pybaseutils 2.0.4__tar.gz → 2.0.5__tar.gz

{pybaseutils-2.0.4 → pybaseutils-2.0.5}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: pybaseutils
-Version: 2.0.4
+Version: 2.0.5
 Summary: pybaseutils
 Home-page: https://github.com/PanJinquan/base-utils
 Author: PanJinquan

{pybaseutils-2.0.4 → pybaseutils-2.0.5}/pybaseutils/__init__.py

@@ -5,4 +5,4 @@
     @Date   : 2019-05-07 17:40:27
 """
 
-__version__ = '2.0.4'
+__version__ = '2.0.5'

{pybaseutils-2.0.4 → pybaseutils-2.0.5}/pybaseutils/converter/convert_cvat2labelme.py

@@ -38,14 +38,15 @@ def parser_annotations(xml_file):
     return filename, annos, width, height
 
 
-def convert_cvat2labelme(anno_dir, image_dir="", thickness=1, fontScale=1.0, vis=False):
+def convert_cvat2labelme(anno_dir, image_dir="", out_dir="", thickness=1, fontScale=1.0, vis=False):
     """
     将CVAT标注格式(LabelMe 3.0)转换labelme通用格式
-    :param anno_dir: 标注文件目录，输出json文件与anno_dir同目录
+    :param anno_dir: 标注文件目录，默认输出json文件与anno_dir同目录
     :param image_dir: 图片文件目录
     :param vis:
     :return:
     """
+    if not out_dir: out_dir = os.path.join(os.path.dirname(anno_dir), "json")
     xml_list = file_utils.get_files_lists(anno_dir, postfix=["*.xml"])
     for xml_file in tqdm(xml_list):
         image_name, annos, w, h = parser_annotations(xml_file)
@@ -56,13 +57,15 @@ def convert_cvat2labelme(anno_dir, image_dir="", thickness=1, fontScale=1.0, vis
             continue
         if image_dir or vis:
             image_file = os.path.join(image_dir, image_name)
+            print(image_file, "labels:{}".format(labels))
             image = cv2.imread(image_file)
             h, w = image.shape[:2]
             if vis:
-                image = image_utils.draw_image_contours(image, points, texts=labels, thickness=thickness, fontScale=fontScale)
+                image = image_utils.draw_image_contours(image, points, texts=labels, thickness=thickness,
+                                                        fontScale=fontScale)
                 image_utils.cv_show_image("det", image)
         image_id = image_name.split(".")[0]
-        json_file = os.path.join(anno_dir, f"{image_id}.json")
+        json_file = os.path.join(out_dir, f"{image_id}.json")
         build_labelme.maker_labelme(json_file, points, labels, image_name, image_size=[w, h], image_bs64=None)
 
 

{pybaseutils-2.0.4 → pybaseutils-2.0.5}/pybaseutils/converter/convert_voc2yolo.py

@@ -80,7 +80,7 @@ def convert_voc2yolo_file(filename, out_text_dir, out_image_dir=None, class_name
             format = "jpg"
         newname = "{}.{}".format(image_id, format)
         text_path = file_utils.create_dir(out_text_dir, None, "{}.txt".format(image_id))
-        labels = np.asarray(labels).astype(np.int).reshape(-1)
+        labels = np.asarray(labels).astype(np.int32).reshape(-1)
         contents = create_yolo_dets(bboxes, labels, width=w, height=h)
         file_utils.write_data(text_path, contents)
         if out_image_dir:
@@ -131,7 +131,7 @@ def convert_voc2yolo(data_root, out_text_dir, out_image_dir=None, class_name=Non
             format = "jpg"
         newname = "{}.{}".format(image_id, format)
         text_path = file_utils.create_dir(out_text_dir, None, "{}.txt".format(image_id))
-        labels = np.asarray(labels).astype(np.int).reshape(-1)
+        labels = np.asarray(labels).astype(np.int32).reshape(-1)
         contents = create_yolo_dets(bboxes, labels, width=w, height=h)
         file_utils.write_data(text_path, contents, split=" ")
         if out_image_dir:
@@ -183,7 +183,7 @@ def convert_voc2yolo_segment(data_root, out_text_dir, out_image_dir=None, class_
             format = "jpg"
         newname = "{}.{}".format(image_id, format)
         text_path = file_utils.create_dir(out_text_dir, None, "{}.txt".format(image_id))
-        labels = np.asarray(labels).astype(np.int).reshape(-1)
+        labels = np.asarray(labels).astype(np.int32).reshape(-1)
         contents = create_yolo_segs(bboxes, labels, width=w, height=h)
         file_utils.write_data(text_path, contents, split=" ")
         if out_image_dir:

