justinge

#error This file requires compiler and library support for the ISO C++ 2011 standard. This support is currently experimental, and must be enabled with the -std=c++11 or -std=gnu++11 compiler options.

1

(base) [jianming_ge@localhost build]$ make .. (base) [jianming_ge@localhost build]$ cmake .. -- cuda found TRUE -- Building shared library with GPU support -- Configuring done -- Generating done -- Build files...

open_dataset.yaml 和 open_dataset_resnest50_FPN_DBhead_pilyLR.yaml 上报错跑不通

1

用icdar2015.yaml 和 icdar2015_resnet18_FPN_DBheead_polyLR.yaml 能跑通的训练集和测试集的结构 放到 open_dataset.yaml 和 open_dataset_resnest50_FPN_DBhead_pilyLR.yaml 上报错跑不通, 请问自定义的配置文件 有样例说明么?

nvidia.line( NameError: name 'nvidia' is not defined

RuntimeError: Expected a 'cuda' device type for generator but found 'cpu'

2

D:\ProgramData\Anaconda3\python.exe D:/code/python/ssd.pytorch/train.py Loading base network... Initializing weights... Loading the dataset... Training SSD on: VOC0712 Using the specified args: Namespace(basenet='vgg16_reducedfc.pth', batch_size=32, cuda=True, dataset='VOC', dataset_root='D:\\code\\python\\ssd.pytorch\\data/VOCdevkit/', gamma=0.1, lr=0.001, momentum=0.9, num_workers=4, resume=None, save_folder='weights/', start_iter=0,...

1. modify add src. before .model otherwise fail to import bodypose_model and handpose_model from src.model import bodypose_model, handpose_model but when run bodymodel = bodypose_model() hl.build_graph(bodymodel, torch.zeros([1, 3, 368, 368])) it...

I'd like it show as  but i dont find how to fullfill it. and only find how to get scatter map and trajectory

9.15日编辑安装的最新MNN， 9.19 pip install的 mnn python 环境 Python 3.8.12 centos7.9 然而报错 ``` >>> import MNN Traceback (most recent call last): File "", line 1, in File "/home/jianming_ge/.local/lib/python3.8/site-packages/MNN/__init__.py", line 4, in...