diff --git a/examples/CMakeLists.txt b/examples/CMakeLists.txt
index 534bb6238..97423caad 100644
--- a/examples/CMakeLists.txt
+++ b/examples/CMakeLists.txt
@@ -61,6 +61,7 @@ if(NCNN_PIXEL)
         ncnn_add_example(yolact)
         ncnn_add_example(nanodet)
         ncnn_add_example(scrfd)
+        ncnn_add_example(scrfd_crowdhuman)
         ncnn_add_example(rvm)
     else()
         message(WARNING "OpenCV not found and NCNN_SIMPLEOCV disabled, examples won't be built")
diff --git a/examples/scrfd_crowdhuman.cpp b/examples/scrfd_crowdhuman.cpp
new file mode 100644
index 000000000..067c0fafa
--- /dev/null
+++ b/examples/scrfd_crowdhuman.cpp
@@ -0,0 +1,471 @@
+// Tencent is pleased to support the open source community by making ncnn available.
+//
+// Copyright (C) 2021 THL A29 Limited, a Tencent company. All rights reserved.
+//
+// Licensed under the BSD 3-Clause License (the "License"); you may not use this file except
+// in compliance with the License. You may obtain a copy of the License at
+//
+// https://opensource.org/licenses/BSD-3-Clause
+//
+// Unless required by applicable law or agreed to in writing, software distributed
+// under the License is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR
+// CONDITIONS OF ANY KIND, either express or implied. See the License for the
+// specific language governing permissions and limitations under the License.
+
+#include "net.h"
+
+#if defined(USE_NCNN_SIMPLEOCV)
+#include "simpleocv.h"
+#else
+#include <opencv2/core/core.hpp>
+#include <opencv2/highgui/highgui.hpp>
+#include <opencv2/imgproc/imgproc.hpp>
+#endif
+#include <stdio.h>
+#include <vector>
+
+struct FaceObject
+{
+    cv::Rect_<float> rect;
+    float prob;
+};
+
+static inline float intersection_area(const FaceObject& a, const FaceObject& b)
+{
+    cv::Rect_<float> inter = a.rect & b.rect;
+    return inter.area();
+}
+
+static void qsort_descent_inplace(std::vector<FaceObject>& faceobjects, int left, int right)
+{
+    int i = left;
+    int j = right;
+    float p = faceobjects[(left + right) / 2].prob;
+
+    while (i <= j)
+    {
+        while (faceobjects[i].prob > p)
+            i++;
+
+        while (faceobjects[j].prob < p)
+            j--;
+
+        if (i <= j)
+        {
+            // swap
+            std::swap(faceobjects[i], faceobjects[j]);
+
+            i++;
+            j--;
+        }
+    }
+
+    #pragma omp parallel sections
+    {
+        #pragma omp section
+        {
+            if (left < j) qsort_descent_inplace(faceobjects, left, j);
+        }
+        #pragma omp section
+        {
+            if (i < right) qsort_descent_inplace(faceobjects, i, right);
+        }
+    }
+}
+
+static void qsort_descent_inplace(std::vector<FaceObject>& faceobjects)
+{
+    if (faceobjects.empty())
+        return;
+
+    qsort_descent_inplace(faceobjects, 0, faceobjects.size() - 1);
+}
+
+static void nms_sorted_bboxes(const std::vector<FaceObject>& faceobjects, std::vector<int>& picked, float nms_threshold)
+{
+    picked.clear();
+
+    const int n = faceobjects.size();
+
+    std::vector<float> areas(n);
+    for (int i = 0; i < n; i++)
+    {
+        areas[i] = faceobjects[i].rect.area();
+    }
+
+    for (int i = 0; i < n; i++)
+    {
+        const FaceObject& a = faceobjects[i];
+
+        int keep = 1;
+        for (int j = 0; j < (int)picked.size(); j++)
+        {
+            const FaceObject& b = faceobjects[picked[j]];
+
+            // intersection over union
+            float inter_area = intersection_area(a, b);
+            float union_area = areas[i] + areas[picked[j]] - inter_area;
+            //             float IoU = inter_area / union_area
+            if (inter_area / union_area > nms_threshold)
+                keep = 0;
+        }
+
+        if (keep)
