PytorchOCR/torchocr/networks/backbones/ConvNext.py

from functools import partial
import logging
import os

import torch
import torch.nn as nn
import torch.nn.functional as F
from torchocr.networks.backbones.Transformer import DropPath


class Block(nn.Module):
    r""" ConvNeXt Block. There are two equivalent implementations:
    (1) DwConv -> LayerNorm (channels_first) -> 1x1 Conv -> GELU -> 1x1 Conv; all in (N, C, H, W)
    (2) DwConv -> Permute to (N, H, W, C); LayerNorm (channels_last) -> Linear -> GELU -> Linear; Permute back
    We use (2) as we find it slightly faster in PyTorch

    Args:
        dim (int): Number of input channels.
        drop_path (float): Stochastic depth rate. Default: 0.0
        layer_scale_init_value (float): Init value for Layer Scale. Default: 1e-6.
    """

    def __init__(self, dim, drop_path=0., layer_scale_init_value=1e-6):
        super().__init__()
        self.dwconv = nn.Conv2d(dim, dim, kernel_size=7, padding=3, groups=dim)  # depthwise conv
        self.norm = LayerNorm(dim, eps=1e-6)
        self.pwconv1 = nn.Linear(dim, 4 * dim)  # pointwise/1x1 convs, implemented with linear layers
        self.act = nn.GELU()
        self.pwconv2 = nn.Linear(4 * dim, dim)
        self.gamma = nn.Parameter(layer_scale_init_value * torch.ones((dim)),
                                  requires_grad=True) if layer_scale_init_value > 0 else None
        self.drop_path = DropPath(drop_path) if drop_path > 0. else nn.Identity()

    def forward(self, x):
        input = x
        x = self.dwconv(x)
        x = x.permute(0, 2, 3, 1)  # (N, C, H, W) -> (N, H, W, C)
        x = self.norm(x)
        x = self.pwconv1(x)
        x = self.act(x)
        x = self.pwconv2(x)
        if self.gamma is not None:
            x = self.gamma * x
        x = x.permute(0, 3, 1, 2)  # (N, H, W, C) -> (N, C, H, W)

        x = input + self.drop_path(x)
        return x


class ConvNeXt(nn.Module):
    r""" ConvNeXt
        A PyTorch impl of : `A ConvNet for the 2020s`  -
          https://arxiv.org/pdf/2201.03545.pdf
    Args:
        in_chans (int): Number of input image channels. Default: 3
        num_classes (int): Number of classes for classification head. Default: 1000
        depths (tuple(int)): Number of blocks at each stage. Default: [3, 3, 9, 3]
        dims (int): Feature dimension at each stage. Default: [96, 192, 384, 768]
        drop_path_rate (float): Stochastic depth rate. Default: 0.
        layer_scale_init_value (float): Init value for Layer Scale. Default: 1e-6.
        head_init_scale (float): Init scaling value for classifier weights and biases. Default: 1.
    """

    def __init__(self, in_chans=3, depths=[3, 3, 9, 3], dims=[96, 192, 384, 768],
                 drop_path_rate=0.4, layer_scale_init_value=1.0, out_indices=[0, 1, 2, 3], **kwargs
                 ):
        super().__init__()

        self.downsample_layers = nn.ModuleList()  # stem and 3 intermediate downsampling conv layers
        stem = nn.Sequential(
            nn.Conv2d(in_chans, dims[0], kernel_size=4, stride=4),
            LayerNorm(dims[0], eps=1e-6, data_format="channels_first")
        )
        self.downsample_layers.append(stem)
        for i in range(3):
            downsample_layer = nn.Sequential(
                LayerNorm(dims[i], eps=1e-6, data_format="channels_first"),
                nn.Conv2d(dims[i], dims[i + 1], kernel_size=2, stride=2),
            )
            self.downsample_layers.append(downsample_layer)

        self.stages = nn.ModuleList()  # 4 feature resolution stages, each consisting of multiple residual blocks
        self.pretrained = kwargs.get('pretrained', True)
        dp_rates = [x.item() for x in torch.linspace(0, drop_path_rate, sum(depths))]
        self.out_channels = [96, 192, 384, 768]
        cur = 0
        for i in range(4):
            stage = nn.Sequential(
                *[Block(dim=dims[i], drop_path=dp_rates[cur + j],
                        layer_scale_init_value=layer_scale_init_value) for j in range(depths[i])]
            )
            self.stages.append(stage)
            cur += depths[i]

        self.out_indices = out_indices

        norm_layer = partial(LayerNorm, eps=1e-6, data_format="channels_first")
        for i_layer in range(4):
            layer = norm_layer(dims[i_layer])
            layer_name = f'norm{i_layer}'
            self.add_module(layer_name, layer)

        if self.pretrained:
            ckpt_path = f'./weights/convnext_tiny_1k_512x512.pth'
            logger = logging.getLogger('torchocr')
            if os.path.exists(ckpt_path):
                logger.info('load convnext weights')
                self.load_state_dict(torch.load(ckpt_path), strict=True)
            else:
                logger.info(f'{ckpt_path} not exists')
                self.apply(self._init_weights)
        else:
            self.apply(self._init_weights)

    def _init_weights(self, m):
        if isinstance(m, nn.Linear):
            nn.init.trunc_normal_(m.weight, std=.02)
            if isinstance(m, nn.Linear) and m.bias is not None:
                nn.init.constant_(m.bias, 0)
        elif isinstance(m, nn.LayerNorm):
            nn.init.constant_(m.bias, 0)
            nn.init.constant_(m.weight, 1.0)

    def forward_features(self, x):
        outs = []
        for i in range(4):
            x = self.downsample_layers[i](x)
            x = self.stages[i](x)
            if i in self.out_indices:
                norm_layer = getattr(self, f'norm{i}')
                x_out = norm_layer(x)
                outs.append(x_out)

        return tuple(outs)

    def forward(self, x):
        x = self.forward_features(x)
        return x


class LayerNorm(nn.Module):
    r""" LayerNorm that supports two data formats: channels_last (default) or channels_first.
    The ordering of the dimensions in the inputs. channels_last corresponds to inputs with
    shape (batch_size, height, width, channels) while channels_first corresponds to inputs
    with shape (batch_size, channels, height, width).
    """

    def __init__(self, normalized_shape, eps=1e-6, data_format="channels_last"):
        super().__init__()
        self.weight = nn.Parameter(torch.ones(normalized_shape))
        self.bias = nn.Parameter(torch.zeros(normalized_shape))
        self.eps = eps
        self.data_format = data_format
        if self.data_format not in ["channels_last", "channels_first"]:
            raise NotImplementedError
        self.normalized_shape = (normalized_shape,)

    def forward(self, x):
        if self.data_format == "channels_last":
            return F.layer_norm(x, self.normalized_shape, self.weight, self.bias, self.eps)
        elif self.data_format == "channels_first":
            u = x.mean(1, keepdim=True)
            s = (x - u).pow(2).mean(1, keepdim=True)
            x = (x - u) / torch.sqrt(s + self.eps)
            x = self.weight[:, None, None] * x + self.bias[:, None, None]
            return x