{pybaseutils-2.0.4 → pybaseutils-2.0.5}/pybaseutils/converter/convert_yolo2voc.py

@@ -50,7 +50,7 @@ def convert_yolo2voc(filename, out_xml_dir=None, out_image_dir=None, class_name=
             format = "jpg"
         newname = "{}.{}".format(image_id, format)
         xml_path = file_utils.create_dir(out_xml_dir, None, "{}.xml".format(image_id))
-        labels = np.asarray(labels).astype(np.int).reshape(-1)
+        labels = np.asarray(labels).astype(np.int32).reshape(-1)
         objects = build_voc.create_objects(bboxes, labels, keypoints=None, class_name=class_name)
         build_voc.write_voc_xml_objects(newname, image_shape, objects, xml_path)
         if out_image_dir:

{pybaseutils-2.0.4 → pybaseutils-2.0.5}/pybaseutils/image_utils.py

@@ -2482,6 +2482,29 @@ def draw_mask_contours(contours: List[np.ndarray], size, value=255):
     return mask
 
 
+def contours_interpolation(contours, n=1000):
+    """
+    对图像轮廓或者对直线进行线性差值，来源于ultralytics/utils/ops.py
+    轮廓插值，线性插值，直线插值
+    Inputs a list of contours (n,2) and returns a list of contours (n,2) up-sampled to n points each.
+
+    Args:
+        contours (list): a list of (n,2) arrays, where n is the number of points in the segment.
+        n (int): number of points to resample the segment to. Defaults to 1000
+
+    Returns:
+        contours (list): the resampled contours.
+    """
+    for i, s in enumerate(contours):
+        s = np.concatenate((s, s[0:1, :]), axis=0)
+        x = np.linspace(0, len(s) - 1, n)
+        xp = np.arange(len(s))
+        contours[i] = (
+            np.concatenate([np.interp(x, xp, s[:, i]) for i in range(2)], dtype=np.float32).reshape(2, -1).T
+        )  # segment xy
+    return contours
+
+
 def get_mask_boundrect_cv(mask, binarize=False, shift=0):
     """
     获得mask的最大外接矩形框(其速度比get_mask_boundrect快2倍左右)

{pybaseutils-2.0.4 → pybaseutils-2.0.5}/pybaseutils/metrics/plot_roc.py

@@ -39,9 +39,9 @@ def plot_roc_curve(true_labels, pred_scores, vis=True):
     # 绘制ROC曲线
     if vis:
         plt_roc_curve([fpr], [tpr], [roc_auc], names=[""])
-        print("FPR           :{}".format(fpr))
-        print("TPR           :{}".format(tpr))
-        print("Threshold     :{}".format(threshold))
+        # print("FPR           :{}".format(fpr))
+        # print("TPR           :{}".format(tpr))
+        # print("Threshold     :{}".format(threshold))
         print("AUC(ROC)      :{}".format(roc_auc))
         print("best_threshold:{} ".format(threshold[optimal_index]))
     return fpr, tpr, roc_auc, threshold, optimal_index
@@ -134,8 +134,60 @@ def custom_roc_curve(y_true, y_score):
     plt.show()
 
