step_single(Xi, yi, **fit_params)
    706             step_accumulator.store_step(step)
    707             return step['loss']

~/.local/lib/python3.7/site-packages/skorch/net.py in train_step_single(self, Xi, yi, **fit_params)
    643         """
    644         self.module_.train()
--> 645         y_pred = self.infer(Xi, **fit_params)
    646         loss = self.get_loss(y_pred, yi, X=Xi, training=True)
    647         loss.backward()

~/.local/lib/python3.7/site-packages/skorch/net.py in infer(self, x, **fit_params)
   1046             x_dict = self._merge_x_and_fit_params(x, fit_params)
   1047             return self.module_(**x_dict)
-> 1048         return self.module_(x, **fit_params)
   1049 
   1050     def _get_predict_nonlinearity(self):

~/.local/lib/python3.7/site-packages/torch/nn/modules/module.py in _call_impl(self, *input, **kwargs)
    725             result = self._slow_forward(*input, **kwargs)
    726         else:
--> 727             result = self.forward(*input, **kwargs)
    728         for hook in itertools.chain(
    729                 _global_forward_hooks.values(),

~/al/model.py in forward(self, x)
     51 
     52     def forward(self, x):
---> 53         conv1 = self.conv1(x)
     54         conv2 = self.conv2(conv1)
     55         conv3 = self.conv3(conv2)

~/.local/lib/python3.7/site-packages/torch/nn/modules/module.py in _call_impl(self, *input, **kwargs)
    725             result = self._slow_forward(*input, **kwargs)
    726         else:
--> 727             result = self.forward(*input, **kwargs)
    728         for hook in itertools.chain(
    729                 _global_forward_hooks.values(),

~/.local/lib/python3.7/site-packages/torch/nn/modules/container.py in forward(self, input)
    115     def forward(self, input):
    116         for module in self:
--> 117             input = module(input)
    118         return input
    119 

~/.local/lib/python3.7/site-packages/torch/nn/modules/module.py in _call_impl(self, *input, **kwargs)
    725             result = self._slow_forward(*input, **kwargs)
    726         else:
--> 727             result = self.forward(*input, **kwargs)
    728         for hook in itertools.chain(
    729                 _global_forward_hooks.values(),

~/.local/lib/python3.7/site-packages/torch/nn/modules/conv.py in forward(self, input)
    421 
    422     def forward(self, input: Tensor) -> Tensor:
--> 423         return self._conv_forward(input, self.weight)
    424 
    425 class Conv3d(_ConvNd):

~/.local/lib/python3.7/site-packages/torch/nn/modules/conv.py in _conv_forward(self, input, weight)
    418                             _pair(0), self.dilation, self.groups)
    419         return F.conv2d(input, weight, self.bias, self.stride,
--> 420                         self.padding, self.dilation, self.groups)
    421 
    422     def forward(self, input: Tensor) -> Tensor:

RuntimeError: Input type (torch.cuda.ByteTensor) and weight type (torch.cuda.FloatTensor) should be the same

如果有人能帮忙的话，我会非常感激的！尽管我搜索遍了所有的UNet模型，但我还是被困住了--把我的.cuda模型抛到浮子上没有什么帮助，我想我已经打电话给了.cuda()，我应该在这里这样做。

我试过的一些具体的事情：

• RuntimeError:输入类型(torch.FloatTensor)和权重类型(torch.cuda.FloatTensor)应该相同将DataLoader的条目加载到CUDA
• 将pin_memory添加到我的DataLoader
• 如这里所述，将我的skorch NeuralNetwork加载到CUDA (因为它不是skorch中的一个函数而无法工作)
• 将数据转换为浮动(https://discuss.pytorch.org/t/input-type-torch-cuda-doubletensor-and-weight-type-torch-cuda-floattensor-should-be-the-same/22704)

Answer 1

cv2.imread为您提供np.uint8数据类型，它将被转换为PyTorch的字节。字节类型不能与浮动类型一起使用(这很可能是您的模型使用的)。

您需要通过修改数据集将字节类型转换为浮动类型(并转换为张量类型)

import torchvision.transforms as transforms
class ImagesDataset(Dataset):
    """Constructs dataset of satellite images + masks"""
    def __init__(self, image_paths):
        super().__init__()
        self.image_paths = image_paths
        self.transform = transforms.Compose([transforms.ToTensor()])

    def __len__(self):
        return len(self.image_paths)

    def __getitem__(self, idx):  
        if torch.is_tensor(idx):
            idx = idx.tolist()
        print("idx:", idx)
        sample_dir = self.image_paths[idx]
        img_path = sample_dir +"/images/"+ Path(sample_dir).name +'.png'
        mask_path = sample_dir +'/mask.png'
        img, mask = cv2.imread(img_path), cv2.imread(mask_path)
        img = self.transform(img)
        mask = self.transform(mask)
        print("shape of img", img.shape)
        return img, mask