hpc203 / 10kinds-light-face-detector-align-recognition Goto Github PK

Run person0, name:baiqianyuanTraceback (most recent call last): File "D:/Project/video_recognition/get_face_feature.py", line 101, in <module> _, face_img = detect_face.detect(srcimg) ###肖像照，图片中有且仅有有一个人脸 File "D:\Project\video_recognition\mtcnn_pfld_landmark.py", line 14, in detect bounding_boxes, landmarks = self.mtcnn.detect(srcimg) ###landmarks: numpy array, n x 10 (x1, x2 ... x5, y1, y2 ..y5) File "D:\Project\video_recognition\pfld_mtcnn\detector.py", line 397, in detect bounding_boxes = np.vstack(bounding_boxes) File "<__array_function__ internals>", line 6, in vstack File "D:\Ksoftware\Anaconda2020.2\envs\Restorch\lib\site-packages\numpy\core\shape_base.py", line 283, in vstack return _nx.concatenate(arrs, 0) File "<__array_function__ internals>", line 6, in concatenate ValueError: need at least one array to concatenate

当测试图像为w70 h154 时
in
facebox_dnn_result, _ = facebox_dnn_detect.detect(srcimg)facebox_dnn_result, _ = facebox_dnn_detect.detect(srcimg)
in detect
detections = self.net.forward()

cv2.error: OpenCV(4.4.0) C:\Users\appveyor\AppData\Local\Temp\1\pip-req-build-hfoi92lm\opencv\modules\dnn\src\dnn.cpp:3466: error: (-215:Assertion failed) total(os[i]) > 0 in function 'cv::dnn::dnn4_v20200609::Net::Impl::getLayerShapesRecursively'

是不图像太小了，无法前向计算？需要修改resize？

大佬，关注您很久了

遇到报错

Traceback (most recent call last): File "D:/Project/10kinds-light-face-detector-align-recognition-master/10kinds-light-face-detector-align-recognition-master/Run_all_compare_time.py", line 35, in <module> retinaface_dnn_detect = retinaface_dnn(align=align) File "D:\Project\10kinds-light-face-detector-align-recognition-master\10kinds-light-face-detector-align-recognition-master\retinaface_detect_align_module.py", line 45, in __init__ self.net = RetinafaceDetector_dnn() File "D:\Project\10kinds-light-face-detector-align-recognition-master\10kinds-light-face-detector-align-recognition-master\retinaface\detector.py", line 121, in __init__ self.model = cv2.dnn.readNetFromONNX(model_path)

cv2.error: OpenCV(4.1.2) C:\projects\opencv-python\opencv\modules\dnn\src\layers\eltwise_layer.cpp:116: error: (-215:Assertion failed) inputs[0] == inputs[i] in function 'cv::dnn::EltwiseLayerImpl::getMemoryShapes'

是OpenCV版本问题么

Hi, Hope you are doing well. Its quite remarkable work but I am unable to reproduce it because pan.baidu.com is blocked outside china. Can you please upload the model files on somewhere like sync, one drive, google drive etc.

Thanks in advance

这个可以泛化到视频流人脸识别上么，大概怎么操作谢谢大神

小白一个，问下作者两者命名区分开，算法实现上区别是什么？

都说PFLD它是一个简单、快速、超高精度人脸特征点检测算法，但是这个算法还是存在问题的：眨眼的情况下，关键点定位不敏感。

hi,你好。想知道代码中的.onnx及.pth等模型文件是如何训练获得的，方便的话可以告诉以下吗？

遇到报错：
OMP: Error #15: Initializing libiomp5md.dll, but found libiomp5md.dll already initialized.
OMP: Hint This means that multiple copies of the OpenMP runtime have been linked into the program. That is dangerous, since it can degrade performance or cause incorrect results. The best thing to do is to ensure that only a single OpenMP runtime is linked into the process, e.g. by avoiding static linking of the OpenMP runtime in any library. As an unsafe, unsupported, undocumented workaround you can set the environment variable KMP_DUPLICATE_LIB_OK=TRUE to allow the program to continue to execute, but that may cause crashes or silently produce incorrect results. For more information, please see http://www.intel.com/software/products/support/.
请问是什么问题呢？

在detect_face_align_rec这个Python文件中，此句的threshold表示的是阈值还是一个评分呢，默认是0.65，但是输出发现识别我的图片都在1以上甚至有的达到了2.5以上，跟图片质量有关系么，谢谢

drawimg, threshold = srcimg.copy(), 0.65

电脑装的cuda，Run_all_compare_time.py 里如果用GPU跑，报错如下：
Input type (torch.FloatTensor) and weight type (torch.cuda.FloatTensor) should be the same
错误定位在 mtcnn_result, _ = mtcnn_detect.detect(srcimg)里，本人才学，代码能力一般，不知怎么修改，先用CPU了，等待作者和他人完善。

Traceback (most recent call last):
File "10kinds-light-face-detector-align-recognition/libfacedetect_align_module.py", line 275, in
drawimg, face_rois = libface_detect.detect(srcimg)
File "10kinds-light-face-detector-align-recognition/libfacedetect_align_module.py", line 40, in detect
dets = pb.decode(np.squeeze(loc, axis=0), np.squeeze(conf, axis=0))
File "10kinds-light-face-detector-align-recognition/libfacedetection/priorbox.py", line 72, in decode
self.priors[:, 2:4]*np.exp(loc[:, 2:4]*self.variance).reshape((2,1))
ValueError: operands could not be broadcast together with shapes (4385,0) (2,)

您好我想问一下，如何评估arcface在自己的数据集上识别的准确率，是需要自己标注么，如果标注的话是什么格式的呢，视频流的识别准确率又是如何评估的呢，小白求解谢谢大神。

RT，谢谢

希望作者有空上传一下能跑通GPU的版本，感谢~

from retinaface.detector import RetinafaceDetector, RetinafaceDetector_dnn
代码里的这部分会提示 retinaface.detector 不存在。我试了下下载retinaface，他不包含retinaface.detector

请问提取特征的人物肖像一个人要多少张比较好，提取的图像以及检测的图像尺寸有要求吗？有没有推荐的数据集

你好，请问为什么opencv只能使用4.4版本，自己编译的4.5版本都不能成功运行

@hpc203 问下测试过哪个模型最快吗