+            picked.push_back(i);
+    }
+}
+
+// insightface/detection/scrfd/mmdet/core/anchor/anchor_generator.py gen_single_level_base_anchors()
+static ncnn::Mat generate_anchors(int base_size, const ncnn::Mat& ratios, const ncnn::Mat& scales)
+{
+    int num_ratio = ratios.w;
+    int num_scale = scales.w;
+
+    ncnn::Mat anchors;
+    anchors.create(4, num_ratio * num_scale);
+
+    const float cx = 0;
+    const float cy = 0;
+
+    for (int i = 0; i < num_ratio; i++)
+    {
+        float ar = ratios[i];
+
+        int r_w = round(base_size / sqrt(ar));
+        int r_h = round(r_w * ar); //round(base_size * sqrt(ar));
+
+        for (int j = 0; j < num_scale; j++)
+        {
+            float scale = scales[j];
+
+            float rs_w = r_w * scale;
+            float rs_h = r_h * scale;
+
+            float* anchor = anchors.row(i * num_scale + j);
+
+            anchor[0] = cx - rs_w * 0.5f;
+            anchor[1] = cy - rs_h * 0.5f;
+            anchor[2] = cx + rs_w * 0.5f;
+            anchor[3] = cy + rs_h * 0.5f;
+        }
+    }
+
+    return anchors;
+}
+
+static void generate_proposals(const ncnn::Mat& anchors, int feat_stride, const ncnn::Mat& score_blob, const ncnn::Mat& bbox_blob, float prob_threshold, std::vector<FaceObject>& faceobjects)
+{
+    int w = score_blob.w;
+    int h = score_blob.h;
+
+    // generate face proposal from bbox deltas and shifted anchors
+    const int num_anchors = anchors.h;
+
+    for (int q = 0; q < num_anchors; q++)
+    {
+        const float* anchor = anchors.row(q);
+
+        const ncnn::Mat score = score_blob.channel(q);
+        const ncnn::Mat bbox = bbox_blob.channel_range(q * 4, 4);
+
+        // shifted anchor
+        float anchor_y = anchor[1];
+
+        float anchor_w = anchor[2] - anchor[0];
+        float anchor_h = anchor[3] - anchor[1];
+
+        for (int i = 0; i < h; i++)
+        {
+            float anchor_x = anchor[0];
+
+            for (int j = 0; j < w; j++)
+            {
+                int index = i * w + j;
+
+                float prob = score[index];
+
+                if (prob >= prob_threshold)
+                {
+                    // insightface/detection/scrfd/mmdet/models/dense_heads/scrfd_head.py _get_bboxes_single()
+                    float dx = bbox.channel(0)[index] * feat_stride;
+                    float dy = bbox.channel(1)[index] * feat_stride;
+                    float dw = bbox.channel(2)[index] * feat_stride;
+                    float dh = bbox.channel(3)[index] * feat_stride;
+
+                    // insightface/detection/scrfd/mmdet/core/bbox/transforms.py distance2bbox()
+                    float cx = anchor_x + anchor_w * 0.5f;
+                    float cy = anchor_y + anchor_h * 0.5f;
+
+                    float x0 = cx - dx;
+                    float y0 = cy - dy;
+                    float x1 = cx + dw;
+                    float y1 = cy + dh;
+
+                    FaceObject obj;
+                    obj.rect.x = x0;
+                    obj.rect.y = y0;
+                    obj.rect.width = x1 - x0 + 1;
+                    obj.rect.height = y1 - y0 + 1;
+                    obj.prob = prob;
+
+                    faceobjects.push_back(obj);
+                }
+
+                anchor_x += feat_stride;
+            }
+
+            anchor_y += feat_stride;
+        }
+    }
+}
+
+static int detect_scrfd(const cv::Mat& bgr, std::vector<FaceObject>& faceobjects)
+{
+    ncnn::Net scrfd;
+
+    scrfd.opt.use_vulkan_compute = true;
+
+    // Insight face does not provided a trained scrfd_crowdhuman model
+    // but I have one for detecing cat face, you can have a try here:
+    // https://drive.google.com/file/d/1JogkKa0f_09HkENbCnXy9hRYxm35wKTn
+    
+    scrfd.load_param("scrfd_crowdhuman.param");
