torch.load(jii)
时间: 2024-06-15 21:07:41 浏览: 4
torch.load()是PyTorch中的一个函数,用于加载保存的模型或者张量数据。它的语法如下:
torch.load(filepath, map_location=None, pickle_module=<module 'pickle' from '...'>)
其中,参数说明如下:
- filepath:保存模型或张量数据的文件路径。
- map_location:可选参数,用于指定加载模型或张量数据的设备。如果不指定,默认会加载到与保存时相同的设备上。
- pickle_module:可选参数,用于指定pickle模块的位置。如果不指定,默认使用内置的pickle模块。
该函数会返回一个包含加载的模型或张量数据的对象。
相关问题
import torch import os import torch.nn as nn import torch.optim as optim import numpy as np import random class Net(nn.Module): def init(self): super(Net, self).init() self.conv1 = nn.Conv2d(1, 16, kernel_size=3,stride=1) self.pool = nn.MaxPool2d(kernel_size=2,stride=2) self.conv2 = nn.Conv2d(16, 32, kernel_size=3,stride=1) self.fc1 = nn.Linear(32 * 9 * 9, 120) self.fc2 = nn.Linear(120, 84) self.fc3 = nn.Linear(84, 2) def forward(self, x): x = self.pool(nn.functional.relu(self.conv1(x))) x = self.pool(nn.functional.relu(self.conv2(x))) x = x.view(-1, 32 * 9 * 9) x = nn.functional.relu(self.fc1(x)) x = nn.functional.relu(self.fc2(x)) x = self.fc3(x) return x net = Net() criterion = nn.CrossEntropyLoss() optimizer = optim.SGD(net.parameters(), lr=0.001, momentum=0.9) folder_path = 'random_matrices2' # 创建空的tensor x = torch.empty((40, 1, 42, 42)) # 遍历文件夹内的文件,将每个矩阵转化为tensor并存储 for j in range(40): for j in range(40): file_name = 'matrix_{}.npy'.format(j) file_path = os.path.join(folder_path, file_name) matrix = np.load(file_path) x[j] = torch.from_numpy(matrix).unsqueeze(0) #y = torch.cat((torch.zeros(20), torch.ones(20))) #y = torch.cat((torch.zeros(20, dtype=torch.long), torch.ones(20, dtype=torch.long))) y = torch.cat((torch.zeros(20, dtype=torch.long), torch.ones(20, dtype=torch.long)), dim=0) for epoch in range(10): running_loss = 0.0 for i in range(40): inputs = x[i] labels = y[i] optimizer.zero_grad() outputs = net(inputs) #loss = criterion(outputs, labels) loss = criterion(outputs.unsqueeze(0), labels.unsqueeze(0)) loss.backward() optimizer.step() running_loss += loss.item() print('[%d] loss: %.3f' % (epoch + 1, running_loss / 40)) print('Finished Training')报错RuntimeError: Expected target size [1, 2], got [1]怎么修改?
