本文共 6034 字,大约阅读时间需要 20 分钟。
注意:使用 3.16.2版本的labelme, 博主试过4.2.10版本的labelme,会报错,没有draw.py文件。 且博主试过了,将3.16.2版本的draw.py文件拷贝到4.2.10文件夹下的utils文件中,自己构建也是不行的,会报错。 应该得改动draw.py文件中的内容吧。
以下代码为全部代码,可直接运行。
# -*- encoding: utf-8 -*-"""@File : json_to_dataset.py.py@Time : 2020/5/28 18:09@Author : ligang@WeChat : by15188607997@Software: PyCharm@explain:本文件为将json文件批量转为dataset"""import argparseimport jsonimport osimport os.path as ospimport warningsimport PIL.Imageimport yamlfrom labelme import utilsimport base64# 使用 3.16.2版本的labelme, 博主试过4.2.10版本的labelme,会报错,没有draw.py文件。# 且博主试过了,将3.16.2版本的draw.py文件拷贝到4.2.10文件夹下的utils文件中,自己构建也是不行的,会报错。# 应该得改动draw.py文件中的内容吧。def main(frompath, outputpath): count = os.listdir(frompath) for i in range(0, len(count)): path = os.path.join(frompath, count[i]) if os.path.isfile(path) and path.endswith('json'): data = json.load(open(path)) if data['imageData']: imageData = data['imageData'] else: imagePath = os.path.join(os.path.dirname(path), data['imagePath']) print(imagePath) with open(imagePath, 'rb') as f: imageData = f.read() imageData = base64.b64encode(imageData).decode('utf-8') img = utils.img_b64_to_arr(imageData) label_name_to_value = { '_background_': 0} for shape in data['shapes']: label_name = shape['label'] if label_name in label_name_to_value: label_value = label_name_to_value[label_name] else: label_value = len(label_name_to_value) label_name_to_value[label_name] = label_value # label_values must be dense label_values, label_names = [], [] for ln, lv in sorted(label_name_to_value.items(), key=lambda x: x[1]): label_values.append(lv) label_names.append(ln) assert label_values == list(range(len(label_values))) lbl = utils.shapes_to_label(img.shape, data['shapes'], label_name_to_value) captions = ['{}: {}'.format(lv, ln) for ln, lv in label_name_to_value.items()] lbl_viz = utils.draw_label(lbl, img, captions) out_dir = osp.basename(count[i]).replace('.', '_') out_dir = osp.join(osp.dirname(count[i]), out_dir) out_dir = osp.join(outputpath, out_dir) if not osp.exists(out_dir): os.mkdir(out_dir) PIL.Image.fromarray(img).save(osp.join(out_dir, 'img.png')) utils.lblsave(osp.join(out_dir, 'label.png'), lbl) PIL.Image.fromarray(lbl_viz).save(osp.join(out_dir, 'label_viz.png')) with open(osp.join(out_dir, 'label_names.txt'), 'w') as f: for lbl_name in label_names: f.write(lbl_name + '\n') warnings.warn('info.yaml is being replaced by label_names.txt') info = dict(label_names=label_names) with open(osp.join(out_dir, 'info.yaml'), 'w') as f: yaml.safe_dump(info, f, default_flow_style=False) print('Saved to: %s' % out_dir)if __name__ == '__main__': # 源图片、json 文件路径 frompath = "./before/" # 生成数据保存路径 outputpath = "./output" if not osp.exists(outputpath): os.mkdir(outputpath) main(frompath, outputpath)
结果:保存在输出的output文件中,此文件作用同 labelme_json_to_dataset <**.json> 作用。上面代码是批量的。
注意:class_name.txt文件中的类需要手动填写。
# -*- encoding: utf-8 -*-"""@File : get_jpg_and_png.py@Time : 2020/5/28 18:07@Author : ligang@WeChat : by15188607997@Software: PyCharm"""import osfrom PIL import Imageimport numpy as npdef main(frompath_jpg, outputpath_json, output_jpg, output_png, path_allclass): # 读取原文件夹 count = os.listdir(frompath_jpg) for i in range(0, len(count)): # 如果里的文件以jpg结尾 # 则寻找它对应的png if count[i].endswith("jpg"): path = os.path.join(frompath_jpg, count[i]) img = Image.open(path) img.save(os.path.join(output_jpg, count[i])) print(count[i].split(".")[1]) # 找到对应的png path = outputpath_json + count[i].split(".")[0] + "_json/label.png" img = Image.open(path) # 找到全局的类 class_txt = open(path_allclass, "r") class_name = class_txt.read().splitlines() # ["bk","cat","dog"] # 打开json文件里面存在的类,称其为局部类 with open(outputpath_json + count[i].split(".")[0] + "_json/label_names.txt", "r") as f: names = f.read().splitlines() # ["bk","dog"] new = Image.new("RGB", [np.shape(img)[1], np.shape(img)[0]]) for name in names: # index_json是json文件里存在的类,局部类 index_json = names.index(name) # index_all是全局的类 index_all = class_name.index(name) # 将局部类转换成为全局类 new = new + np.expand_dims(index_all * (np.array(img) == index_json), -1) new = Image.fromarray(np.uint8(new)) print(output_png) new.save(os.path.join(output_png, count[i].replace("jpg", "png"))) print(np.max(new), np.min(new))if __name__ == '__main__': # 全局类(所有标签总共有多少类) 如: # _background_(不可少) # Albatross # _Yellowthroat path_allclass = "./before/class_name.txt" # 源图片、json 文件路径 frompath_jpg = "./before/" # 生成数据保存路径 outputpath_json = "./output/" # 生成jpg数据的保存位置 output_jpg = "./traindata/jpg/" # 生成png数据的保存位置 output_png = "./traindata/png/" if not os.path.exists(output_jpg): os.makedirs(output_jpg) if not os.path.exists(output_png): os.makedirs(output_png) main(frompath_jpg, outputpath_json, output_jpg, output_png, path_allclass)
结果:成果保存在traindata文件夹下。生成的png图片为二值化图。像素变化从 (1,1,1)开始的眼是看不来的,可以用取色器进行取色验证下。
目录结构:
转载地址:http://ibhof.baihongyu.com/