Spaces:
Sleeping
Sleeping
| """ | |
| Copyright (c) 2022, salesforce.com, inc. | |
| All rights reserved. | |
| SPDX-License-Identifier: BSD-3-Clause | |
| For full license text, see the LICENSE file in the repo root or https://opensource.org/licenses/BSD-3-Clause | |
| Based on https://github.com/facebookresearch/TimeSformer | |
| """ | |
| # Copyright 2020 Ross Wightman | |
| # Conv2d w/ Same Padding | |
| import torch | |
| import torch.nn as nn | |
| import torch.nn.functional as F | |
| from typing import Tuple, Optional | |
| import math | |
| from typing import List, Tuple | |
| from .vit_utils import is_static_pad, get_padding | |
| # Dynamically pad input x with 'SAME' padding for conv with specified args | |
| def pad_same(x, k: List[int], s: List[int], d: List[int] = (1, 1), value: float = 0): | |
| ih, iw = x.size()[-2:] | |
| pad_h, pad_w = get_same_padding(ih, k[0], s[0], d[0]), get_same_padding( | |
| iw, k[1], s[1], d[1] | |
| ) | |
| if pad_h > 0 or pad_w > 0: | |
| x = F.pad( | |
| x, | |
| [pad_w // 2, pad_w - pad_w // 2, pad_h // 2, pad_h - pad_h // 2], | |
| value=value, | |
| ) | |
| return x | |
| # Calculate asymmetric TensorFlow-like 'SAME' padding for a convolution | |
| def get_same_padding(x: int, k: int, s: int, d: int): | |
| return max((math.ceil(x / s) - 1) * s + (k - 1) * d + 1 - x, 0) | |
| def get_padding_value(padding, kernel_size, **kwargs) -> Tuple[Tuple, bool]: | |
| dynamic = False | |
| if isinstance(padding, str): | |
| # for any string padding, the padding will be calculated for you, one of three ways | |
| padding = padding.lower() | |
| if padding == "same": | |
| # TF compatible 'SAME' padding, has a performance and GPU memory allocation impact | |
| if is_static_pad(kernel_size, **kwargs): | |
| # static case, no extra overhead | |
| padding = get_padding(kernel_size, **kwargs) | |
| else: | |
| # dynamic 'SAME' padding, has runtime/GPU memory overhead | |
| padding = 0 | |
| dynamic = True | |
| elif padding == "valid": | |
| # 'VALID' padding, same as padding=0 | |
| padding = 0 | |
| else: | |
| # Default to PyTorch style 'same'-ish symmetric padding | |
| padding = get_padding(kernel_size, **kwargs) | |
| return padding, dynamic | |
| def conv2d_same( | |
| x, | |
| weight: torch.Tensor, | |
| bias: Optional[torch.Tensor] = None, | |
| stride: Tuple[int, int] = (1, 1), | |
| padding: Tuple[int, int] = (0, 0), | |
| dilation: Tuple[int, int] = (1, 1), | |
| groups: int = 1, | |
| ): | |
| x = pad_same(x, weight.shape[-2:], stride, dilation) | |
| return F.conv2d(x, weight, bias, stride, (0, 0), dilation, groups) | |
| class Conv2dSame(nn.Conv2d): | |
| """Tensorflow like 'SAME' convolution wrapper for 2D convolutions""" | |
| def __init__( | |
| self, | |
| in_channels, | |
| out_channels, | |
| kernel_size, | |
| stride=1, | |
| padding=0, | |
| dilation=1, | |
| groups=1, | |
| bias=True, | |
| ): | |
| super(Conv2dSame, self).__init__( | |
| in_channels, out_channels, kernel_size, stride, 0, dilation, groups, bias | |
| ) | |
| def forward(self, x): | |
| return conv2d_same( | |
| x, | |
| self.weight, | |
| self.bias, | |
| self.stride, | |
| self.padding, | |
| self.dilation, | |
| self.groups, | |
| ) | |
| def create_conv2d_pad(in_chs, out_chs, kernel_size, **kwargs): | |
| padding = kwargs.pop("padding", "") | |
| kwargs.setdefault("bias", False) | |
| padding, is_dynamic = get_padding_value(padding, kernel_size, **kwargs) | |
| if is_dynamic: | |
| return Conv2dSame(in_chs, out_chs, kernel_size, **kwargs) | |
| else: | |
| return nn.Conv2d(in_chs, out_chs, kernel_size, padding=padding, **kwargs) | |