可以将 labels.unsqueeze(0) 修改为 labels.unsqueeze(0).long(),即将标签张量转化为 long 类型。修改后的代码如下:
```
import torch
import os
import torch.nn as nn
import torch.optim as optim
import numpy as np
import random
class Net(nn.Module):
def __init__(self):
super(Net, self).__init__()
self.conv1 = nn.Conv2d(1, 16, kernel_size=3,stride=1)
self.pool = nn.MaxPool2d(kernel_size=2,stride=2)
self.conv2 = nn.Conv2d(16, 32, kernel_size=3,stride=1)
self.fc1 = nn.Linear(32 * 9 * 9, 120)
self.fc2 = nn.Linear(120, 84)
self.fc3 = nn.Linear(84, 2)
def forward(self, x):
x = self.pool(nn.functional.relu(self.conv1(x)))
x = self.pool(nn.functional.relu(self.conv2(x)))
x = x.view(-1, 32 * 9 * 9)
x = nn.functional.relu(self.fc1(x))
x = nn.functional.relu(self.fc2(x))
x = self.fc3(x)
return x
net = Net()
criterion = nn.CrossEntropyLoss()
optimizer = optim.SGD(net.parameters(), lr=0.001, momentum=0.9)
folder_path = 'random_matrices2'
# 创建空的tensor
x = torch.empty((40, 1, 42, 42))
# 遍历文件夹内的文件,将每个矩阵转化为tensor并存储
for j in range(40):
file_name = 'matrix_{}.npy'.format(j)
file_path = os.path.join(folder_path, file_name)
matrix = np.load(file_path)
x[j] = torch.from_numpy(matrix).unsqueeze(0)
y = torch.cat((torch.zeros(20, dtype=torch.long), torch.ones(20, dtype=torch.long)), dim=0)
for epoch in range(10):
running_loss = 0.0
for i in range(40):
inputs = x[i]
labels = y[i]
optimizer.zero_grad()
outputs = net(inputs)
loss = criterion(outputs.unsqueeze(0), labels.unsqueeze(0).long())
loss.backward()
optimizer.step()
running_loss += loss.item()
print('[%d] loss: %.3f' % (epoch + 1, running_loss / 40))
print('Finished Training')
```
这是对单个文件进行预测“import os import json import torch from PIL import Image from torchvision import transforms import matplotlib.pyplot as plt from model import convnext_tiny as create_model def main(): device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu") print(f"using {device} device.") num_classes = 5 img_size = 224 data_transform = transforms.Compose( [transforms.Resize(int(img_size * 1.14)), transforms.CenterCrop(img_size), transforms.ToTensor(), transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])]) # load image img_path = "../tulip.jpg" assert os.path.exists(img_path), "file: '{}' dose not exist.".format(img_path) img = Image.open(img_path) plt.imshow(img) # [N, C, H, W] img = data_transform(img) # expand batch dimension img = torch.unsqueeze(img, dim=0) # read class_indict json_path = './class_indices.json' assert os.path.exists(json_path), "file: '{}' dose not exist.".format(json_path) with open(json_path, "r") as f: class_indict = json.load(f) # create model model = create_model(num_classes=num_classes).to(device) # load model weights model_weight_path = "./weights/best_model.pth" model.load_state_dict(torch.load(model_weight_path, map_location=device)) model.eval() with torch.no_grad(): # predict class output = torch.squeeze(model(img.to(device))).cpu() predict = torch.softmax(output, dim=0) predict_cla = torch.argmax(predict).numpy() print_res = "class: {} prob: {:.3}".format(class_indict[str(predict_cla)], predict[predict_cla].numpy()) plt.title(print_res) for i in range(len(predict)): print("class: {:10} prob: {:.3}".format(class_indict[str(i)], predict[i].numpy())) plt.show() if name == 'main': main()”,改为对指定文件夹下的左右文件进行预测,并绘制混淆矩阵,
好的,为了实现您的需求,您需要进行以下几个步骤:
1. 加载模型和类别标签:
您需要在代码中加载您的模型和类别标签。您可以使用之前的代码中的方式来加载它们,只需要做一些小的改动即可。例如,您需要将模型和类别标签的路径作为参数传递给您的函数。
2. 加载测试集:
您需要加载您的测试集。您可以使用 `torchvision.datasets.ImageFolder` 来加载测试集。这个函数会将每个文件夹中的所有图像文件都加载到一个 tensor 中,并自动为每个文件夹分配一个标签。
3. 进行预测:
您需要对测试集中的每个图像进行预测,并将预测结果与真实标签进行比较。您可以使用之前的代码中的方式来预测每个图像,只需要做一些小的改动即可。例如,您需要将预测结果保存到一个列表中,并将真实标签保存到另一个列表中。
4. 绘制混淆矩阵:
最后,您需要使用预测结果和真实标签来绘制混淆矩阵。您可以使用 `sklearn.metrics.confusion_matrix` 来计算混淆矩阵,并使用 `matplotlib` 来绘制它。
下面是修改后的代码示例:
```
import os
import json
import torch
from PIL import Image
from torchvision import transforms
import matplotlib.pyplot as plt
from sklearn.metrics import confusion_matrix
import numpy as np
from model import convnext_tiny as create_model
def predict_folder(model_path, json_path, folder_path):
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
print(f"using {device} device.")
