[BUG] `ConvNet` memory issues about rl HOT 5 CLOSED

import torch
import torchrl
import sys

input = torch.rand((1, 1000, 7, 3, 88, 88), dtype=torch.float32, device="meta")
print(sys.getsizeof(input.storage())/ 1_000_000, " MB") # This prints 650.496048  MB

net = torchrl.modules.ConvNet(in_features=3)
print(net(input).shape)

output = torch.rand((1, 1000, 7, 215168), dtype=torch.float32)
print(sys.getsizeof(output.storage()) / 1_000_000, " MB") # 6024.704048  MB

import torch
import torchrl
import sys

input = torch.rand((1, 1000, 7, 3, 88, 88), dtype=torch.float32)
print(sys.getsizeof(input.storage())/ 1_000_000, " MB") # This prints 650.496048  MB

net = torchrl.modules.ConvNet(in_features=3)
with torch.no_grad():
    print(net(input).shape)