nn.AdaptiveAvgPool2d does not accept 3D jt.Var

[PREPONDERANCE]

Describe the bug

A clear and concise description of what the bug is. 使用中文也可以。

As the title suggests, nn.AdaptiveAvgPool2d does not accept 3D jittor.Var as opposed to torch.nn.functional.adaptive_avg_pool_2d.

Full Log

Provide a full log of Jittor execution, Jittor will log environment information which help us to locate your bugs. Provide a screenshot is also acceptable.

Traceback (most recent call last):
  File "/home/ubuntu/miniconda3/envs/hint/lib/python3.8/runpy.py", line 194, in _run_module_as_main
    return _run_code(code, main_globals, None,
  File "/home/ubuntu/miniconda3/envs/hint/lib/python3.8/runpy.py", line 87, in _run_code
    exec(code, run_globals)
  File "/home/ubuntu/code/Hint/test.py", line 8, in <module>
    print(pool(x))
  File "/home/ubuntu/miniconda3/envs/hint/lib/python3.8/site-packages/jittor/__init__.py", line 1211, in __call__
    return self.execute(*args, **kw)
  File "/home/ubuntu/miniconda3/envs/hint/lib/python3.8/site-packages/jittor/pool.py", line 420, in execute
    N,C,H,W = x.shape
ValueError: not enough values to unpack (expected 4, got 3)

Minimal Reproduce

Reproduce this error with a file or several lines of code.
If it is not possible, leave it blank.

import jittor as jt
from jittor import nn


pool = nn.AdaptiveAvgPool2d(256)
x = jt.randn(3, 16, 16)

print(pool(x))

Expected behavior

A clear and concise description of what you expected to happen.

Accept 3D jt.Var

If you are submitting an issue for the first time, please refer to our guideline