add yolov7_pnnx example (Tencent#4027)

examples/CMakeLists.txt

@@ -50,6 +50,7 @@ if(NCNN_PIXEL)
         ncnn_add_example(yolov3)
         ncnn_add_example(yolov5)
         ncnn_add_example(yolov5_pnnx)
+        ncnn_add_example(yolov7_pnnx)
         ncnn_add_example(yolov7)
         ncnn_add_example(yolox)
         ncnn_add_example(mobilenetv2ssdlite)

examples/yolov7_pnnx.cpp

@@ -0,0 +1,425 @@
+// Tencent is pleased to support the open source community by making ncnn available.
+//
+// Copyright (C) 2022 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 "layer.h"
+#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 <float.h>
+#include <stdio.h>
+#include <vector>
+
+struct Object
+{
+    cv::Rect_<float> rect;
+    int label;
+    float prob;
+};
+
+static inline float intersection_area(const Object& a, const Object& b)
+{
+    cv::Rect_<float> inter = a.rect & b.rect;
+    return inter.area();
+}
+
+static void qsort_descent_inplace(std::vector<Object>& 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<Object>& faceobjects)
+{
+    if (faceobjects.empty())
+        return;
+
+    qsort_descent_inplace(faceobjects, 0, faceobjects.size() - 1);
+}
+
+static void nms_sorted_bboxes(const std::vector<Object>& 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 Object& a = faceobjects[i];
+
+        int keep = 1;
+        for (int j = 0; j < (int)picked.size(); j++)
+        {
+            const Object& 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);
+    }
+}
+
+static inline float sigmoid(float x)
+{
+    return static_cast<float>(1.f / (1.f + exp(-x)));
+}
+
+static void generate_proposals(const ncnn::Mat& anchors, int stride, const ncnn::Mat& in_pad, const ncnn::Mat& feat_blob, float prob_threshold, std::vector<Object>& objects)
+{
+    const int num_grid_x = feat_blob.w;
+    const int num_grid_y = feat_blob.h;
+
+    const int num_anchors = anchors.w / 2;
+
+    const int num_class = 80;
+
+    for (int q = 0; q < num_anchors; q++)
+    {
+        const float anchor_w = anchors[q * 2];
+        const float anchor_h = anchors[q * 2 + 1];
+
+        for (int i = 0; i < num_grid_y; i++)
+        {
+            for (int j = 0; j < num_grid_x; j++)
+            {
+                // find class index with max class score
+                int class_index = 0;
+                float class_score = -FLT_MAX;
+                for (int k = 0; k < num_class; k++)
+                {
+                    float score = feat_blob.channel(q * 85 + 5 + k).row(i)[j];
+                    if (score > class_score)
+                    {
+                        class_index = k;
+                        class_score = score;
+                    }
+                }
+
+                float box_score = feat_blob.channel(q * 85 + 4).row(i)[j];
+
+                float confidence = sigmoid(box_score) * sigmoid(class_score);
+
+                if (confidence >= prob_threshold)
+                {
+                    // yolov5/models/yolo.py Detect forward
+                    // y = x[i].sigmoid()
+                    // y[..., 0:2] = (y[..., 0:2] * 2. - 0.5 + self.grid[i].to(x[i].device)) * self.stride[i]  # xy
+                    // y[..., 2:4] = (y[..., 2:4] * 2) ** 2 * self.anchor_grid[i]  # wh
+
+                    float dx = sigmoid(feat_blob.channel(q * 85 + 0).row(i)[j]);
+                    float dy = sigmoid(feat_blob.channel(q * 85 + 1).row(i)[j]);
+                    float dw = sigmoid(feat_blob.channel(q * 85 + 2).row(i)[j]);
