CNNの全結合層の出力サイズ確認におけるAssertionErrorの対処

AssertionError                            Traceback (most recent call last)
<ipython-input-386-59bf517e9f78> in <module>()
     41 # ---------- CNNの出力確認 ----------
     42 cnn = CNN()                   #インスタンスの作成
---> 43 print(cnn(size_check).shape)  #AssertionErrorの発生...原因は？？
     44 
     45 #       except AssertionError:

<ipython-input-386-59bf517e9f78> in __call__(self, x)
     27 
     28     def __call__(self, x):
---> 29         conv1 = self.conv1(x)
     30         bat1  = self.bat1(conv1)
     31         relu1 = F.relu(bat1)

~\Anaconda3\lib\site-packages\chainer\link.py in __call__(self, *args, **kwargs)
    285             # forward is implemented in the child classes
    286             forward = self.forward  # type: ignore
--> 287         out = forward(*args, **kwargs)
    288 
    289         # Call forward_postprocess hook

~\Anaconda3\lib\site-packages\chainer\links\connection\convolution_nd.py in forward(self, x)
    213         return convolution_nd.convolution_nd(
    214             x, self.W, self.b, self.stride, self.pad, cover_all=self.cover_all,
--> 215             dilate=self.dilate, groups=self.groups)
    216 
    217 

~\Anaconda3\lib\site-packages\chainer\functions\connection\convolution_nd.py in convolution_nd(x, W, b, stride, pad, cover_all, dilate, groups)
    497     ndim = len(x.shape[2:])
    498     fnode = ConvolutionND(
--> 499         ndim, stride, pad, cover_all, dilate=dilate, groups=groups)
    500     args = (x, W) if b is None else (x, W, b)
    501     y, = fnode.apply(args)

~\Anaconda3\lib\site-packages\chainer\functions\connection\convolution_nd.py in __init__(self, ndim, stride, pad, cover_all, dilate, groups)
     23         self.pad = conv_nd.as_tuple(pad, ndim)
     24         self.cover_all = cover_all
---> 25         self.dilate = conv_nd.as_tuple(dilate, ndim)
     26         self.groups = groups
     27 

~\Anaconda3\lib\site-packages\chainer\utils\conv_nd.py in as_tuple(x, n)
     11 def as_tuple(x, n):
     12     if hasattr(x, '__getitem__'):
---> 13         assert len(x) == n
     14         return tuple(x)
     15     return (x,) * n

AssertionError: 

#---------- import ----------
import chainer
import chainer.functions as F
import chainer.links as L
import numpy as np
import pandas as pd
import scipy.io

# ---------- 入力データの作成 ----------

abc = chainer.Variable(np.array([[1, 2, 3] , [4, 5, 6] , [7, 8, 9] , [10, 11, 12]], dtype=np.float32))
size_check = abc
print("size_check.shape",size_check.shape) 

# ---------- CNNの定義 ----------
class CNN(chainer.Chain):
    def __init__(self):
        super(CNN,self).__init__()
        with self.init_scope():
            self.conv1  = L.ConvolutionND(1,4,10,3,stride=1,pad=1)  #(1次元畳み込み,入力4ch,出力10ch,フィルターサイズ:3、stride=1,pad=1)
            self.bat1   = L.BatchNormalization(10)
            self.l1     = L.Linear(None, 3)

    def __call__(self, x):
        conv1 = self.conv1(x)
        bat1  = self.bat1(conv1)
        relu1 = F.relu(bat1)
        pool1 = F.max_pooling_nd(relu1,2,Stride=1)
        xyz   = self.l1(pool1)
        return xyz 
    
    def check_cnn_size(self,size_check):
        out = self(size_check)
        return out   
    
# ---------- CNNの出力確認 ----------
cnn = CNN()                   #インスタンスの作成    
print(cnn(size_check).shape)  #AssertionErrorの発生...原因は？？