 
+def get_best_accuracy(true_labels, pred_scores, threshold=(0, 1.0, 0.05), vis=False):
+    """
+    计算最佳准确率和阈值
+    :param true_labels:
+    :param pred_scores:
+    :param vis:
+    :return: best_acc, best_th
+    """
+    true_labels, pred_scores = np.asarray(true_labels), np.asarray(pred_scores)
+    threshold = np.arange(threshold[0], threshold[1], threshold[2])
+    acc_list = []
+    for th in threshold:
+        pred_labels = np.asarray(pred_scores > th, dtype=np.int32)
+        acc = metrics.accuracy_score(y_true=true_labels, y_pred=pred_labels)
+        acc_list.append(acc)
+    index = np.argmax(acc_list)
+    best_th = threshold[index]
+    best_acc = acc_list[index]
+    if vis:
+        print("best threshold           :{}".format(best_th))
+        print("best Accuracy            :{}".format(best_acc))
+        plt_curve(X=threshold, Y=acc_list, xtitle="threshold", ytitle="Accuracy", title="", grid=True)
+    return best_acc, best_th
+
+
+def plt_curve(X, Y, xtitle="", ytitle="", title="", grid=True):
+    """
+    绘制PR-threshold曲线
+    :param X: Precision
+    :param recall: Recall
+    :param Y
+    :param title:曲线名称
+    :return:
+    """
+    lw = 2
+    plt.figure(figsize=(10, 10))
+    colors = ["b", "r", "c", "m", "g", "y", "k", "w"]
+    plt.plot(X, Y, color=colors[0], lw=lw, label=ytitle)
+    plt.xlim([0.0, 1.05])
+    plt.ylim([0.0, 1.05])
+    # 设置横纵坐标的名称以及对应字体格式
+    font = {'weight': 'normal', 'size': 20}
+    plt.xlabel(xtitle, font)
+    plt.ylabel('', font)
+    plt.title(title, font)
+    plt.legend(loc="lower right")  # "upper right"
+    # plt.legend(loc="upper right")#"upper right"
+    plt.grid(grid)  # 显示网格;
+    plt.show()
+
+
 if __name__ == "__main__":
     true_labels = [0, 0, 0, 0, 0, 1, 1, 1, 1, 1]  # 真实类别
-    pred_scores = [0.1, 0.2, 0.7, 0.3, 0.4, 0.5, 0.2, 0.7, 0.8, 0.9]  # 预测类别分数
+    pred_scores = [0.1, 0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8, 0.9]  # 预测类别分数
     # pred_scores = [0.11, 0.21, 0.71, 0.31, 0.41, 0.51, 0.21, 0.71, 0.81, 0.91]  # 预测类别分数
-    plot_roc_curve(true_labels, pred_scores)
+    # plot_roc_curve(true_labels, pred_scores)
+    print(get_best_accuracy(true_labels, pred_scores, vis=True))

{pybaseutils-2.0.4 → pybaseutils-2.0.5}/pybaseutils.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: pybaseutils
-Version: 2.0.4
+Version: 2.0.5
 Summary: pybaseutils
 Home-page: https://github.com/PanJinquan/base-utils
 Author: PanJinquan

{pybaseutils-2.0.4 → pybaseutils-2.0.5}/pybaseutils.egg-info/SOURCES.txt

@@ -155,6 +155,7 @@ test_py/WebCrawler/__init__.py
 test_py/WebCrawler/search_image.py
 test_py/WebCrawler/search_image_for_baidu.py
 test_py/aije/__init__.py
+test_py/aije/action_dataset.py
 test_py/aije/build_cython.py
 test_py/aije/build_pyarmor.py
 test_py/aije/build_service.py
@@ -165,7 +166,7 @@ test_py/aije/demo_labelme_crop.py
 test_py/aije/demo_video_aije.py
 test_py/aije/demo_voc_crop.py
 test_py/aije/demo_voc_vis.py
-test_py/aije/video_demo.py
+test_py/aije/video_convertor.py
 test_py/audio/__init__.py
 test_py/audio/demo.py
 test_py/audio/main.py
@@ -198,6 +199,7 @@ test_py/converter/convert_labelme2voc.py
 test_py/converter/convert_voc2labelme.py
 test_py/converter/fatigue_driving.py
 test_py/converter/fdd_dataset.py
+test_py/converter/get_pair_data.py
 test_py/converter/handpose2coco.py
 test_py/converter/insects_for_aichallenger.py
 test_py/converter/tt100k_utils.py