+                    float dh = sigmoid(feat_blob.channel(q * 85 + 3).row(i)[j]);
+
+                    float pb_cx = (dx * 2.f - 0.5f + j) * stride;
+                    float pb_cy = (dy * 2.f - 0.5f + i) * stride;
+
+                    float pb_w = pow(dw * 2.f, 2) * anchor_w;
+                    float pb_h = pow(dh * 2.f, 2) * anchor_h;
+
+                    float x0 = pb_cx - pb_w * 0.5f;
+                    float y0 = pb_cy - pb_h * 0.5f;
+                    float x1 = pb_cx + pb_w * 0.5f;
+                    float y1 = pb_cy + pb_h * 0.5f;
+
+                    Object obj;
+                    obj.rect.x = x0;
+                    obj.rect.y = y0;
+                    obj.rect.width = x1 - x0;
+                    obj.rect.height = y1 - y0;
+                    obj.label = class_index;
+                    obj.prob = confidence;
+
+                    objects.push_back(obj);
+                }
+            }
+        }
+    }
+}
+
+static int detect_yolov7(const cv::Mat& bgr, std::vector<Object>& objects)
+{
+    ncnn::Net yolov7;
+
+    yolov7.opt.use_vulkan_compute = true;
+    // yolov7.opt.use_bf16_storage = true;
+
+    // git clone https://github.com/WongKinYiu/yolov7
+    // cd yolov7
+    // wget https://github.com/WongKinYiu/yolov7/releases/download/v0.1/yolov7.pt
+    // python models/export.py --weights yolov7.pt
+    // pnnx yolov7.torchscript.pt inputshape=[1,3,640,640] inputshape=[1,3,320,320]
+    yolov7.load_param("yolov7.param");
+    yolov7.load_model("yolov7.bin");
+
+    const int target_size = 640;
+    const float prob_threshold = 0.25f;
+    const float nms_threshold = 0.45f;
+
+    int img_w = bgr.cols;
+    int img_h = bgr.rows;
+
+    // yolov5/models/common.py DetectMultiBackend
+    const int max_stride = 64;
+
+    // letterbox pad to multiple of max_stride
+    int w = img_w;
+    int h = img_h;
+    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, img_w, img_h, w, h);
+
+    // pad to target_size rectangle
+    // yolov5/utils/datasets.py letterbox
+    int wpad = (w + max_stride - 1) / max_stride * max_stride - w;
+    int hpad = (h + max_stride - 1) / max_stride * max_stride - 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, 114.f);
+
+    const float norm_vals[3] = {1 / 255.f, 1 / 255.f, 1 / 255.f};
+    in_pad.substract_mean_normalize(0, norm_vals);
+
+    ncnn::Extractor ex = yolov7.create_extractor();
+
+    ex.input("in0", in_pad);
+
+    std::vector<Object> proposals;
+
+    // anchor setting from yolov5/models/yolov5s.yaml
+
+    // stride 8
+    {
+        ncnn::Mat out;
+        ex.extract("out0", out);
+
+        ncnn::Mat anchors(6);
+        anchors[0] = 12.f;
+        anchors[1] = 16.f;
+        anchors[2] = 19.f;
+        anchors[3] = 36.f;
+        anchors[4] = 40.f;
+        anchors[5] = 28.f;
+
+        std::vector<Object> objects8;
+        generate_proposals(anchors, 8, in_pad, out, prob_threshold, objects8);
+
+        proposals.insert(proposals.end(), objects8.begin(), objects8.end());
+    }
+
+    // stride 16
+    {
+        ncnn::Mat out;
+        ex.extract("out1", out);
+
+        ncnn::Mat anchors(6);
+        anchors[0] = 36.f;
+        anchors[1] = 75.f;
+        anchors[2] = 76.f;
+        anchors[3] = 55.f;
+        anchors[4] = 72.f;
+        anchors[5] = 146.f;
+
+        std::vector<Object> objects16;
+        generate_proposals(anchors, 16, in_pad, out, prob_threshold, objects16);
