sbdcv / sbd_mask Goto Github PK

看到模型的输入是10x3x32x32 的shape。 如果我有一个720P的图片，那我应该如何取适配？

我在运行demo_baidu.py程序时，导入paddlehub包的那一行程序Json报错。具体如下：
Traceback (most recent call last):
File "F:/Python编程/sbd_mask-master/demo_baidu.py", line 1, in
import paddlehub as hub
File "D:\Anaconda2019\envs\tf-gpu\lib\site-packages\paddlehub_init_.py", line 25, in
from . import module
File "D:\Anaconda2019\envs\tf-gpu\lib\site-packages\paddlehub\module_init_.py", line 16, in
from . import module
File "D:\Anaconda2019\envs\tf-gpu\lib\site-packages\paddlehub\module\module.py", line 31, in
from paddlehub.common import utils
File "D:\Anaconda2019\envs\tf-gpu\lib\site-packages\paddlehub\common_init_.py", line 16, in
from . import utils
File "D:\Anaconda2019\envs\tf-gpu\lib\site-packages\paddlehub\common\utils.py", line 33, in
from paddlehub.common.logger import logger
File "D:\Anaconda2019\envs\tf-gpu\lib\site-packages\paddlehub\common\logger.py", line 155, in
logger = Logger()
File "D:\Anaconda2019\envs\tf-gpu\lib\site-packages\paddlehub\common\logger.py", line 67, in init
level = json.load(fp).get("log_level", "DEBUG")
File "D:\Anaconda2019\envs\tf-gpu\lib\json_init_.py", line 299, in load
parse_constant=parse_constant, object_pairs_hook=object_pairs_hook, **kw)
File "D:\Anaconda2019\envs\tf-gpu\lib\json_init_.py", line 354, in loads
return _default_decoder.decode(s)
File "D:\Anaconda2019\envs\tf-gpu\lib\json\decoder.py", line 339, in decode
obj, end = self.raw_decode(s, idx=_w(s, 0).end())
File "D:\Anaconda2019\envs\tf-gpu\lib\json\decoder.py", line 357, in raw_decode
raise JSONDecodeError("Expecting value", s, err.value) from None
json.decoder.JSONDecodeError: Expecting value: line 1 column 1 (char 0)

上网查不到结果，想问问大家有什么解决方案吗？

如题。请问口罩分类训练数据集可以分享吗？thanks

您好，我在尝试执行 demo_sbd.py，有如下报错：

请问是什么原因呢？

您好～ 我在使用单张图片测试demo_sbd时，发现所有检测结果的label都为“mask”，且概率都为-0.766，请问为什么会这样呢？
输出结果：

lable:0,prob:-0.766279101372
lable:0,prob:-0.766279101372
lable:0,prob:-0.766279101372
lable:0,prob:-0.766279101372
lable:0,prob:-0.766279101372
lable:0,prob:-0.766279101372
lable:0,prob:-0.766279101372
lable:0,prob:-0.766279101372
lable:0,prob:-0.766279101372
lable:0,prob:-0.766279101372
('time: ', 0.3952939510345459)
: cannot connect to X server

您好，我在尝试执行 demo_sbd.py，有如下报错：
cv2.error: OpenCV(4.0.0) C:\projects\opencv-python\opencv\modules\dnn\src\onnx\onnx_importer.cpp:272: error: (-204:Requested object was not found) Blob 343 not found in const blobs in function 'cv::dnn::dnn4_v20180917::ONNXImporter::getBlob'
请问是什么原因呢？

感谢开源代码，本人在对比贵公司和百度的算法时。在进行图片的批量检测处理时，贵公司算法在cpu资源的使用上较高，是否有优化的空间。谢谢
下图中 图一为百度的口罩检测算法运行时的cpu使用情况，图二为贵公司算法运行时cpu使用情况

我想训练。我如何获取数据集。感谢分享。