pybaseutils-2.0.5/test_py/aije/action_dataset.py

@@ -0,0 +1,86 @@
+# -*-coding: utf-8 -*-
+"""
+    @Author : PKing
+    @E-mail : 390737991@qq.com
+    @Date   : 2022-11-29 18:11:47
+    @Brief  :
+"""
+import os
+import cv2
+from tqdm import tqdm
+from pybaseutils.dataloader import parser_labelme
+from pybaseutils import image_utils, file_utils
+
+
+def save_object_crops(data_info, out_dir, class_name=None, scale=[], square=False,
+                      padding=False, min_size=20 * 20 * 3, flag="", vis=False):
+    """
+    对VOC的数据目标进行裁剪
+    :param image:
+    :param out_dir:
+    :param bboxes:
+    :param labels:
+    :param image_id:
+    :param class_name:
+    :param scale:
+    :param square:
+    :param padding:
+    :param flag:
+    :param vis:
+    :return:
+    """
+    image, points, boxes, labels = data_info["image"], data_info["points"], data_info["boxes"], data_info["labels"]
+    if len(boxes) == 0: return
+    image_file = data_info["image_file"]
+    h, w = image.shape[:2]
+    image_id = os.path.basename(image_file).split(".")[0]
+    if square:
+        boxes = image_utils.get_square_boxes(boxes, use_max=True, baseline=-1)
+    if scale:
+        boxes = image_utils.extend_xyxy(boxes, scale=scale)
+    if padding:
+        crops = image_utils.get_bboxes_crop_padding(image, boxes)
+    else:
+        crops = image_utils.get_bboxes_crop(image, boxes)
+    if vis:
+        m = image_utils.draw_image_bboxes_labels(image.copy(), boxes, labels, class_name=class_name,
+                                                 thickness=2, fontScale=0.8, drawType="chinese")
+        image_utils.cv_show_image("image", m, use_rgb=False, delay=0)
+    for i, img in enumerate(crops):
+        if img.size < min_size: continue
+        name = class_name[int(labels[i])] if class_name else labels[i]
+        if out_dir:
+            file_name = "{}_{:0=4d}_{}.jpg".format(image_id, i, flag) if flag else "{}_{:0=4d}.jpg".format(image_id, i)
+            img_file = file_utils.create_dir(out_dir, name, file_name)
+            cv2.imwrite(img_file, img)
+        if vis: image_utils.cv_show_image("crop", img, use_rgb=False, delay=0)
+
+
+if __name__ == "__main__":
+    """
+    对VOC的数据目标进行裁剪
+    室内：['主杆', '从此进出标示牌', '其他鞋', '吊物绳', '在此工作标示牌', '垫子', '安全带', '安全帽', '安全绳',
+          '导线头', '尖嘴钳', '工具袋', '手', '扳手', '抹布', '未穿工作服','柱式绝缘子', '止步高压危险标示牌',
+          '绝缘手套', '绝缘鞋', '脚扣', '螺丝', '身穿工作服', '遮拦杆', '铁架', '铝扎线']
+    室外: []
+    """
+    anno_dir = "/home/PKing/nasdata/dataset-dmai/AIJE/dataset/aije-action-det/aije-action-train-v01/json"
+    class_name = None  # 室内
+    out_dir = os.path.join(os.path.dirname(anno_dir), "crops")
+    dataset = parser_labelme.LabelMeDatasets(filename=None,
+                                             data_root=None,
+                                             anno_dir=anno_dir,
+                                             image_dir=None,
+                                             class_name=class_name,
+                                             check=False,
+                                             phase="val",
+                                             shuffle=False)
+    print("have num:{}".format(len(dataset)))
+    class_name = dataset.class_name
+    scale = [2.0, 2.0]
+    flag = str(scale[0]).replace(".", "p")
+    flag = None
+    # scale = None
+    for i in tqdm(range(len(dataset))):
+        data_info = dataset.__getitem__(i)
+        save_object_crops(data_info, out_dir, class_name=class_name, scale=scale, flag=flag, vis=False)

{pybaseutils-2.0.4 → pybaseutils-2.0.5}/test_py/aije/demo_voc_crop.py

@@ -12,13 +12,13 @@ from pybaseutils.dataloader import parser_voc
 from pybaseutils import image_utils, file_utils
 
 
-def save_object_crops(image, out_dir, bboxes, labels, image_id, class_name=None,
+def save_object_crops(image, out_dir, boxes, labels, image_id, class_name=None,
                       scale=[], square=False, padding=False, flag="", vis=False):
     """
     对VOC的数据目标进行裁剪
     :param image:
     :param out_dir:
-    :param bboxes:
+    :param boxes:
     :param labels:
     :param image_id:
     :param class_name:
@@ -31,15 +31,15 @@ def save_object_crops(image, out_dir, bboxes, labels, image_id, class_name=None,
     """
     image_id = image_id.split(".")[0]
     if square:
-        bboxes = image_utils.get_square_boxes(bboxes, use_max=True, baseline=-1)
+        boxes = image_utils.get_square_boxes(boxes, use_max=True, baseline=-1)
     if scale:
-        bboxes = image_utils.extend_xyxy(bboxes, scale=scale)
+        boxes = image_utils.extend_xyxy(boxes, scale=scale)
     if padding:
-        crops = image_utils.get_bboxes_crop_padding(image, bboxes)
+        crops = image_utils.get_bboxes_crop_padding(image, boxes)
     else:
-        crops = image_utils.get_bboxes_crop(image, bboxes)
+        crops = image_utils.get_bboxes_crop(image, boxes)
     if vis:
-        m = image_utils.draw_image_bboxes_labels(image.copy(), bboxes, labels, class_name=class_name,
+        m = image_utils.draw_image_bboxes_labels(image.copy(), boxes, labels, class_name=class_name,
                                                  thickness=2, fontScale=0.8, drawType="custom")
         image_utils.cv_show_image("image", m, use_rgb=False, delay=0)
     for i, img in enumerate(crops):

