FileNotFoundError Traceback (most recent call last)
Cell In[1], line 55
52 print(f"去重完成:{duplicate_count}张重复图像,保留{len(seen_hashes)}张有效图像")
54 # 处理训练集
---> 55 process_dataset(
56 original_data_dir=r'C:/Users/Administrator/swb/2025_“ShuWei Cup”B_Problem/Problem B:Data/AgriculturalDisease_trainingset',
57 save_data_dir=r'C:/Users/Administrator/swb/2025_“ShuWei Cup”B_Problem/clean_data/train',
58 is_train=True
59 )
61 # 处理验证集(假设验证集路径为 'AgriculturalDisease_validationset',需替换为实际路径)
62 process_dataset(
63 original_data_dir=r'C:/Users/Administrator/swb/2025_“ShuWei Cup”B_Problem/Problem B:Data/AgriculturalDisease_validationset',
64 save_data_dir=r'C:/Users/Administrator/swb/2025_“ShuWei Cup”B_Problem/clean_data/val',
65 is_train=False
66 )
Cell In[1], line 25, in process_dataset(original_data_dir, save_data_dir, is_train)
23 if is_train:
24 label_csv = os.path.join(original_data_dir, 'train.csv') # 假设官方训练集标签为train.csv
---> 25 labels = pd.read_csv(label_csv)
26 else:
27 labels = None # 验证集无标签,仅去重图像
File C:\ProgramData\anaconda3\Lib\site-packages\pandas\io\parsers\readers.py:1026, in read_csv(filepath_or_buffer, sep, delimiter, header, names, index_col, usecols, dtype, engine, converters, true_values, false_values, skipinitialspace, skiprows, skipfooter, nrows, na_values, keep_default_na, na_filter, verbose, skip_blank_lines, parse_dates, infer_datetime_format, keep_date_col, date_parser, date_format, dayfirst, cache_dates, iterator, chunksize, compression, thousands, decimal, lineterminator, quotechar, quoting, doublequote, escapechar, comment, encoding, encoding_errors, dialect, on_bad_lines, delim_whitespace, low_memory, memory_map, float_precision, storage_options, dtype_backend)
1013 kwds_defaults = _refine_defaults_read(
1014 dialect,
1015 delimiter,
(...)
1022 dtype_backend=dtype_backend,
1023 )
1024 kwds.update(kwds_defaults)
-> 1026 return _read(filepath_or_buffer, kwds)
File C:\ProgramData\anaconda3\Lib\site-packages\pandas\io\parsers\readers.py:620, in _read(filepath_or_buffer, kwds)
617 _validate_names(kwds.get("names", None))
619 # Create the parser.
--> 620 parser = TextFileReader(filepath_or_buffer, **kwds)
622 if chunksize or iterator:
623 return parser
File C:\ProgramData\anaconda3\Lib\site-packages\pandas\io\parsers\readers.py:1620, in TextFileReader.__init__(self, f, engine, **kwds)
1617 self.options["has_index_names"] = kwds["has_index_names"]
1619 self.handles: IOHandles | None = None
-> 1620 self._engine = self._make_engine(f, self.engine)
File C:\ProgramData\anaconda3\Lib\site-packages\pandas\io\parsers\readers.py:1880, in TextFileReader._make_engine(self, f, engine)
1878 if "b" not in mode:
1879 mode += "b"
-> 1880 self.handles = get_handle(
1881 f,
1882 mode,
1883 encoding=self.options.get("encoding", None),
1884 compression=self.options.get("compression", None),
1885 memory_map=self.options.get("memory_map", False),
1886 is_text=is_text,
1887 errors=self.options.get("encoding_errors", "strict"),
1888 storage_options=self.options.get("storage_options", None),
1889 )
1890 assert self.handles is not None
1891 f = self.handles.handle
File C:\ProgramData\anaconda3\Lib\site-packages\pandas\io\common.py:873, in get_handle(path_or_buf, mode, encoding, compression, memory_map, is_text, errors, storage_options)
868 elif isinstance(handle, str):
869 # Check whether the filename is to be opened in binary mode.
870 # Binary mode does not support 'encoding' and 'newline'.
871 if ioargs.encoding and "b" not in ioargs.mode:
872 # Encoding
--> 873 handle = open(
874 handle,
875 ioargs.mode,
876 encoding=ioargs.encoding,
877 errors=errors,
878 newline="",
879 )
880 else:
881 # Binary mode
882 handle = open(handle, ioargs.mode)
FileNotFoundError: [Errno 2] No such file or directory: 'C:/Users/Administrator/swb/2025_“ShuWei Cup”B_Problem/Problem B:Data/AgriculturalDisease_trainingset\\train.csv'