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
时间: 2024-03-23 15:38:17 浏览: 63
好的,你的问题是如何将上述代码修改为对指定文件夹下的所有文件进行预测,并绘制混淆矩阵。
要实现这个功能,你需要进行以下几个步骤:
1. 导入必要的包:
```python
import os
import json
import torch
from PIL import Image
from torchvision import transforms
from sklearn.metrics import confusion_matrix
import matplotlib.pyplot as plt
import numpy as np
from model import convnext_tiny as create_model
```
2. 定义函数 `predict_folder`,用于对指定文件夹下的所有文件进行预测:
```python
def predict_folder(folder_path, model_weight_path, json_path, img_size, num_classes, device):
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])
])
# read class_indict
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_weight_path, map_location=device))
model.eval()
y_true = []
y_pred = []
for root, dirs, files in os.walk(folder_path):
for file in files:
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)
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()
y_true.append(class_indict[os.path.basename(root)])
y_pred.append(predict_cla)
return y_true, y_pred
```
这个函数接受五个参数:
- `folder_path`:要预测的文件夹路径。
- `model_weight_path`:模型权重文件路径。
- `json_path`:类别标签文件路径。
- `img_size`:输入图片的大小。
- `num_classes`:分类器的类别数。
- `device`:设备类型。
函数会返回两个列表 `y_true` 和 `y_pred`,分别代表真实标签和预测标签。
3. 加载类别标签:
```python
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)
```
4. 调用 `predict_folder` 函数进行预测:
```python
folder_path = './test'
assert os.path.exists(folder_path), "folder: '{}' dose not exist.".format(folder_path)
y_true, y_pred = predict_folder(folder_path, "./weights/best_model.pth", json_path, 224, 5, device)
```
这里假设要预测的文件夹路径为 `./test`,模型权重文件路径为 `./weights/best_model.pth`,输入图片大小为 224,分类器的类别数为 5。
5. 绘制混淆矩阵:
```python
cm = confusion_matrix(y_true, y_pred)
fig, ax = plt.subplots()
im = ax.imshow(cm, interpolation='nearest', cmap=plt.cm.Blues)
ax.figure.colorbar(im, ax=ax)
ax.set(xticks=np.arange(cm.shape[1]),
yticks=np.arange(cm.shape[0]),
xticklabels=list(class_indict.values()), yticklabels=list(class_indict.values()),
title='Confusion matrix',
ylabel='True label',
xlabel='Predicted label')
plt.setp(ax.get_xticklabels(), rotation=45, ha="right",
rotation_mode="anchor")
fmt = 'd'
thresh = cm.max() / 2.
for i in range(cm.shape[0]):
for j in range(cm.shape[1]):
ax.text(j, i, format(cm[i, j], fmt),
ha="center", va="center",
color="white" if cm[i, j] > thresh else "black")
fig.tight_layout()
plt.show()
```
这里使用了 `sklearn.metrics` 中的 `confusion_matrix` 函数进行混淆矩阵的计算。然后使用 `matplotlib` 绘制混淆矩阵图像。