pybaseutils-2.0.5/test_py/aije/video_convertor.py

@@ -0,0 +1,27 @@
+# -*-coding: utf-8 -*-
+"""
+    @Author : PKing
+    @E-mail : 
+    @Date   : 2023-08-25 17:42:55
+    @Brief  :
+"""
+import os
+import cv2
+import numpy as np
+from tqdm import tqdm
+from pybaseutils.cvutils import video_utils
+from pybaseutils import image_utils, file_utils
+
+
+def video_converter(inp_dir, out_dir):
+    files = file_utils.get_files_list(inp_dir, postfix=["*.dav"])
+    for video_file in tqdm(files):
+        save_video = file_utils.create_dir(out_dir, None, os.path.basename(video_file))
+        save_video = save_video.replace(".dav", ".mp4")
+        video_utils.video2video(video_file, save_video, interval=1, vis=False)
+
+
+if __name__ == '__main__':
+    inp_dir = "/home/PKing/nasdata/dataset-dmai/AIJE/技能人才系统_数据集管理/江门四维数据/江门四维2024-08-06/NVR录像文件"
+    out_dir = "/home/PKing/nasdata/dataset-dmai/AIJE/技能人才系统_数据集管理/江门四维数据/江门四维2024-08-06/MP4录像文件"
+    video_converter(inp_dir, out_dir)

{pybaseutils-2.0.4 → pybaseutils-2.0.5}/test_py/converter/convert_cvat2labelme.py

@@ -14,6 +14,7 @@ from pybaseutils.converter import build_voc, build_labelme, convert_cvat2labelme
 from pybaseutils import file_utils, image_utils, json_utils
 
 if __name__ == "__main__":
-    image_dir = "/home/PKing/nasdata/dataset-dmai/AIJE/dataset/aije-outdoor-det-fix/dataset-v20/JPEGImages"
-    anno_dir = "/home/PKing/nasdata/dataset-dmai/AIJE/dataset/aije-outdoor-det-fix/dataset-v20/xml"
-    convert_cvat2labelme.convert_cvat2labelme(anno_dir=anno_dir, image_dir=image_dir,  thickness=2, fontScale=1.2,vis=True)
+    image_dir = "/home/PKing/nasdata/dataset-dmai/AIJE/dataset/aije-action-det/aije-action-train-v20/JPEGImages"
+    anno_dir = "/home/PKing/nasdata/dataset-dmai/AIJE/dataset/aije-action-det/aije-action-train-v20/xml"
+    convert_cvat2labelme.convert_cvat2labelme(anno_dir=anno_dir, image_dir=image_dir,
+                                              thickness=2, fontScale=1.2, vis=False)

