-
각 장비의 tf model server에 로드된 모델을 관리하는 기능이 필요하다. 모델을 추가적으로 로드하거나 로드된 모델을 내릴 수 있어야한다.
현재 model config 파일에 있는 모델을 로드하는데 --model_config_file_poll_wait_seconds 옵션 사용하면 model config 파일의 수정사항을 감지하고 적용한다.
추가적…
-
I am training the Yolo with MobilenetV1 on VOC07+12 trainval dataset. I loaded Mobilenet with imagenet weights and built Yolo layers on top of it. I freeze the Mobilnet for first 50 epochs and tried t…
-
Hi can i use pretrained backbone mobilenet darknet network as feature extractor, freeze this layers and train only detector layers ? AKA transfer learning ?
-
Hi,
Thanks for providing such helpful project.
I have images of 2 class i extracted the images of the objects, then i created the XML annotations
the images are 68*68 and the object is around 2/3 o…
-
I convert weights to pb format as following
``
python convert_weights_pb.py --class_names coco.names --data_format NHWC --weights_file
yolov3.weights --output_graph freeze_yolov3_model.pb
``
How…
-
Hi! Nice work!
I'm interested in how this MobileNet.mlmodel compares to the ones provided by Apple on their download page. Specifically how it compares to the VGG16 model which I've been using.
Ge…
-
-
无意间查看darknet的时候发现了你的项目，觉得蛮有意义。
因为项目上的需要，用darknet也算比较长时间了，对yolo进行过caffe以及嵌入式单hpp的整体算法移植，对darknet算是烂熟于心了。现在darknet也成了我进行算法验证的直接框架，DeepCompression,mobilenet
等算法也基于darknet进行了验证。并且为darknet的增添了多分支的数据传输结构。…
-
why not?
x[index] = (x[index] - mean[f])/(sqrt(variance[f]+ .000001f));
-
To tranform caffe failed！ How can we solute the question？