之前第二三篇有更新过单点，多点，单框。本篇加上多框输入。

先确定一下目录

新建test_boxes.py文件，复制以下代码

import sys
import torch
import numpy as np
from datetime import datetime
import matplotlib.pyplot as plt
from Net.segment_anything import SamPredictor,sam_model_registry
import cv2image = cv2.imread('1.jpg')  # 读取的图像以NumPy数组的形式存储在变量image中
image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)  # 将图像从BGR颜色空间转换为RGB颜色空间，还原图片色彩（图像处理库所认同的格式）model_type = "vit_b"  # 定义模型类型
device = "cuda"  # "cpu"  or  "cuda"
sam = sam_model_registry[model_type](checkpoint='sam_vit_b_01ec64.pth')
sam.to(device=device)  # 定义模型参数
predictor = SamPredictor(sam)  # 调用预测模型predictor.set_image(image)def show_mask(mask, ax, random_color=False):if random_color:color = np.concatenate([np.random.random(3), np.array([0.6])], axis=0)else:color = np.array([30 / 255, 144 / 255, 255 / 255, 0.6])h, w = mask.shape[-2:]mask_image = mask.reshape(h, w, 1) * color.reshape(1, 1, -1)ax.imshow(mask_image)def show_points(coords, labels, ax, marker_size=375):pos_points = coords[labels == 1]neg_points = coords[labels == 0]ax.scatter(pos_points[:, 0], pos_points[:, 1], color='green', marker='*', s=marker_size, edgecolor='white',linewidth=1.25)ax.scatter(neg_points[:, 0], neg_points[:, 1], color='red', marker='*', s=marker_size, edgecolor='white',linewidth=1.25)def show_box(box, ax):x0, y0 = box[0], box[1]w, h = box[2] - box[0], box[3] - box[1]ax.add_patch(plt.Rectangle((x0, y0), w, h, edgecolor='green', facecolor=(0, 0, 0, 0), lw=2))# 多框
# input_boxes = torch.tensor([
#     [75, 275, 1725, 850],
#     [425, 600, 700, 875],
#     [1375, 550, 1650, 800],
#     [1240, 675, 1400, 750],
# ], device=predictor.device)  # 假设为目标检测的预测结果# 单框
input_boxes = torch.tensor([[75, 275, 1725, 850]
], device=predictor.device)  # 假设为目标检测的预测结果
input_boxes = input_boxes / 2
transformed_boxes = predictor.transform.apply_boxes_torch(input_boxes, image.shape[:2])
masks, _, _ = predictor.predict_torch(point_coords=None,point_labels=None,boxes=transformed_boxes,multimask_output=False,
)plt.figure(figsize=(10, 10))
plt.imshow(image)
for mask in masks:show_mask(mask.cpu().numpy(), plt.gca(), random_color=True)
for box in input_boxes:show_box(box.cpu().numpy(), plt.gca())
plt.axis('off')
plt.show()

打断点

在如下位置打断点，debug运行，观察单框和多框传入有什么维度不同，自己训练的时候按照对应维度组装。