python libs/convert/convert_torch_to_onnx.py

"""
This code is used to convert the pytorch model into an onnx format model.
"""
import sys
import ossys.path.insert(0, os.getcwd())
import torch.onnx
import onnx
from classifier.models.build_models import get_models
from basetrainer.utils import torch_toolsdef build_net(model_file, net_type, input_size, num_classes, width_mult=1.0):""":param model_file: 模型文件:param net_type: 模型名称:param input_size: 模型输入大小:param num_classes: 类别数:param width_mult::return:"""model = get_models(net_type, input_size, num_classes, width_mult=width_mult, is_train=False, pretrained=False)state_dict = torch_tools.load_state_dict(model_file)model.load_state_dict(state_dict)return modeldef convert2onnx(model_file, net_type, input_size, num_classes, width_mult=1.0, device="cpu", onnx_type="default"):model = build_net(model_file, net_type, input_size, num_classes, width_mult=width_mult)model = model.to(device)model.eval()model_name = os.path.basename(model_file)[:-len(".pth")] + ".onnx"onnx_path = os.path.join(os.path.dirname(model_file), model_name)# dummy_input = torch.randn(1, 3, 240, 320).to("cuda")dummy_input = torch.randn(1, 3, input_size[1], input_size[0]).to(device)# torch.onnx.export(model, dummy_input, onnx_path, verbose=False,#                   input_names=['input'],output_names=['scores', 'boxes'])do_constant_folding = Trueif onnx_type == "default":torch.onnx.export(model, dummy_input, onnx_path, verbose=False, export_params=True,do_constant_folding=do_constant_folding,input_names=['input'],output_names=['output'])elif onnx_type == "det":torch.onnx.export(model,dummy_input,onnx_path,do_constant_folding=do_constant_folding,export_params=True,verbose=False,input_names=['input'],output_names=['scores', 'boxes', 'ldmks'])elif onnx_type == "kp":torch.onnx.export(model,dummy_input,onnx_path,do_constant_folding=do_constant_folding,export_params=True,verbose=False,input_names=['input'],output_names=['output'])onnx_model = onnx.load(onnx_path)onnx.checker.check_model(onnx_model)print(onnx_path)if __name__ == "__main__":net_type = "mobilenet_v2"width_mult = 1.0input_size = [128, 128]num_classes = 2model_file = "work_space/mobilenet_v2_1.0_CrossEntropyLoss/model/best_model_022_98.1848.pth"convert2onnx(model_file, net_type, input_size, num_classes, width_mult=width_mult)

package com.cv.tnn.model;import android.graphics.Bitmap;public class Detector {static {System.loadLibrary("tnn_wrapper");}/**** 初始化检测模型* @param det_model： 检测模型（不含后缀名）* @param cls_model： 识别模型（不含后缀名）* @param root：模型文件的根目录，放在assets文件夹下* @param model_type：模型类型* @param num_thread：开启线程数* @param useGPU：是否开启GPU进行加速*/public static native void init(String det_model, String cls_model, String root, int model_type, int num_thread, boolean useGPU);/**** 返回检测和识别结果* @param bitmap 图像（bitmap），ARGB_8888格式* @param score_thresh：置信度阈值* @param iou_thresh：  IOU阈值* @return*/public static native FrameInfo[] detect(Bitmap bitmap, float score_thresh, float iou_thresh);
}