+
+        proposals.insert(proposals.end(), objects16.begin(), objects16.end());
+    }
+
+    // stride 32
+    {
+        ncnn::Mat out;
+        ex.extract("out2", out);
+
+        ncnn::Mat anchors(6);
+        anchors[0] = 142.f;
+        anchors[1] = 110.f;
+        anchors[2] = 192.f;
+        anchors[3] = 243.f;
+        anchors[4] = 459.f;
+        anchors[5] = 401.f;
+
+        std::vector<Object> objects32;
+        generate_proposals(anchors, 32, in_pad, out, prob_threshold, objects32);
+
+        proposals.insert(proposals.end(), objects32.begin(), objects32.end());
+    }
+
+    // sort all proposals by score from highest to lowest
+    qsort_descent_inplace(proposals);
+
+    // apply nms with nms_threshold
+    std::vector<int> picked;
+    nms_sorted_bboxes(proposals, picked, nms_threshold);
+
+    int count = picked.size();
+
+    objects.resize(count);
+    for (int i = 0; i < count; i++)
+    {
+        objects[i] = proposals[picked[i]];
+
+        // adjust offset to original unpadded
+        float x0 = (objects[i].rect.x - (wpad / 2)) / scale;
+        float y0 = (objects[i].rect.y - (hpad / 2)) / scale;
+        float x1 = (objects[i].rect.x + objects[i].rect.width - (wpad / 2)) / scale;
+        float y1 = (objects[i].rect.y + objects[i].rect.height - (hpad / 2)) / scale;
+
+        // clip
+        x0 = std::max(std::min(x0, (float)(img_w - 1)), 0.f);
+        y0 = std::max(std::min(y0, (float)(img_h - 1)), 0.f);
+        x1 = std::max(std::min(x1, (float)(img_w - 1)), 0.f);
+        y1 = std::max(std::min(y1, (float)(img_h - 1)), 0.f);
+
+        objects[i].rect.x = x0;
+        objects[i].rect.y = y0;
+        objects[i].rect.width = x1 - x0;
+        objects[i].rect.height = y1 - y0;
+    }
+
+    return 0;
+}
+
+static void draw_objects(const cv::Mat& bgr, const std::vector<Object>& objects)
+{
+    static const char* class_names[] = {
+        "person", "bicycle", "car", "motorcycle", "airplane", "bus", "train", "truck", "boat", "traffic light",
+        "fire hydrant", "stop sign", "parking meter", "bench", "bird", "cat", "dog", "horse", "sheep", "cow",
+        "elephant", "bear", "zebra", "giraffe", "backpack", "umbrella", "handbag", "tie", "suitcase", "frisbee",
+        "skis", "snowboard", "sports ball", "kite", "baseball bat", "baseball glove", "skateboard", "surfboard",
+        "tennis racket", "bottle", "wine glass", "cup", "fork", "knife", "spoon", "bowl", "banana", "apple",
+        "sandwich", "orange", "broccoli", "carrot", "hot dog", "pizza", "donut", "cake", "chair", "couch",
+        "potted plant", "bed", "dining table", "toilet", "tv", "laptop", "mouse", "remote", "keyboard", "cell phone",
+        "microwave", "oven", "toaster", "sink", "refrigerator", "book", "clock", "vase", "scissors", "teddy bear",
+        "hair drier", "toothbrush"
+    };
+
+    cv::Mat image = bgr.clone();
+
+    for (size_t i = 0; i < objects.size(); i++)
+    {
+        const Object& obj = objects[i];
+
+        fprintf(stderr, "%d = %.5f at %.2f %.2f %.2f x %.2f\n", obj.label, obj.prob,
+                obj.rect.x, obj.rect.y, obj.rect.width, obj.rect.height);
+
+        cv::rectangle(image, obj.rect, cv::Scalar(255, 0, 0));
+
+        char text[256];
+        sprintf(text, "%s %.1f%%", class_names[obj.label], 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<Object> objects;
+    detect_yolov7(m, objects);
+
+    draw_objects(m, objects);
+
+    return 0;
+}