+    scrfd.load_model("scrfd_crowdhuman.bin");
+
+    int width = bgr.cols;
+    int height = bgr.rows;
+
+    const int target_size = 640;
+    const float prob_threshold = 0.3f;
+    const float nms_threshold = 0.45f;
+
+    // pad to multiple of 32
+    int w = width;
+    int h = height;
+    float scale = 1.f;
+    if (w > h)
+    {
+        scale = (float)target_size / w;
+        w = target_size;
+        h = h * scale;
+    }
+    else
+    {
+        scale = (float)target_size / h;
+        h = target_size;
+        w = w * scale;
+    }
+
+    ncnn::Mat in = ncnn::Mat::from_pixels_resize(bgr.data, ncnn::Mat::PIXEL_BGR2RGB, width, height, w, h);
+
+    // pad to target_size rectangle
+    int wpad = (w + 31) / 32 * 32 - w;
+    int hpad = (h + 31) / 32 * 32 - h;
+    ncnn::Mat in_pad;
+    ncnn::copy_make_border(in, in_pad, hpad / 2, hpad - hpad / 2, wpad / 2, wpad - wpad / 2, ncnn::BORDER_CONSTANT, 0.f);
+
+    const float mean_vals[3] = {127.5f, 127.5f, 127.5f};
+    const float norm_vals[3] = {1 / 128.f, 1 / 128.f, 1 / 128.f};
+    in_pad.substract_mean_normalize(mean_vals, norm_vals);
+
+    ncnn::Extractor ex = scrfd.create_extractor();
+
+    ex.input("input.1", in_pad);
+
+    std::vector<FaceObject> faceproposals;
+
+    // stride 8
+    {
+        ncnn::Mat score_blob, bbox_blob;
+        ex.extract("490", score_blob);
+        ex.extract("493", bbox_blob);
+
+        const int base_size = 8;
+        const int feat_stride = 8;
+        ncnn::Mat ratios(1);
+        ratios[0] = 2.f;
+        ncnn::Mat scales(1);
+        scales[0] = 3.f;
+        ncnn::Mat anchors = generate_anchors(base_size, ratios, scales);
+
+        std::vector<FaceObject> faceobjects32;
+        generate_proposals(anchors, feat_stride, score_blob, bbox_blob, prob_threshold, faceobjects32);
+
+        faceproposals.insert(faceproposals.end(), faceobjects32.begin(), faceobjects32.end());
+    }
+
+    // stride 16
+    {
+        ncnn::Mat score_blob, bbox_blob;
+        ex.extract("510", score_blob);
+        ex.extract("513", bbox_blob);
+
+        const int base_size = 16;
+        const int feat_stride = 16;
+        ncnn::Mat ratios(1);
+        ratios[0] = 2.f;
+        ncnn::Mat scales(1);
+        scales[0] = 3.f;
+        ncnn::Mat anchors = generate_anchors(base_size, ratios, scales);
+
+        std::vector<FaceObject> faceobjects16;
+        generate_proposals(anchors, feat_stride, score_blob, bbox_blob, prob_threshold, faceobjects16);
+
+        faceproposals.insert(faceproposals.end(), faceobjects16.begin(), faceobjects16.end());
+    }
+
+    // stride 32
+    {
+        ncnn::Mat score_blob, bbox_blob;
+        ex.extract("530", score_blob);
+        ex.extract("533", bbox_blob);
+
+        const int base_size = 32;
+        const int feat_stride = 32;
+        ncnn::Mat ratios(1);
+        ratios[0] = 2.f;
+        ncnn::Mat scales(1);
+        scales[0] = 3.f;
+        ncnn::Mat anchors = generate_anchors(base_size, ratios, scales);
+
+        std::vector<FaceObject> faceobjects8;
+        generate_proposals(anchors, feat_stride, score_blob, bbox_blob, prob_threshold, faceobjects8);
+
+        faceproposals.insert(faceproposals.end(), faceobjects8.begin(), faceobjects8.end());
+    }
+
+    // stride 64
+    {
+        ncnn::Mat score_blob, bbox_blob, kps_blob;
+        ex.extract("550", score_blob);
+        ex.extract("553", bbox_blob);
+
+        const int base_size = 64;
+        const int feat_stride = 64;
+        ncnn::Mat ratios(1);
+        ratios[0] = 2.f;
+        ncnn::Mat scales(1);
+        scales[0] = 3.f;
+        ncnn::Mat anchors = generate_anchors(base_size, ratios, scales);
+
+        std::vector<FaceObject> faceobjects8;
+        generate_proposals(anchors, feat_stride, score_blob, bbox_blob, prob_threshold, faceobjects8);
