我正在使用googlequickdraw数据集ndjson文件制作一个应用程序。我在文件的每一行运行此函数:
def parse_line(ndjson_line):
"""Parse an ndjson line and return ink (as np array) and classname."""
sample = json.loads(ndjson_line)
class_name = sample["word"]
if not class_name:
print("Empty classname")
return None, None
inkarray = sample["drawing"]
stroke_lengths = [len(stroke[0]) for stroke in inkarray]
total_points = sum(stroke_lengths)
np_ink = np.zeros((total_points, 3), dtype=np.float32)
current_t = 0
if not inkarray:
print("Empty inkarray")
return None, None
for stroke in inkarray:
if len(stroke[0]) != len(stroke[1]):
print("Inconsistent number of x and y coordinates.")
return None, None
for i in [0, 1]:
np_ink[current_t:(current_t + len(stroke[0])), i] = stroke[i]
current_t += len(stroke[0])
np_ink[current_t - 1, 2] = 1 # stroke_end
# Preprocessing.
# 1. Size normalization.
lower = np.min(np_ink[:, 0:2], axis=0)
upper = np.max(np_ink[:, 0:2], axis=0)
scale = upper - lower
scale[scale == 0] = 1
np_ink[:, 0:2] = (np_ink[:, 0:2] - lower) / scale
# 2. Compute deltas.
np_ink[1:, 0:2] -= np_ink[0:-1, 0:2]
np_ink = np_ink[1:, :]
return np_ink, class_name
它适用于大多数线路,但也适用于少数线路,例如:
^{pr2}$我得到以下错误:
Traceback (most recent call last):
File "A:\Code\Machine Learning\Software Engineering project\Quick Draw\Create_Dataset_from_ndjson.py", line 168, in <module>
tf.app.run(main=main,argv=[sys.argv[0]]+unparsed)
File "C:\Users\shind\AppData\Local\Programs\Python\Python36\lib\site-packages\tensorflow\python\platform\app.py", line 125, in run
_sys.exit(main(argv))
File "A:\Code\Machine Learning\Software Engineering project\Quick Draw\Create_Dataset_from_ndjson.py", line 124, in main
classes = convert_to_tfrecord(FLAGS.source_path,FLAGS.destination_path,FLAGS.train_examples_per_class,FLAGS.eval_examples_per_class,FLAGS.classes_path,FLAGS.output_shards)
File "A:\Code\Machine Learning\Software Engineering project\Quick Draw\Create_Dataset_from_ndjson.py", line 98, in convert_to_tfrecord
drawing, class_name = parse_line(ndjson_line)
File "A:\Code\Machine Learning\Software Engineering project\Quick Draw\Create_Dataset_from_ndjson.py", line 13, in parse_line
sample = json.loads(ndjson_line)
File "C:\Users\shind\AppData\Local\Programs\Python\Python36\lib\json\__init__.py", line 354, in loads
return _default_decoder.decode(s)
File "C:\Users\shind\AppData\Local\Programs\Python\Python36\lib\json\decoder.py", line 339, in decode
obj, end = self.raw_decode(s, idx=_w(s, 0).end())
File "C:\Users\shind\AppData\Local\Programs\Python\Python36\lib\json\decoder.py", line 357, in raw_decode
raise JSONDecodeError("Expecting value", s, err.value) from None
json.decoder.JSONDecodeError: Expecting value: line 1 column 1 (char 0)
这个错误的原因是什么?上面写的是期望值,但我已经过了,那它需要什么?而且,这看起来和我传递的其他行没有什么不同,它们没有给出任何错误,那么这行是怎么回事?我需要对JSON文件或代码进行哪些更改?我已经从googlegithub存储库中获取了代码。另外,我在数据集中使用简化的JSON文件。整个数据集是:
可能是你的数据集有空行,你可以尝试添加这个来检查错误字符串
更新#2
异常处理
^{pr2}$相关问题 更多 >
编程相关推荐