def load_img(img_path): out_np = np.asarray(Image.open(img_path)) if(out_np.ndim==2): out_np = np.tile(out_np[:,:,None],3) return out_np def resize_img(img, HW=(256,256), resample=3): return np.asarray(Image.fromarray(img).resize((HW[1],HW[0]), resample=resample))
时间: 2024-02-01 16:12:11 浏览: 145
这段代码实现了两个函数,一个是`load_img`,一个是`resize_img`。`load_img`函数用于读取图片,并将其转换为numpy数组;如果图片是灰度图像,则将其转换为RGB三通道图像。`resize_img`函数用于将图片按照指定的尺寸进行缩放。其中,`HW`参数指定了目标尺寸,`resample`参数指定了缩放方法。`resize_img`函数也将图片转换为numpy数组并返回。
相关问题
def unzip_infer_data(src_path,target_path): ''' 解压预测数据集 ''' if(not os.path.isdir(target_path)): z = zipfile.ZipFile(src_path, 'r') z.extractall(path=target_path) z.close() def load_image(img_path): ''' 预测图片预处理 ''' img = Image.open(img_path) if img.mode != 'RGB': img = img.convert('RGB') img = img.resize((224, 224), Image.BILINEAR) img = np.array(img).astype('float32') img = img.transpose((2, 0, 1)) # HWC to CHW img = img/255 # 像素值归一化 return img infer_src_path = './archive_test.zip' infer_dst_path = './archive_test' unzip_infer_data(infer_src_path,infer_dst_path) para_state_dict = paddle.load("MyDNN") model = MyDNN() model.set_state_dict(para_state_dict) #加载模型参数 model.eval() #验证模式 #展示预测图片 infer_path='./archive_test/alexandrite_18.jpg' img = Image.open(infer_path) plt.imshow(img) #根据数组绘制图像 plt.show() #显示图像 #对预测图片进行预处理 infer_imgs = [] infer_imgs.append(load_image(infer_path)) infer_imgs = np.array(infer_imgs) label_dic = train_parameters['label_dict'] for i in range(len(infer_imgs)): data = infer_imgs[i] dy_x_data = np.array(data).astype('float32') dy_x_data=dy_x_data[np.newaxis,:, : ,:] img = paddle.to_tensor (dy_x_data) out = model(img) lab = np.argmax(out.numpy()) #argmax():返回最大数的索引 print("第{}个样本,被预测为:{},真实标签为:{}".format(i+1,label_dic[str(lab)],infer_path.split('/')[-1].split("_")[0])) print("结束")根据这一段代码续写一段利用这个模型进行宝石预测的GUI界面
好的,根据这段代码,我可以为您提供一个基于tkinter库的简单GUI界面,您可以在其中选择待预测的图片,并得到预测结果。以下是续写的代码:
```python
import tkinter as tk
from tkinter import filedialog
from PIL import ImageTk, Image
# 创建窗口
window = tk.Tk()
window.title("宝石预测")
window.geometry("400x400")
# 加载模型参数
para_state_dict = paddle.load("MyDNN")
model = MyDNN()
model.set_state_dict(para_state_dict)
model.eval()
# 加载标签字典
label_dict = train_parameters['label_dict']
# 创建预测函数
def predict():
# 获取待预测图片路径
img_path = filedialog.askopenfilename()
img = Image.open(img_path)
# 预处理图片
img = img.resize((224, 224), Image.BILINEAR)
img = np.array(img).astype('float32')
img = img.transpose((2, 0, 1))
img = img / 255
img = np.array([img])
# 进行预测
img = paddle.to_tensor(img)
out = model(img)
label = np.argmax(out.numpy())
result = label_dict[str(label)]
# 显示预测结果
result_label.config(text="预测结果:{}".format(result))
# 显示待预测图片
img = ImageTk.PhotoImage(Image.open(img_path).resize((200, 200)))
img_label.config(image=img)
img_label.image = img
# 创建选择图片按钮
select_button = tk.Button(window, text="选择图片", command=predict)
select_button.pack(pady=20)
# 创建待预测图片区域
img_label = tk.Label(window)
img_label.pack()
# 创建预测结果区域
result_label = tk.Label(window, font=("Helvetica", 16))
result_label.pack(pady=20)
# 进入消息循环
window.mainloop()
```
您可以将这段代码保存为.py文件并运行,即可启动GUI界面。界面中有一个“选择图片”按钮,您可以点击该按钮选择待预测的图片,程序将会自动对该图片进行预测,并在界面上显示预测结果和待预测图片。
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,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。
阅读全文