train!

实验八/1.get_dataset.py

@@ -1,4 +1,7 @@
+import bz2
 import os
+import tempfile
+
 import requests
 import tqdm
 import tarfile
@@ -62,6 +65,27 @@ def decompress(file_path, output_dir):
                 tar.extract(member, path=output_dir)
                 bar.update(1)
 
+
+def decompress_bz2(file_path, output_dir):
+    # 确保输出目录存在
+    os.makedirs(output_dir, exist_ok=True)
+    print('解压 ' + file_path.split('/')[-1], ' 到 ', output_dir)
+
+    # 获取.bz2文件的名称，不包含扩展名
+    output_filename = os.path.basename(file_path).rsplit('.bz2', 1)[0]
+
+    # 构建输出文件的完整路径
+    output_file_path = os.path.join(output_dir, output_filename)
+
+    # 检查输出文件是否已存在，如果存在则跳过解压
+    if os.path.exists(output_file_path):
+        print(output_filename, ' 已存在，跳过解压')
+        return
+
+    # 解压.bz2文件
+    with bz2.BZ2File(file_path, 'rb') as bz2_file, open(output_file_path, 'wb') as output_file:
+        output_file.write(bz2_file.read())
+
 # 下载人脸数据集
 face_dataset_url='http://vis-www.cs.umass.edu/fddb/originalPics.tar.gz'
 face_dataset_path='cache/dataset/face/'
@@ -77,8 +101,11 @@ decompress(os.path.join(face_dataset_path,face_dataset_url.split('/')[-1]),face_
 decompress(os.path.join(face_label_path,face_label_url.split('/')[-1]),face_label_path)
 
 # 下载ResNet模型
-model_url1='https://github.com/davisking/dlib-models/raw/master/shape_predictor_68_face_landmarks.dat'
-model_url2='https://github.com/davisking/dlib-models/raw/master/dlib_face_recognition_resnet_model_v1.dat'
+model_url1='https://github.com/davisking/dlib-models/raw/refs/heads/master/shape_predictor_68_face_landmarks.dat.bz2'
+model_url2='https://github.com/davisking/dlib-models/raw/refs/heads/master/dlib_face_recognition_resnet_model_v1.dat.bz2'
 model_path='models/'
 download(model_url1,model_path)
-download(model_url2,model_path)
+download(model_url2,model_path)
+
+decompress_bz2(os.path.join(model_path,model_url1.split('/')[-1]),model_path)
+decompress_bz2(os.path.join(model_path,model_url2.split('/')[-1]),model_path)