pybaseutils-2.0.5/test_py/converter/get_pair_data.py

@@ -0,0 +1,58 @@
+# -*-coding: utf-8 -*-
+"""
+    @Author : PKing
+    @E-mail : 
+    @Date   : 2024-08-24 11:05:52
+    @Brief  :
+"""
+import os
+import numpy as np
+import itertools
+from pybaseutils import file_utils, image_utils
+
+
+def get_combinations_pair_data(image_dir, pair_num=0):
+    """
+    :param image_dir:
+    :param pair_num:
+    :return:
+    """
+    max_nums = int(pair_num / 2)
+    image_list = file_utils.get_files_lists(image_dir)
+    image_list = file_utils.get_sub_list(image_list, dirname=image_dir)
+    nums = len(image_list)
+    print("have {} images and {} combinations".format(nums, nums * (nums - 1) / 2))
+    pairs = []
+    for paths in itertools.combinations(image_list, 2):
+        file1, file2 = paths
+        label1 = file1.split(os.sep)[0]
+        label2 = file2.split(os.sep)[0]
+        if label1 == label2:
+            pairs.append([file1, file2, 1])
+        else:
+            pairs.append([file1, file2, 0])
+    pairs = np.asarray(pairs)
+    pairs = pairs[np.lexsort(pairs.T)]
+    pair0 = pairs[pairs[:, -1] == "0", :]
+    pair1 = pairs[pairs[:, -1] == "1", :]
+    nums1 = len(pair1)
+    nums0 = len(pair0)
+    if pair_num < 0: max_nums = nums1
+    if max_nums > nums1:
+        raise Exception("pair_nums({}) must be less than num_pair_issame_1({})".format(max_nums, nums1))
+    index_0 = np.random.permutation(nums0)[:max_nums]  # 打乱后的行号
+    index_1 = np.random.permutation(nums1)[:max_nums]  # 打乱后的行号
+    pair0 = pair0[index_0, :]  # 获取打乱后的训练数据
+    pair1 = pair1[index_1, :]  # 获取打乱后的训练数据
+    pairs = np.concatenate([pair0, pair1], axis=0).tolist()
+    print("pair0 nums:{}".format(len(pair0)))
+    print("pair1 nums:{}".format(len(pair1)))
+    print("have {} pairs".format(len(pairs)))
+    return pairs
+
+
+if __name__ == '__main__':
+    image_dir = "/home/PKing/nasdata/dataset-dmai/AIJE/dataset/aije-action-cvlm/test/images"
+    pairs_file = os.path.join(image_dir,"pairs.txt")
+    pairs = get_combinations_pair_data(image_dir, pair_num=10000)
+    file_utils.write_data(pairs_file, pairs)

{pybaseutils-2.0.4 → pybaseutils-2.0.5}/test_py/demo1.py

@@ -32,14 +32,23 @@ class MultiViewer(object):
         return "exit"
 
 
-def demo():
-    key = "multiview"
-    frame_info = {"multiview": ["ABCD"]}
-    with MultiViewer(frame_info=frame_info, key=key) as v:
-        pass
-    print("data")
-    return "Z"
+class Promote():
+    def __init__(self, promote):
+        self.promote = file_utils.read_data(promote, split=None)
+        print("promote:{}".format(self.promote))
+
+    def __len__(self):
+        return len(self.promote)
+
+    def __getitem__(self, index):
+        data: str = self.promote[random.randint(0, len(self.promote)-1)]
+        data = data.format("ddd")
+        return data
 
 
 if __name__ == '__main__':
-    print(demo())
+    file = "/home/PKing/nasdata/dataset-dmai/AIJE/dataset/aije-action-cvlm/promote.txt"
+    p = Promote(promote=file)
+    for index in range(len(p)):
+        data = p.__getitem__(index)
+        print(data)

pybaseutils-2.0.5/test_py/demo2.py

@@ -0,0 +1,29 @@
+# -*-coding: utf-8 -*-
+"""
+    @Author : PKing
+    @E-mail : 390737991@qq.com
+    @Date   : 2022-12-31 11:37:30
+    @Brief  : https://blog.csdn.net/qdPython/article/details/121381363
+"""
+import cv2
+import random
+import types
+import numpy as np
+from typing import Callable
+from pybaseutils import image_utils, file_utils
+from pybaseutils.cvutils import video_utils
+import cv2
+
+if __name__ == '__main__':
+    from pybaseutils.converter import convert_voc2yolo
+
+    # 定义类别数
+    class_name = ["aeroplane", "bicycle", "bird", "boat", "bottle", "bus", "car", "cat",
+                  "chair", "cow", "diningtable", "dog", "horse", "motorbike", "person",
+                  "pottedplant", "sheep", "sofa", "train", "tvmonitor"]
+    # VOC数据目录
+    data_root = "/path/to/VOC2007"
+    # 保存输出yolo格式数据目录
+    out_text_dir = os.path.join(data_root, "labels")
+    # 开始转换,vis=True进行可视化
+    convert_voc2yolo.convert_voc2yolo(data_root, out_text_dir, class_name=class_name, vis=True)

