![](/img/trans.png)
[英]ValueError: cannot reshape array of size 270000 into shape (1,100,100,3)
[英]ValueError: cannot reshape array of size 300 into shape (100,100,3)
我正在努力重塑我的形象。 这是维度(100,100,3)。 所有图像的总数组组成 (3267, 100, 3)
def get_batch(batch_size,s="train"):
"""Create batch of n pairs, half same class, half different class"""
if s == 'train':
X = Xtrain
X= X.reshape(-1,100,100,3)
#X= X.reshape(-1,20,105,105)
categories = train_classes
else:
X = Xval
X= X.reshape(-1,100,100,3)
categories = val_classes
n_classes, n_examples, w, h, chan = X.shape
print(n_classes)
print(type(n_classes))
print(n_classes.shape)
# randomly sample several classes to use in the batch
categories = rng.choice(n_classes,size=(batch_size,),replace=False)
# initialize 2 empty arrays for the input image batch
pairs=[np.zeros((batch_size, h, w,1)) for i in range(2)]
# initialize vector for the targets
targets=np.zeros((batch_size,))
# make one half of it '1's, so 2nd half of batch has same class
targets[batch_size//2:] = 1
for i in range(batch_size):
category = categories[i]
idx_1 = rng.randint(0, n_examples)
pairs[0][i,:,:,:] = X[category, idx_1].reshape(w, h, chan)
idx_2 = rng.randint(0, n_examples)
# pick images of same class for 1st half, different for 2nd
if i >= batch_size // 2:
category_2 = category
else:
# add a random number to the category modulo n classes to ensure 2nd image has a different category
category_2 = (category + rng.randint(1,n_classes)) % n_classes
pairs[1][i,:,:,:] = X[category_2,idx_2].reshape(w, h,1)
return pairs, targets
但是,当尝试重塑数组pairs[0][i,:,:,:] = X[category, idx_1].reshape(w, h, chan)
我总是得到一个错误,即 300 的数组大小是不可重塑的进入(100,100,3)。 老实说,我不明白为什么应该是这个问题......有人可以帮我吗?
你想要 300 到 100,100,3 的数组。 这不可能是因为(100*100*3)=30000
和30000 not equal to 300
,如果 output 形状具有与输入相同数量的值,则只能重新整形。
我建议你应该改为(10,10,3)
因为(10*10*3)=300
声明:本站的技术帖子网页,遵循CC BY-SA 4.0协议,如果您需要转载,请注明本站网址或者原文地址。任何问题请咨询:yoyou2525@163.com.