modules/cnet_modules/face_id/arcface.py

import numpy as np
import onnx, onnx2torch, cv2
import torch
from insightface.utils import face_align


class ArcFaceRecognizer:
    def __init__(self, model_file=None, device='cpu', dtype=torch.float32):
        assert model_file is not None
        self.model_file = model_file

        self.device = device
        self.dtype = dtype
        self.model = onnx2torch.convert(onnx.load(model_file)).to(device=device, dtype=dtype)
        for param in self.model.parameters():
            param.requires_grad = False
        self.model.eval()

        self.input_mean = 127.5
        self.input_std = 127.5
        self.input_size = (112, 112)
        self.input_shape = ['None', 3, 112, 112]

    def get(self, img, face):
        aimg = face_align.norm_crop(img, landmark=face.kps, image_size=self.input_size[0])
        face.embedding = self.get_feat(aimg).flatten()
        return face.embedding

    def compute_sim(self, feat1, feat2):
        from numpy.linalg import norm
        feat1 = feat1.ravel()
        feat2 = feat2.ravel()
        sim = np.dot(feat1, feat2) / (norm(feat1) * norm(feat2))
        return sim

    def get_feat(self, imgs):
        if not isinstance(imgs, list):
            imgs = [imgs]
        input_size = self.input_size

        blob = cv2.dnn.blobFromImages(imgs, 1.0 / self.input_std, input_size,
                                      (self.input_mean, self.input_mean, self.input_mean), swapRB=True)

        blob_torch = torch.tensor(blob).to(device=self.device, dtype=self.dtype)
        net_out = self.model(blob_torch)
        return net_out[0].float().cpu()


def distance2bbox(points, distance, max_shape=None):
    """Decode distance prediction to bounding box.

    Args:
        points (Tensor): Shape (n, 2), [x, y].
        distance (Tensor): Distance from the given point to 4
            boundaries (left, top, right, bottom).
        max_shape (tuple): Shape of the image.

    Returns:
        Tensor: Decoded bboxes.
    """
    x1 = points[:, 0] - distance[:, 0]
    y1 = points[:, 1] - distance[:, 1]
    x2 = points[:, 0] + distance[:, 2]
    y2 = points[:, 1] + distance[:, 3]
    if max_shape is not None:
        x1 = x1.clamp(min=0, max=max_shape[1])
        y1 = y1.clamp(min=0, max=max_shape[0])
        x2 = x2.clamp(min=0, max=max_shape[1])
        y2 = y2.clamp(min=0, max=max_shape[0])
    return np.stack([x1, y1, x2, y2], axis=-1)


def distance2kps(points, distance, max_shape=None):
    """Decode distance prediction to bounding box.

    Args:
        points (Tensor): Shape (n, 2), [x, y].
        distance (Tensor): Distance from the given point to 4
            boundaries (left, top, right, bottom).
        max_shape (tuple): Shape of the image.

    Returns:
        Tensor: Decoded bboxes.
    """
    preds = []
    for i in range(0, distance.shape[1], 2):
        px = points[:, i % 2] + distance[:, i]
        py = points[:, i % 2 + 1] + distance[:, i + 1]
        if max_shape is not None:
            px = px.clamp(min=0, max=max_shape[1])
            py = py.clamp(min=0, max=max_shape[0])
        preds.append(px)
        preds.append(py)
    return np.stack(preds, axis=-1)


class FaceDetector:
    def __init__(self, model_file=None, dtype=torch.float32, device='cuda'):
        self.model_file = model_file
        self.taskname = 'detection'
        self.center_cache = {}
        self.nms_thresh = 0.4
        self.det_thresh = 0.5

        self.device = device
        self.dtype = dtype
        self.model = onnx2torch.convert(onnx.load(model_file)).to(device=device, dtype=dtype)
        for param in self.model.parameters():
            param.requires_grad = False
        self.model.eval()

        input_shape = (320, 320)
        self.input_size = input_shape
        self.input_shape = input_shape

        self.input_mean = 127.5
        self.input_std = 128.0
        self._anchor_ratio = 1.0
        self._num_anchors = 1
        self.fmc = 3
        self._feat_stride_fpn = [8, 16, 32]
        self._num_anchors = 2
        self.use_kps = True

        self.det_thresh = 0.5
        self.nms_thresh = 0.4

    def forward(self, img, threshold):
        scores_list = []
        bboxes_list = []
        kpss_list = []
        input_size = tuple(img.shape[0:2][::-1])
        blob = cv2.dnn.blobFromImage(img, 1.0 / self.input_std, input_size,
                                     (self.input_mean, self.input_mean, self.input_mean), swapRB=True)
        blob_torch = torch.tensor(blob).to(device=self.device, dtype=self.dtype)
        net_outs_torch = self.model(blob_torch)
        # print(list(map(lambda x: x.shape, net_outs_torch)))
        net_outs = list(map(lambda x: x.float().cpu().numpy(), net_outs_torch))

        input_height = blob.shape[2]
        input_width = blob.shape[3]
        fmc = self.fmc
        for idx, stride in enumerate(self._feat_stride_fpn):
            scores = net_outs[idx]
            bbox_preds = net_outs[idx + fmc]
            bbox_preds = bbox_preds * stride
            if self.use_kps:
                kps_preds = net_outs[idx + fmc * 2] * stride
            height = input_height // stride
            width = input_width // stride
            K = height * width
            key = (height, width, stride)
            if key in self.center_cache:
                anchor_centers = self.center_cache[key]
            else:
                # solution-1, c style:
                # anchor_centers = np.zeros( (height, width, 2), dtype=np.float32 )
                # for i in range(height):
                #    anchor_centers[i, :, 1] = i
                # for i in range(width):
                #    anchor_centers[:, i, 0] = i

