Is there a better way to do this? How to pad tensor with zeros, without creating new tensor object? I need inputs to be of the same batchsize all the time, so I want to pad inputs that are smaller than batchsize with zeros. Like padding zeros in NLP when sequence length is shorter, but this is padding for batch.
Currently, I created a new tensor, but because of that, my GPU will go out of memory. I don’t want to reduce batchsize by half to handle this operation.
import torch
from torch import nn
class MyModel(nn.Module):
def __init__(self, batchsize=16):
super().__init__()
self.batchsize = batchsize
def forward(self, x):
b, d = x.shape
print(x.shape) # torch.Size([7, 32])
if b != self.batchsize: # 2. I need batches to be of size 16, if batch isn't 16, I want to pad the rest to zero
new_x = torch.zeros(self.batchsize,d) # 3. so I create a new tensor, but this is bad as it increase the GPU memory required greatly
new_x[0:b,:] = x
x = new_x
b = self.batchsize
print(x.shape) # torch.Size([16, 32])
return x
model = MyModel()
x = torch.randn((7, 32)) # 1. shape's batch is 7, because this is last batch, and I dont want to "drop_last"
y = model(x)
print(y.shape)