《Keras 3 ：使用 Vision Transformers 进行物体检测》：此文为AI自动翻译

《Keras 3 ：使用 Vision Transformers 进行物体检测》

作者：Karan V. Dave
创建日期：2022 年 3 月 27
日最后修改时间：2023 年 11 月 20
日描述：使用 Vision Transformer 进行对象检测的简单 Keras 实现。

（i） 此示例使用 Keras 3

 在 Colab 中查看 

 GitHub 源

---

介绍

Alexey Dosovitskiy 等人的文章 Vision Transformer （ViT） 架构。 表明直接应用于图像序列的纯 transformer 补丁可以在对象检测任务中表现良好。

在这个 Keras 示例中，我们实现了一个对象检测 ViT 我们在加州理工学院 101 数据集上对其进行训练，以检测给定图像中的飞机。

---

导入和设置

import os

os.environ["KERAS_BACKEND"] = "jax"  # @param ["tensorflow", "jax", "torch"]


import numpy as np
import keras
from keras import layers
from keras import ops
import matplotlib.pyplot as plt
import numpy as np
import cv2
import os
import scipy.io
import shutil

---

准备数据集

我们使用加州理工学院 101 数据集。

# Path to images and annotations
path_images = "./101_ObjectCategories/airplanes/"
path_annot = "./Annotations/Airplanes_Side_2/"

path_to_downloaded_file = keras.utils.get_file(
    fname="caltech_101_zipped",
    origin="https://data.caltech.edu/records/mzrjq-6wc02/files/caltech-101.zip",
    extract=True,
    archive_format="zip",  # downloaded file format
    cache_dir="/",  # cache and extract in current directory
)
download_base_dir = os.path.dirname(path_to_downloaded_file)

# Extracting tar files found inside main zip file
shutil.unpack_archive(
    os.path.join(download_base_dir, "caltech-101", "101_ObjectCategories.tar.gz"), "."
)
shutil.unpack_archive(
    os.path.join(download_base_dir, "caltech-101", "Annotations.tar"), "."
)

# list of paths to images and annotations
image_paths = [
    f for f in os.listdir(path_images) if os.path.isfile(os.path.join(path_images, f))
]
annot_paths = [
    f for f in os.listdir(path_annot) if os.path.isfile(os.path.join(path_annot, f))
]

image_paths.sort()
annot_paths.sort()

image_size = 224  # resize input images to this size

images, targets = [], []

# loop over the annotations and images, preprocess them and store in lists
for i in range(0, len(annot_paths)):
    # Access bounding box coordinates
    annot = scipy.io.loadmat(path_annot + annot_paths[i])["box_coord"][0]

    top_left_x, top_left_y = annot[2], annot[0]
    bottom_right_x, bottom_right_y = annot[3], annot[1]

    image = keras.utils.load_img(
        path_images + image_paths[i],
    )
    (w, h) = image.size[:2]

    # resize images
    image = image.resize((image_size, image_size))

    # convert image to array and append to list
    images.append(keras.utils.img_to_array(image))

    # apply relative scaling to bounding boxes as per given image and append to list
    targets.append(
        (
            float(top_left_x) / w,
            float(top_left_y) / h,
            float(bottom_right_x) / w,
            float(bottom_right_y) / h,
        )
    )

# Convert the list to numpy array, split to train and test dataset
(x_train), (y_train) = (
    np.asarray(images[: int(len(images) * 0.8)]),
    np.asarray(targets[: int(len(targets) * 0.8)]),
)
(x_test), (y_test) = (
    np.asarray(images[int(len(images