#include <jni.h>
#include <string>
#include <fstream>
#include "src/object_detection.h"
#include "src/classification.h"
#include "src/Types.h"
#include "debug.h"
#include "android_utils.h"
#include "opencv2/opencv.hpp"
#include "file_utils.h"using namespace dl;
using namespace vision;static ObjectDetection *detector = nullptr;
static Classification *classifier = nullptr;JNIEXPORT jint JNI_OnLoad(JavaVM *vm, void *reserved) {return JNI_VERSION_1_6;
}JNIEXPORT void JNI_OnUnload(JavaVM *vm, void *reserved) {}extern "C"
JNIEXPORT void JNICALL
Java_com_cv_tnn_model_Detector_init(JNIEnv *env,jclass clazz,jstring det_model,jstring cls_model,jstring root,jint model_type,jint num_thread,jboolean use_gpu) {if (detector != nullptr) {delete detector;detector = nullptr;}std::string parent = env->GetStringUTFChars(root, 0);std::string det_model_ = env->GetStringUTFChars(det_model, 0);std::string cls_model_ = env->GetStringUTFChars(cls_model, 0);string det_model_file = path_joint(parent, det_model_ + ".tnnmodel");string det_proto_file = path_joint(parent, det_model_ + ".tnnproto");string cls_model_file = path_joint(parent, cls_model_ + ".tnnmodel");string cls_proto_file = path_joint(parent, cls_model_ + ".tnnproto");DeviceType device = use_gpu ? GPU : CPU;LOGW("parent     : %s", parent.c_str());LOGW("useGPU     : %d", use_gpu);LOGW("device_type: %d", device);LOGW("model_type : %d", model_type);LOGW("num_thread : %d", num_thread);ObjectDetectionParam model_param = FACE_MODEL;detector = new ObjectDetection(det_model_file,det_proto_file,model_param,num_thread,device);//ClassificationParam ClassParam = FACE_MASK_MODEL;ClassificationParam ClassParam = EYEGLASSES_MODEL;classifier = new Classification(cls_model_file,cls_proto_file,ClassParam,num_thread,device);
}extern "C"
JNIEXPORT jobjectArray JNICALL
Java_com_cv_tnn_model_Detector_detect(JNIEnv *env, jclass clazz, jobject bitmap,jfloat score_thresh, jfloat iou_thresh) {cv::Mat bgr;BitmapToMatrix(env, bitmap, bgr);int src_h = bgr.rows;int src_w = bgr.cols;// 检测区域为整张图片的大小FrameInfo resultInfo;// 开始检测if (detector != nullptr) {detector->detect(bgr, &resultInfo, score_thresh, iou_thresh);} else {ObjectInfo objectInfo;objectInfo.x1 = 0;objectInfo.y1 = 0;objectInfo.x2 = (float)src_w;objectInfo.y2 = (float)src_h;objectInfo.label = 0;resultInfo.info.push_back(objectInfo);}int nums = resultInfo.info.size();LOGW("object nums: %d\n", nums);if (nums > 0) {// 开始检测classifier->detect(bgr, &resultInfo);// 可视化代码printf("sitting label:%d,score:%3.5f", resultInfo.label, resultInfo.score);//classifier->visualizeResult(bgr, &resultInfo);}//cv::cvtColor(bgr, bgr, cv::COLOR_BGR2RGB);//MatrixToBitmap(env, bgr, dst_bitmap);auto BoxInfo = env->FindClass("com/cv/tnn/model/FrameInfo");auto init_id = env->GetMethodID(BoxInfo, "<init>", "()V");auto box_id = env->GetMethodID(BoxInfo, "addBox", "(FFFFIF)V");auto ky_id = env->GetMethodID(BoxInfo, "addKeyPoint", "(FFF)V");jobjectArray ret = env->NewObjectArray(resultInfo.info.size(), BoxInfo, nullptr);for (int i = 0; i < nums; ++i) {auto info = resultInfo.info[i];env->PushLocalFrame(1);//jobject obj = env->AllocObject(BoxInfo);jobject obj = env->NewObject(BoxInfo, init_id);// set bbox//LOGW("rect:[%f,%f,%f，%f] label:%d,score:%f \n", info.rect.x,info.rect.y, info.rect.w, info.rect.h, 0, 1.0f);env->CallVoidMethod(obj, box_id, info.x1, info.y1, info.x2 - info.x1, info.y2 - info.y1,info.category.label, info.category.score);// set keypointfor (const auto &kps : info.landmarks) {//LOGW("point:[%f,%f] score:%f \n", lm.point.x, lm.point.y, lm.score);env->CallVoidMethod(obj, ky_id, (float) kps.x, (float) kps.y, 1.0f);}obj = env->PopLocalFrame(obj);env->SetObjectArrayElement(ret, i, obj);}return ret;
}