                # solution-2:
                # ax = np.arange(width, dtype=np.float32)
                # ay = np.arange(height, dtype=np.float32)
                # xv, yv = np.meshgrid(np.arange(width), np.arange(height))
                # anchor_centers = np.stack([xv, yv], axis=-1).astype(np.float32)

                # solution-3:
                anchor_centers = np.stack(np.mgrid[:height, :width][::-1], axis=-1).astype(np.float32)
                # print(anchor_centers.shape)

                anchor_centers = (anchor_centers * stride).reshape((-1, 2))
                if self._num_anchors > 1:
                    anchor_centers = np.stack([anchor_centers] * self._num_anchors, axis=1).reshape((-1, 2))
                if len(self.center_cache) < 100:
                    self.center_cache[key] = anchor_centers

            pos_inds = np.where(scores >= threshold)[0]
            bboxes = distance2bbox(anchor_centers, bbox_preds)
            pos_scores = scores[pos_inds]
            pos_bboxes = bboxes[pos_inds]
            scores_list.append(pos_scores)
            bboxes_list.append(pos_bboxes)
            if self.use_kps:
                kpss = distance2kps(anchor_centers, kps_preds)
                # kpss = kps_preds
                kpss = kpss.reshape((kpss.shape[0], -1, 2))
                pos_kpss = kpss[pos_inds]
                kpss_list.append(pos_kpss)
        return scores_list, bboxes_list, kpss_list

    def detect(self, img, input_size=None, max_num=0, metric='default'):
        assert input_size is not None or self.input_size is not None
        input_size = self.input_size if input_size is None else input_size

        im_ratio = float(img.shape[0]) / img.shape[1]
        model_ratio = float(input_size[1]) / input_size[0]
        if im_ratio > model_ratio:
            new_height = input_size[1]
            new_width = int(new_height / im_ratio)
        else:
            new_width = input_size[0]
            new_height = int(new_width * im_ratio)
        det_scale = float(new_height) / img.shape[0]
        resized_img = cv2.resize(img, (new_width, new_height))
        det_img = np.zeros((input_size[1], input_size[0], 3), dtype=np.uint8)
        det_img[:new_height, :new_width, :] = resized_img

        scores_list, bboxes_list, kpss_list = self.forward(det_img, self.det_thresh)

        scores = np.vstack(scores_list)
        scores_ravel = scores.ravel()
        order = scores_ravel.argsort()[::-1]
        bboxes = np.vstack(bboxes_list) / det_scale
        if self.use_kps:
            kpss = np.vstack(kpss_list) / det_scale
        pre_det = np.hstack((bboxes, scores)).astype(np.float32, copy=False)
        pre_det = pre_det[order, :]
        keep = self.nms(pre_det)
        det = pre_det[keep, :]
        if self.use_kps:
            kpss = kpss[order, :, :]
            kpss = kpss[keep, :, :]
        else:
            kpss = None
        if max_num > 0 and det.shape[0] > max_num:
            area = (det[:, 2] - det[:, 0]) * (det[:, 3] -
                                              det[:, 1])
            img_center = img.shape[0] // 2, img.shape[1] // 2
            offsets = np.vstack([
                (det[:, 0] + det[:, 2]) / 2 - img_center[1],
                (det[:, 1] + det[:, 3]) / 2 - img_center[0]
            ])
            offset_dist_squared = np.sum(np.power(offsets, 2.0), 0)
            if metric == 'max':
                values = area
            else:
                values = area - offset_dist_squared * 2.0  # some extra weight on the centering
            bindex = np.argsort(
                values)[::-1]  # some extra weight on the centering
            bindex = bindex[0:max_num]
            det = det[bindex, :]
            if kpss is not None:
                kpss = kpss[bindex, :]
        return det, kpss

    def nms(self, dets):
        thresh = self.nms_thresh
        x1 = dets[:, 0]
        y1 = dets[:, 1]
        x2 = dets[:, 2]
        y2 = dets[:, 3]
        scores = dets[:, 4]

        areas = (x2 - x1 + 1) * (y2 - y1 + 1)
        order = scores.argsort()[::-1]

        keep = []
        while order.size > 0:
            i = order[0]
            keep.append(i)
            xx1 = np.maximum(x1[i], x1[order[1:]])
            yy1 = np.maximum(y1[i], y1[order[1:]])
            xx2 = np.minimum(x2[i], x2[order[1:]])
            yy2 = np.minimum(y2[i], y2[order[1:]])

            w = np.maximum(0.0, xx2 - xx1 + 1)
            h = np.maximum(0.0, yy2 - yy1 + 1)
            inter = w * h
            ovr = inter / (areas[i] + areas[order[1:]] - inter)

            inds = np.where(ovr <= thresh)[0]
            order = order[inds + 1]

        return keep