《Keras 3 ：使用 Vision Transformers 進行物體檢測》
作者：Karan V. Dave
創建日期：2022 年 3 月 27
日最后修改時間：2023 年 11 月 20
日描述：使用 Vision Transformer 進行對象檢測的簡單 Keras 實現。
（i） 此示例使用 Keras 3
在 Colab 中查看
GitHub 源
介紹
Alexey Dosovitskiy 等人的文章 Vision Transformer （ViT） 架構。 表明直接應用于圖像序列的純 transformer 補丁可以在對象檢測任務中表現良好。
在這個 Keras 示例中，我們實現了一個對象檢測 ViT 我們在加州理工學院 101 數據集上對其進行訓練，以檢測給定圖像中的飛機。
導入和設置
import osos.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
準備數據集
我們使用加州理工學院 101 數據集。
# 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 formatcache_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 sizeimages, targets = [], []# loop over the annotations and images, preprocess them and store in lists
for i in range(0, len(annot_paths)):# Access bounding box coordinatesannot = 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 imagesimage = image.resize((image_size, image_size))# convert image to array and append to listimages.append(keras.utils.img_to_array(image))# apply relative scaling to bounding boxes as per given image and append to listtargets.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
)
![[MDM 2024]Spatial-Temporal Large Language Model for Traffic Prediction](http://pic.xiahunao.cn/[MDM 2024]Spatial-Temporal Large Language Model for Traffic Prediction)