num_classes = 5
img_size = 224
data_transform = transforms.Compose([
transforms.Resize(int(img_size * 1.14)),
transforms.CenterCrop(img_size),
transforms.ToTensor(),
transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
])
# load class_indict json
with open(json_path, "r") as f:
class_indict = json.load(f)
# create model
model = create_model(num_classes=num_classes).to(device)
# load model weights
model.load_state_dict(torch.load(model_path, map_location=device))
model.eval()
y_true = []
y_pred = []
for root, dirs, files in os.walk(folder_path):
for file in files:
if file.endswith(".jpg") or file.endswith(".jpeg"):
img_path = os.path.join(root, file)
assert os.path.exists(img_path), "file: '{}' dose not exist.".format(img_path)
img = Image.open(img_path)
# [N, C, H, W]
img = data_transform(img)
# expand batch dimension
img = torch.unsqueeze(img, dim=0)
# predict class
with torch.no_grad():
output = torch.squeeze(model(img.to(device))).cpu()
predict = torch.softmax(output, dim=0)
predict_cla = torch.argmax(predict).numpy()
y_true.append(class_indict[os.path.basename(root)])
y_pred.append(predict_cla)
# plot confusion matrix
cm = confusion_matrix(y_true, y_pred)
fig, ax = plt.subplots(figsize=(5, 5))
ax.imshow(cm, cmap=plt.cm.Blues, aspect='equal')
ax.set_xlabel('Predicted label')
ax.set_ylabel('True label')
ax.set_xticks(np.arange(len(class_indict)))
ax.set_yticks(np.arange(len(class_indict)))
ax.set_xticklabels(class_indict.values(), rotation=90)
ax.set_yticklabels(class_indict.values())
ax.tick_params(axis=u'both', which=u'both',length=0)
for i in range(len(class_indict)):
for j in range(len(class_indict)):
text = ax.text(j, i, cm[i, j], ha="center", va="center", color="white" if cm[i, j] > cm.max() / 2. else "black")
fig.tight_layout()
plt.show()
if __name__ == '__main__':
# set the paths for the model, class_indict json, and test data folder
model_path = './weights/best_model.pth'
json_path = './class_indices.json'
folder_path = './test_data'
predict_folder(model_path, json_path, folder_path)
```
请注意,这个函数的参数需要您自己根据您的实际情况进行设置,以匹配模型、类别标签和测试集的路径。
相关推荐
![pdf](https://img-home.csdnimg.cn/images/20210720083512.png)
![pdf](https://img-home.csdnimg.cn/images/20210720083512.png)
![pdf](https://img-home.csdnimg.cn/images/20210720083512.png)
![](https://csdnimg.cn/download_wenku/file_type_ask_c1.png)
![](https://csdnimg.cn/download_wenku/file_type_ask_c1.png)
![](https://csdnimg.cn/download_wenku/file_type_ask_c1.png)
![](https://csdnimg.cn/download_wenku/file_type_ask_c1.png)
![](https://csdnimg.cn/download_wenku/file_type_ask_c1.png)
![](https://csdnimg.cn/download_wenku/file_type_ask_c1.png)
![pdf](https://img-home.csdnimg.cn/images/20210720083512.png)
![pdf](https://img-home.csdnimg.cn/images/20210720083512.png)
![pdf](https://img-home.csdnimg.cn/images/20210720083512.png)
![pdf](https://img-home.csdnimg.cn/images/20210720083512.png)
![xlsx](https://img-home.csdnimg.cn/images/20210720083732.png)
![zip](https://img-home.csdnimg.cn/images/20210720083736.png)