EasyCV/thirdparty/mtcnn/get_nets.py

from os import path
import os
import torch
import torch.nn as nn
import torch.nn.functional as F
from collections import OrderedDict
import numpy as np

from io import BytesIO
from urllib import request

class Flatten(nn.Module):
    def __init__(self):
        super(Flatten, self).__init__()

    def forward(self, x):
        """
        Arguments:
            x: a float tensor with shape [batch_size, c, h, w].
        Returns:
            a float tensor with shape [batch_size, c*h*w].
        """

        # without this pretrained model isn't working
        x = x.transpose(3, 2).contiguous()

        return x.view(x.size(0), -1)

def get_url_weights(path, dir_path ,url_index="http://pai-vision-data-hz.oss-cn-zhangjiakou.aliyuncs.com/release/mtcnn/"):
    wpath = os.path.join(dir_path, path)
    if os.path.exists(wpath):
        weights = np.load(wpath, allow_pickle=True)[
            ()
        ]
    else:
        try:
            s = request.urlopen(os.path.join(url_index, path)).read()
            m = BytesIO(s)
            weights = np.load(m, allow_pickle=True).item()
        except:
            print("Failed to load %s from %s, please ensure access to %s  or provide face detector model !"%(path, os.path.join(url_index, path, path)))
            weights = None
    
    if weights is not None:
        print("load weight from %s / %s success!"%(wpath, os.path.join(url_index, path) ))
    
    return weights




class PNet(nn.Module):
    def __init__(self, dir_path=None):

        super(PNet, self).__init__()

        # suppose we have input with size HxW, then
        # after first layer: H - 2,
        # after pool: ceil((H - 2)/2),
        # after second conv: ceil((H - 2)/2) - 2,
        # after last conv: ceil((H - 2)/2) - 4,
        # and the same for W

        self.features = nn.Sequential(
            OrderedDict(
                [
                    ("conv1", nn.Conv2d(3, 10, 3, 1)),
                    ("prelu1", nn.PReLU(10)),
                    ("pool1", nn.MaxPool2d(2, 2, ceil_mode=True)),
                    ("conv2", nn.Conv2d(10, 16, 3, 1)),
                    ("prelu2", nn.PReLU(16)),
                    ("conv3", nn.Conv2d(16, 32, 3, 1)),
                    ("prelu3", nn.PReLU(32)),
                ]
            )
        )

        self.conv4_1 = nn.Conv2d(32, 2, 1, 1)
        self.conv4_2 = nn.Conv2d(32, 4, 1, 1)

        if dir_path is None:
            dir_path = path.dirname(__file__)
        
        weights = get_url_weights("weights/pnet.npy", dir_path)

        for n, p in self.named_parameters():
            p.data = torch.FloatTensor(weights[n])

    def forward(self, x):
        """
        Arguments:
            x: a float tensor with shape [batch_size, 3, h, w].
        Returns:
            b: a float tensor with shape [batch_size, 4, h', w'].
            a: a float tensor with shape [batch_size, 2, h', w'].
        """
        x = self.features(x)
        a = self.conv4_1(x)
        b = self.conv4_2(x)
        a = F.softmax(a, dim=1)
        return b, a


class RNet(nn.Module):
    def __init__(self, dir_path=None):

        super(RNet, self).__init__()

        self.features = nn.Sequential(
            OrderedDict(
                [
                    ("conv1", nn.Conv2d(3, 28, 3, 1)),
                    ("prelu1", nn.PReLU(28)),
                    ("pool1", nn.MaxPool2d(3, 2, ceil_mode=True)),
                    ("conv2", nn.Conv2d(28, 48, 3, 1)),
                    ("prelu2", nn.PReLU(48)),
                    ("pool2", nn.MaxPool2d(3, 2, ceil_mode=True)),
                    ("conv3", nn.Conv2d(48, 64, 2, 1)),
                    ("prelu3", nn.PReLU(64)),
                    ("flatten", Flatten()),
                    ("conv4", nn.Linear(576, 128)),
                    ("prelu4", nn.PReLU(128)),
                ]
            )
        )

        self.conv5_1 = nn.Linear(128, 2)
        self.conv5_2 = nn.Linear(128, 4)

        if dir_path is None:
            dir_path = path.dirname(__file__)
        weights = get_url_weights("weights/rnet.npy", dir_path)

        for n, p in self.named_parameters():
            p.data = torch.FloatTensor(weights[n])

    def forward(self, x):
        """
        Arguments:
            x: a float tensor with shape [batch_size, 3, h, w].
        Returns:
            b: a float tensor with shape [batch_size, 4].
            a: a float tensor with shape [batch_size, 2].
        """
        x = self.features(x)
        a = self.conv5_1(x)
        b = self.conv5_2(x)
        a = F.softmax(a, dim=1)
        return b, a


class ONet(nn.Module):
    def __init__(self, dir_path=None):

        super(ONet, self).__init__()

        self.features = nn.Sequential(
            OrderedDict(
                [
                    ("conv1", nn.Conv2d(3, 32, 3, 1)),
                    ("prelu1", nn.PReLU(32)),
                    ("pool1", nn.MaxPool2d(3, 2, ceil_mode=True)),
                    ("conv2", nn.Conv2d(32, 64, 3, 1)),
                    ("prelu2", nn.PReLU(64)),
                    ("pool2", nn.MaxPool2d(3, 2, ceil_mode=True)),
                    ("conv3", nn.Conv2d(64, 64, 3, 1)),
                    ("prelu3", nn.PReLU(64)),
                    ("pool3", nn.MaxPool2d(2, 2, ceil_mode=True)),
                    ("conv4", nn.Conv2d(64, 128, 2, 1)),
                    ("prelu4", nn.PReLU(128)),
                    ("flatten", Flatten()),
                    ("conv5", nn.Linear(1152, 256)),
                    ("drop5", nn.Dropout(0.25)),
                    ("prelu5", nn.PReLU(256)),
                ]
            )
        )

        self.conv6_1 = nn.Linear(256, 2)
        self.conv6_2 = nn.Linear(256, 4)
        self.conv6_3 = nn.Linear(256, 10)
        
        if dir_path is None:
            dir_path = path.dirname(__file__)
        weights = get_url_weights("weights/onet.npy", dir_path)
    
        for n, p in self.named_parameters():
            p.data = torch.FloatTensor(weights[n])

    def forward(self, x):
        """
        Arguments:
            x: a float tensor with shape [batch_size, 3, h, w].
        Returns:
            c: a float tensor with shape [batch_size, 10].
            b: a float tensor with shape [batch_size, 4].
            a: a float tensor with shape [batch_size, 2].
        """
        x = self.features(x)
        a = self.conv6_1(x)
        b = self.conv6_2(x)
        c = self.conv6_3(x)
        a = F.softmax(a, dim=1)
        return c, b, a