Pytorch技巧:DataLoader的collate_fn参数使用详解

class torch.utils.data.DataLoader(
 dataset,
 batch_size=1,
 shuffle=False,
 sampler=None,
 batch_sampler=None,
 num_workers=0,
 collate_fn=<function default_collate>,
 pin_memory=False,
 drop_last=False,
 timeout=0,
 worker_init_fn=None)

import torch
import torch.utils.data as Data
import numpy as np

test = np.array([0,1,2,3,4,5,6,7,8,9,10,11])

inputing = torch.tensor(np.array([test[i:i + 3] for i in range(10)]))
target = torch.tensor(np.array([test[i:i + 1] for i in range(10)]))

torch_dataset = Data.TensorDataset(inputing,target)
batch = 3

loader = Data.DataLoader(
 dataset=torch_dataset,
 batch_size=batch, # 批大小
 # 若dataset中的样本数不能被batch_size整除的话，最后剩余多少就使用多少
 collate_fn=lambda x:(
  torch.cat(
   [x[i][j].unsqueeze(0) for i in range(len(x))], 0
   ).unsqueeze(0) for j in range(len(x[0]))
  )
 )

for (i,j) in loader:
 print(i)
 print(j)

tensor([[[ 0, 1, 2],
   [ 1, 2, 3],
   [ 2, 3, 4]]], dtype=torch.int32)
tensor([[[ 0],
   [ 1],
   [ 2]]], dtype=torch.int32)
tensor([[[ 3, 4, 5],
   [ 4, 5, 6],
   [ 5, 6, 7]]], dtype=torch.int32)
tensor([[[ 3],
   [ 4],
   [ 5]]], dtype=torch.int32)
tensor([[[ 6, 7, 8],
   [ 7, 8, 9],
   [ 8, 9, 10]]], dtype=torch.int32)
tensor([[[ 6],
   [ 7],
   [ 8]]], dtype=torch.int32)
tensor([[[ 9, 10, 11]]], dtype=torch.int32)
tensor([[[ 9]]], dtype=torch.int32)

tensor([[ 0, 1, 2],
  [ 1, 2, 3],
  [ 2, 3, 4]], dtype=torch.int32)
tensor([[ 0],
  [ 1],
  [ 2]], dtype=torch.int32)
tensor([[ 3, 4, 5],
  [ 4, 5, 6],
  [ 5, 6, 7]], dtype=torch.int32)
tensor([[ 3],
  [ 4],
  [ 5]], dtype=torch.int32)
tensor([[ 6, 7, 8],
  [ 7, 8, 9],
  [ 8, 9, 10]], dtype=torch.int32)
tensor([[ 6],
  [ 7],
  [ 8]], dtype=torch.int32)
tensor([[ 9, 10, 11]], dtype=torch.int32)
tensor([[ 9]], dtype=torch.int32)

collate_fn=lambda x:x

for i in loader:
 print(i)

[(tensor([ 0, 1, 2], dtype=torch.int32), tensor([ 0], dtype=torch.int32)), (tensor([ 1, 2, 3], dtype=torch.int32), tensor([ 1], dtype=torch.int32)), (tensor([ 2, 3, 4], dtype=torch.int32), tensor([ 2], dtype=torch.int32))]
[(tensor([ 3, 4, 5], dtype=torch.int32), tensor([ 3], dtype=torch.int32)), (tensor([ 4, 5, 6], dtype=torch.int32), tensor([ 4], dtype=torch.int32)), (tensor([ 5, 6, 7], dtype=torch.int32), tensor([ 5], dtype=torch.int32))]
[(tensor([ 6, 7, 8], dtype=torch.int32), tensor([ 6], dtype=torch.int32)), (tensor([ 7, 8, 9], dtype=torch.int32), tensor([ 7], dtype=torch.int32)), (tensor([ 8, 9, 10], dtype=torch.int32), tensor([ 8], dtype=torch.int32))]
[(tensor([ 9, 10, 11], dtype=torch.int32), tensor([ 9], dtype=torch.int32))]

collate_fn=lambda x:(
 torch.cat(
  [x[i][j].unsqueeze(0) for i in range(len(x))], 0
  ).unsqueeze(0) for j in range(len(x[0]))
 )