+
+        faceproposals.insert(faceproposals.end(), faceobjects8.begin(), faceobjects8.end());
+    }
+
+    // stride 128
+    {
+        ncnn::Mat score_blob, bbox_blob, kps_blob;
+        ex.extract("570", score_blob);
+        ex.extract("573", bbox_blob);
+
+        const int base_size = 128;
+        const int feat_stride = 128;
+        ncnn::Mat ratios(1);
+        ratios[0] = 2.f;
+        ncnn::Mat scales(1);
+        scales[0] = 3.f;
+        ncnn::Mat anchors = generate_anchors(base_size, ratios, scales);
+
+        std::vector<FaceObject> faceobjects8;
+        generate_proposals(anchors, feat_stride, score_blob, bbox_blob, prob_threshold, faceobjects8);
+
+        faceproposals.insert(faceproposals.end(), faceobjects8.begin(), faceobjects8.end());
+    }
+
+    // sort all proposals by score from highest to lowest
+    qsort_descent_inplace(faceproposals);
+
+    // apply nms with nms_threshold
+    std::vector<int> picked;
+    nms_sorted_bboxes(faceproposals, picked, nms_threshold);
+
+    int face_count = picked.size();
+
+    faceobjects.resize(face_count);
+    for (int i = 0; i < face_count; i++)
+    {
+        faceobjects[i] = faceproposals[picked[i]];
+
+        // adjust offset to original unpadded
+        float x0 = (faceobjects[i].rect.x - (wpad / 2)) / scale;
+        float y0 = (faceobjects[i].rect.y - (hpad / 2)) / scale;
+        float x1 = (faceobjects[i].rect.x + faceobjects[i].rect.width - (wpad / 2)) / scale;
+        float y1 = (faceobjects[i].rect.y + faceobjects[i].rect.height - (hpad / 2)) / scale;
+
+        x0 = std::max(std::min(x0, (float)width - 1), 0.f);
+        y0 = std::max(std::min(y0, (float)height - 1), 0.f);
+        x1 = std::max(std::min(x1, (float)width - 1), 0.f);
+        y1 = std::max(std::min(y1, (float)height - 1), 0.f);
+
+        faceobjects[i].rect.x = x0;
+        faceobjects[i].rect.y = y0;
+        faceobjects[i].rect.width = x1 - x0;
+        faceobjects[i].rect.height = y1 - y0;
+    }
+
+    return 0;
+}
+
+static void draw_faceobjects(const cv::Mat& bgr, const std::vector<FaceObject>& faceobjects)
+{
+    cv::Mat image = bgr.clone();
+
+    for (size_t i = 0; i < faceobjects.size(); i++)
+    {
+        const FaceObject& obj = faceobjects[i];
+
+        fprintf(stderr, "%.5f at %.2f %.2f %.2f x %.2f\n", obj.prob,
+                obj.rect.x, obj.rect.y, obj.rect.width, obj.rect.height);
+
+        cv::rectangle(image, obj.rect, cv::Scalar(0, 255, 0));
+
+        char text[256];
+        sprintf(text, "%.1f%%", obj.prob * 100);
+
+        int baseLine = 0;
+        cv::Size label_size = cv::getTextSize(text, cv::FONT_HERSHEY_SIMPLEX, 0.5, 1, &baseLine);
+
+        int x = obj.rect.x;
+        int y = obj.rect.y - label_size.height - baseLine;
+        if (y < 0)
+            y = 0;
+        if (x + label_size.width > image.cols)
+            x = image.cols - label_size.width;
+
+        cv::rectangle(image, cv::Rect(cv::Point(x, y), cv::Size(label_size.width, label_size.height + baseLine)),
+                      cv::Scalar(255, 255, 255), -1);
+
+        cv::putText(image, text, cv::Point(x, y + label_size.height),
+                    cv::FONT_HERSHEY_SIMPLEX, 0.5, cv::Scalar(0, 0, 0));
+    }
+
+    cv::imshow("image", image);
+    cv::waitKey(0);
+}
+
+int main(int argc, char** argv)
+{
+    if (argc != 2)
+    {
+        fprintf(stderr, "Usage: %s [imagepath]\n", argv[0]);
+        return -1;
+    }
+
+    const char* imagepath = argv[1];
+
+    cv::Mat m = cv::imread(imagepath, 1);
+    if (m.empty())
+    {
+        fprintf(stderr, "cv::imread %s failed\n", imagepath);
+        return -1;
+    }
+
+    std::vector<FaceObject> faceobjects;
+    detect_scrfd(m, faceobjects);
+
+    draw_faceobjects(m, faceobjects);
+
+    return 0;
+}