0

我正在使用 fastai ==0.7.0 当我尝试运行此代码时，每次都会抛出此错误。

data = ImageClassifierData.from_paths(PATH, tfms=tfms, bs=bs, num_workers=4) #this line throws error
learn = ConvLearner.pretrained(arch, data, precompute=False)

  File "demo.py", line 37, in <module>
    data = ImageClassifierData.from_paths(PATH, tfms=tfms, bs=bs, num_workers=4)
  File "/home/anilvanjaremp3/.conda/envs/fastai/lib/python3.6/site-packages/fastai/dataset.py", line 425, in from_paths
    datasets = cls.get_ds(FilesIndexArrayDataset, trn, val, tfms, path=path, test=test)
  File "/home/anilvanjaremp3/.conda/envs/fastai/lib/python3.6/site-packages/fastai/dataset.py", line 363, in get_ds
    fn(trn[0], trn[1], tfms[0], **kwargs), # train
  File "/home/anilvanjaremp3/.conda/envs/fastai/lib/python3.6/site-packages/fastai/dataset.py", line 261, in __init__
    super().__init__(fnames, transform, path)
  File "/home/anilvanjaremp3/.conda/envs/fastai/lib/python3.6/site-packages/fastai/dataset.py", line 237, in __init__
    super().__init__(transform)
  File "/home/anilvanjaremp3/.conda/envs/fastai/lib/python3.6/site-packages/fastai/dataset.py", line 156, in __init__
    self.c = self.get_c()
  File "/home/anilvanjaremp3/.conda/envs/fastai/lib/python3.6/site-packages/fastai/dataset.py", line 267, in get_c
    def get_c(self): return int(self.y.max())+1
  File "/home/anilvanjaremp3/.conda/envs/fastai/lib/python3.6/site-packages/numpy/core/_methods.py", line 28, in _amax
    return umr_maximum(a, axis, None, out, keepdims, initial)
ValueError: zero-size array to reduction operation maximum which has no identity
4

0 回答 0