错误ValueError的原因是什么：每个通道预计超过1个值？

Question

reference fast.ai

github repository of fast.ai（因为代码提升了构建在PyTorch之上的库）

请滚动讨论一下

我正在运行以下代码，并在尝试将数据传递给predict_array函数时出错

当我尝试使用它直接在单个图像上进行预测时代码失败但是当相同的图像在test文件夹中时它运行完美

from fastai.conv_learner import *
from planet import f2

PATH = 'data/shopstyle/'

metrics=[f2]
f_model = resnet34

def get_data(sz):
    tfms = tfms_from_model(f_model, sz, aug_tfms=transforms_side_on, max_zoom=1.05)
    return ImageClassifierData.from_csv(PATH, 'train', label_csv, tfms=tfms, suffix='.jpg', val_idxs=val_idxs, test_name='test')

def print_list(list_or_iterator):
        return "[" + ", ".join( str(x) for x in list_or_iterator) + "]"

label_csv = f'{PATH}prod_train.csv'
n = len(list(open(label_csv)))-1
val_idxs = get_cv_idxs(n)

sz = 64
data = get_data(sz)

print("Loading model...")
learn = ConvLearner.pretrained(f_model, data, metrics=metrics)
learn.load(f'{sz}')
#learn.load("tmp")

print("Predicting...")
learn.precompute=False
trn_tfms, val_tfrms = tfms_from_model(f_model, sz)
#im = val_tfrms(open_image(f'{PATH}valid/4500132.jpg'))
im = val_tfrms(np.array(PIL.Image.open(f'{PATH}valid/4500132.jpg')))
preds = learn.predict_array(im[None])
p=list(zip(data.classes, preds))
print("predictions = " + print_list(p))

这是我正在获取的回溯

  Traceback (most recent call last):
  File "predict.py", line 34, in <module>
    preds = learn.predict_array(im[None])
  File "/home/ubuntu/fastai/courses/dl1/fastai/learner.py", line 266, in predict_array
    def predict_array(self, arr): return to_np(self.model(V(T(arr).cuda())))
  File "/home/ubuntu/src/anaconda3/envs/fastai/lib/python3.6/site-packages/torch/nn/modules/module.py", line 325, in __call__
    result = self.forward(*input, **kwargs)
  File "/home/ubuntu/src/anaconda3/envs/fastai/lib/python3.6/site-packages/torch/nn/modules/container.py", line 67, in forward
    input = module(input)
  File "/home/ubuntu/src/anaconda3/envs/fastai/lib/python3.6/site-packages/torch/nn/modules/module.py", line 325, in __call__
    result = self.forward(*input, **kwargs)
  File "/home/ubuntu/src/anaconda3/envs/fastai/lib/python3.6/site-packages/torch/nn/modules/batchnorm.py", line 37, in forward
    self.training, self.momentum, self.eps)
  File "/home/ubuntu/src/anaconda3/envs/fastai/lib/python3.6/site-packages/torch/nn/functional.py", line 1011, in batch_norm
    raise ValueError('Expected more than 1 value per channel when training, got input size {}'.format(size))
ValueError: Expected more than 1 value per channel when training, got input size [1, 1024]

我试过的事情

• np.expand_dims(IMG,axis=0) or image = image[..., np.newaxis]
• 尝试了另一种阅读图像的方式

  img = cv2.imread(img_path)
  img = cv2.resize(img, dsize = (200,200))
  img = np.einsum('ijk->kij', img)
  img = np.expand_dims(img, axis =0) 
  img = torch.from_numpy(img) 
  learn.model(Variable(img.float()).cuda())

BTW错误仍然存​​在

ValueError: Expected more than 1 value per channel when training, got input size [1, 1024]

在Google搜索中也找不到任何参考..

Answer 1

如果我们使用特征明确的批量标准化，它将在批量1的批次上失败。

正如批量标准化计算：

y = (x - mean(x)) / (std(x) + eps)

如果我们每批有一个样本，那么mean(x) = x，输出将完全为零（忽略偏差）。我们不能用它来学习......

Answer 2

要使用训练有素的模型，请调用model.eval（）以禁用进一步的训练。这会阻止BatchNorm图层更新其均值和方差，并允许仅输入一个样本。如果需要，使用model.train（）恢复训练模式。