Spaces:
Runtime error
Runtime error
File size: 5,446 Bytes
fc8c192 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 |
import json
import os
import random
import traceback
import numpy as np
from paddle.io import Dataset
from .imaug import create_operators, transform
class SimpleDataSet(Dataset):
def __init__(self, config, mode, logger, seed=None):
super(SimpleDataSet, self).__init__()
self.logger = logger
self.mode = mode.lower()
global_config = config["Global"]
dataset_config = config[mode]["dataset"]
loader_config = config[mode]["loader"]
self.delimiter = dataset_config.get("delimiter", "\t")
label_file_list = dataset_config.pop("label_file_list")
data_source_num = len(label_file_list)
ratio_list = dataset_config.get("ratio_list", 1.0)
if isinstance(ratio_list, (float, int)):
ratio_list = [float(ratio_list)] * int(data_source_num)
assert (
len(ratio_list) == data_source_num
), "The length of ratio_list should be the same as the file_list."
self.data_dir = dataset_config["data_dir"]
self.do_shuffle = loader_config["shuffle"]
self.seed = seed
logger.info("Initialize indexs of datasets:%s" % label_file_list)
self.data_lines = self.get_image_info_list(label_file_list, ratio_list)
self.data_idx_order_list = list(range(len(self.data_lines)))
if self.mode == "train" and self.do_shuffle:
self.shuffle_data_random()
self.ops = create_operators(dataset_config["transforms"], global_config)
self.ext_op_transform_idx = dataset_config.get("ext_op_transform_idx", 2)
self.need_reset = True in [x < 1 for x in ratio_list]
def get_image_info_list(self, file_list, ratio_list):
if isinstance(file_list, str):
file_list = [file_list]
data_lines = []
for idx, file in enumerate(file_list):
with open(file, "rb") as f:
lines = f.readlines()
if self.mode == "train" or ratio_list[idx] < 1.0:
random.seed(self.seed)
lines = random.sample(lines, round(len(lines) * ratio_list[idx]))
data_lines.extend(lines)
return data_lines
def shuffle_data_random(self):
random.seed(self.seed)
random.shuffle(self.data_lines)
return
def _try_parse_filename_list(self, file_name):
# multiple images -> one gt label
if len(file_name) > 0 and file_name[0] == "[":
try:
info = json.loads(file_name)
file_name = random.choice(info)
except:
pass
return file_name
def get_ext_data(self):
ext_data_num = 0
for op in self.ops:
if hasattr(op, "ext_data_num"):
ext_data_num = getattr(op, "ext_data_num")
break
load_data_ops = self.ops[: self.ext_op_transform_idx]
ext_data = []
while len(ext_data) < ext_data_num:
file_idx = self.data_idx_order_list[np.random.randint(self.__len__())]
data_line = self.data_lines[file_idx]
data_line = data_line.decode("utf-8")
substr = data_line.strip("\n").split(self.delimiter)
file_name = substr[0]
file_name = self._try_parse_filename_list(file_name)
label = substr[1]
img_path = os.path.join(self.data_dir, file_name)
data = {"img_path": img_path, "label": label}
if not os.path.exists(img_path):
continue
with open(data["img_path"], "rb") as f:
img = f.read()
data["image"] = img
data = transform(data, load_data_ops)
if data is None:
continue
if "polys" in data.keys():
if data["polys"].shape[1] != 4:
continue
ext_data.append(data)
return ext_data
def __getitem__(self, idx):
file_idx = self.data_idx_order_list[idx]
data_line = self.data_lines[file_idx]
try:
data_line = data_line.decode("utf-8")
substr = data_line.strip("\n").split(self.delimiter)
file_name = substr[0]
file_name = self._try_parse_filename_list(file_name)
label = substr[1]
img_path = os.path.join(self.data_dir, file_name)
data = {"img_path": img_path, "label": label}
if not os.path.exists(img_path):
raise Exception("{} does not exist!".format(img_path))
with open(data["img_path"], "rb") as f:
img = f.read()
data["image"] = img
data["ext_data"] = self.get_ext_data()
outs = transform(data, self.ops)
except:
self.logger.error(
"When parsing line {}, error happened with msg: {}".format(
data_line, traceback.format_exc()
)
)
outs = None
if outs is None:
# during evaluation, we should fix the idx to get same results for many times of evaluation.
rnd_idx = (
np.random.randint(self.__len__())
if self.mode == "train"
else (idx + 1) % self.__len__()
)
return self.__getitem__(rnd_idx)
return outs
def __len__(self):
return len(self.data_idx_order_list)
|