問題六：
問題五：這里是怎么得到的？
問題四：為什么會是如下結果？
torch.bernoulli(a)怎么是這個結果？
問題1：torch各個類型數據格式如何轉換？數據類型在官方文檔torch.Tensor中，有八種類型。
#嘗試一 i32=torch.IntTensor([1,2,3]) i64=torch.LongTensor([1,2,3]) #兩種轉換都報錯 #new_i64=torch.IntTensor(i64) #new_i32=torch.LongTensor(i32) #didn't match because some of the arguments have invalid types: (!torch.LongTensor!) #嘗試二 new_i32=i32.long() print(torch.equal(new_i32,i64)) #True #torch.Tensor對應八種數據轉換,各種數據可以相互轉換 i32.float() i32.double() i32.half() i32.byte() i32.char() i32.short() i32.int() i32.long()
問題2：官方文檔中sequence of tensors是什么意思？在torch.stack(sequence, dim=0, out=None).
是tensors構成的序列，可以為列表，也可以為元組。
#torch.stack(sequence, dim=0, out=None) 連接Tensors i32=torch.Tensor([1,2,3]) print(torch.stack([i32,i32,i32])) #默認dim=0,以列為基准 # 1 2 3 # 1 2 3 # 1 2 3 # [torch.FloatTensor of size 3x3] print(torch.stack([i32,i32,i32],dim=1)) # 1 1 1 # 2 2 2 # 3 3 3 # [torch.FloatTensor of size 3x3] print(torch.stack((i32,i32,i32),dim=1)) # 1 1 1 # 2 2 2 # 3 3 3 # [torch.FloatTensor of size 3x3]
問題3：為什么有如下Tensor格式區別？有的是size 3，有的是size 4x1 ？
torch.from_numpy(np.array([1,2,3])) #torch.IntTensor of size 3
torch.from_numpy(np.array([1.0,2,3])) #torch.DoubleTensor of size 3
torch.nonzero(torch.Tensor([1,2,3,0,4]))==torch.Tensor([0,1,2,4]) #nonzero 非0元素所在位置
# TypeError: eq received an invalid combination of arguments - got (torch.FloatTensor), but expected one of:
# * (int value)
# didn't match because some of the arguments have invalid types: (!torch.FloatTensor!)
# * (torch.LongTensor other)
# didn't match because some of the arguments have invalid types: (!torch.FloatTensor!)
#注意上面代碼中兩者數據格式類型不一致，torch.FloatTensor torch.LongTensor
#torch.unsqueeze(input,dim,out=None)
m=torch.Tensor([1,2,3,4])
print(m) #torch.FloatTensor of size 4
m_zero=torch.unsqueeze(m,0) print(m_zero) #torch.FloatTensor of size 1x4 m_one=torch.unsqueeze(m,1) print(m_one) #torch.FloatTensor of size 4x1 m_zero_to_m=torch.squeeze(m_zero) print(m_zero_to_m) #torch.FloatTensor of size 4 print(m==m_zero_to_m) #torch.ByteTensor of size 4 # 1 # 1 # 1 # 1
print(m.equal(m_zero_to_m)) True
可見為兩種不同數據類型，可以通過unsqueeze和squeeze來相互轉化。判斷兩個Tensor是否相等，用equal
問題4、