{pybaseutils-2.0.4 → pybaseutils-2.0.5}/test_py/demo_lableme_vis.py

@@ -20,7 +20,7 @@ if __name__ == "__main__":
     # anno_dir = "/home/PKing/nasdata/tmp/tmp/WaterMeter/水表数据集/Water-Meter-Det3/train/json"
     # names = ["BG", "unique"]
     anno_dir = "/home/PKing/nasdata/tmp/tmp/WaterMeter/水表数据集/Water-Meter-Det1/val/json"
-    anno_dir = "/home/PKing/nasdata/dataset-dmai/AIJE/dataset/aije-outdoor-det-fix/dataset-v01/json"
+    anno_dir = "/home/PKing/nasdata/dataset-dmai/AIJE/dataset/aije-outdoor-det-fix/dataset-v20/json"
     names = None
     dataset = parser_labelme.LabelMeDatasets(filename=None,
                                              data_root=None,

pybaseutils-2.0.4/test_py/aije/video_demo.py

@@ -1,47 +0,0 @@
-# -*-coding: utf-8 -*-
-"""
-    @Author : PKing
-    @E-mail : 
-    @Date   : 2023-08-25 17:42:55
-    @Brief  :
-"""
-import os
-import cv2
-import numpy as np
-from tqdm import tqdm
-from pybaseutils import image_utils, file_utils
-
-
-def rename_image_file(video_file, image_dir, filename, output, prefix="", vis=True):
-    video_cap = image_utils.get_video_capture(video_file)
-    width, height, num_frames, fps = image_utils.get_video_info(video_cap)
-    file_list = file_utils.read_data(filename, split=None)
-    file_utils.create_dir(output)
-    for i, file in tqdm(enumerate(file_list)):
-        image_file = os.path.join(image_dir, file)
-        image_id = os.path.basename(file).split(".")[0]
-        count = int(image_id.split("_")[-1])
-        # 设置抽帧的位置
-        video_cap.set(cv2.CAP_PROP_POS_FRAMES, count)
-        isSuccess, frame = video_cap.read()
-        if isSuccess and os.path.exists(image_file):
-            srcfile = os.path.join(output, f"{image_id}_1x.jpg")
-            outfile = os.path.join(output, f"{image_id}_6x.jpg")
-            image = cv2.imread(image_file)
-            cv2.imwrite(outfile, frame)
-            file_utils.copy_file(image_file, srcfile)
-            diff = np.asarray(image, dtype=np.float32) - np.asarray(frame, dtype=np.float32)
-            diff = np.asarray(np.abs(diff), dtype=np.uint8)
-            # com = image_utils.image_vstack([image, frame, diff])
-            com = image_utils.image_hstack([image, frame])
-            # image_utils.cv_show_image("image-frame", com, delay=0)
-
-
-if __name__ == '__main__':
-    image_dir = "/home/PKing/nasdata/dataset-dmai/AIJE/dataset/aije-det-dataset/video-compress/JPEGImages"
-    filename = "/home/PKing/nasdata/dataset-dmai/AIJE/dataset/aije-det-dataset/video-compress/camera3.txt"
-    # video_file = "/home/PKing/nasdata/dataset-dmai/AIJE/POC/南方电网视频/我的文件/室内/平视-3号位.mp4"
-    video_file = "/home/PKing/nasdata/dataset-dmai/AIJE/岗评项目数据/东莞视频/室内/20231027_第二场"
-    output = "/home/PKing/nasdata/dataset-dmai/AIJE/dataset/aije-det-dataset/video-compress/compress/camera3"
-
-    rename_image_file(video_file, image_dir, filename, output)

pybaseutils-2.0.4/test_py/demo2.py

@@ -1,25 +0,0 @@
-# -*-coding: utf-8 -*-
-"""
-    @Author : PKing
-    @E-mail : 390737991@qq.com
-    @Date   : 2022-12-31 11:37:30
-    @Brief  : https://blog.csdn.net/qdPython/article/details/121381363
-"""
-import cv2
-import random
-import types
-import numpy as np
-from typing import Callable
-from pybaseutils import image_utils, file_utils
-from pybaseutils.cvutils import video_utils
-import cv2
-
-if __name__ == '__main__':
-    video_file = "/home/PKing/Downloads/kunkun_cut.mp4"
-    saves_file = "/home/PKing/Downloads/kunkun_res.mp4"
-    video_cap = video_utils.video_iterator(video_file, saves_file, start=4, end=10)
-    for data_info in video_cap:
-        frame = data_info["frame"]
-        frame = cv2.resize(frame, dsize=(100, 100))
-        frame = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
-        data_info["frame"] = frame