Comments (5)
@shuxsu 可以的,比如 SSD的config中 https://github.com/PaddlePaddle/PaddleDetection/blob/release/0.1/configs/ssd/ssd_vgg16_300.yml#L139 :
SSDTestFeed:
batch_size: 1
dataset:
annotation: dataset/coco/annotations/instances_val2017.json
image_shape: [3, 300, 300]
sample_transforms:
- !DecodeImage
to_rgb: true
with_mixup: false
- !ResizeImage
interp: 1
max_size: 0
target_size: 300
use_cv2: false
- !Permute
to_bgr: false
- !NormalizeImage
is_scale: false
mean: [104, 117, 123]
std: [1, 1, 1]
from paddledetection.
@shuxsu 可以的,比如 SSD的config中 https://github.com/PaddlePaddle/PaddleDetection/blob/release/0.1/configs/ssd/ssd_vgg16_300.yml#L139 :
SSDTestFeed: batch_size: 1 dataset: annotation: dataset/coco/annotations/instances_val2017.json image_shape: [3, 300, 300] sample_transforms: - !DecodeImage to_rgb: true with_mixup: false - !ResizeImage interp: 1 max_size: 0 target_size: 300 use_cv2: false - !Permute to_bgr: false - !NormalizeImage is_scale: false mean: [104, 117, 123] std: [1, 1, 1]
配置信息如下:
MaskRCNNTestFeed:
batch_size: 1
dataset:
annotation: /home/shuxsu/models-develop/PaddleCV/PaddleDetection/dataset/coco/annotations/instance_val.json
image_shape: [3, 2048,1024]
sample_transforms:
- !DecodeImage
to_rgb: true # default: true
with_mixup: false # default: false
- !ResizeImage
interp: 1
max_size: 1333
target_size: 800
use_cv2: true # default: true
报错信息如下:
UserWarning: The following exception is not an EOF exception.
"The following exception is not an EOF exception.")
Traceback (most recent call last):
File "infer.py", line 270, in <module>
main()
File "infer.py", line 184, in main
return_numpy=False)
File "/home/shuxsu/anaconda3/lib/python3.7/site-packages/paddle/fluid/executor.py", line 775, in run
six.reraise(*sys.exc_info())
File "/home/shuxsu/anaconda3/lib/python3.7/site-packages/six.py", line 693, in reraise
raise value
File "/home/shuxsu/anaconda3/lib/python3.7/site-packages/paddle/fluid/executor.py", line 770, in run
use_program_cache=use_program_cache)
File "/home/shuxsu/anaconda3/lib/python3.7/site-packages/paddle/fluid/executor.py", line 817, in _run_impl
use_program_cache=use_program_cache)
File "/home/shuxsu/anaconda3/lib/python3.7/site-packages/paddle/fluid/executor.py", line 894, in _run_program
fetch_var_name)
paddle.fluid.core_avx.EnforceNotMet:
--------------------------------------------
C++ Call Stacks (More useful to developers):
--------------------------------------------
0 std::string paddle::platform::GetTraceBackString<std::string const&>(std::string const&, char const*, int)
1 paddle::platform::EnforceNotMet::EnforceNotMet(std::string const&, char const*, int)
2 paddle::operators::ConvOp::InferShape(paddle::framework::InferShapeContext*) const
3 paddle::framework::OperatorWithKernel::RunImpl(paddle::framework::Scope const&, boost::variant<paddle::platform::CUDAPlace, paddle::platform::CPUPlace, paddle::platform::CUDAPinnedPlace, boost::detail::variant::void_, boost::detail::variant::void_, boost::detail::variant::void_, boost::detail::variant::void_, boost::detail::variant::void_, boost::detail::variant::void_, boost::detail::variant::void_, boost::detail::variant::void_, boost::detail::variant::void_, boost::detail::variant::void_, boost::detail::variant::void_, boost::detail::variant::void_, boost::detail::variant::void_, boost::detail::variant::void_, boost::detail::variant::void_, boost::detail::variant::void_, boost::detail::variant::void_> const&, paddle::framework::RuntimeContext*) const
4 paddle::framework::OperatorWithKernel::RunImpl(paddle::framework::Scope const&, boost::variant<paddle::platform::CUDAPlace, paddle::platform::CPUPlace, paddle::platform::CUDAPinnedPlace, boost::detail::variant::void_, boost::detail::variant::void_, boost::detail::variant::void_, boost::detail::variant::void_, boost::detail::variant::void_, boost::detail::variant::void_, boost::detail::variant::void_, boost::detail::variant::void_, boost::detail::variant::void_, boost::detail::variant::void_, boost::detail::variant::void_, boost::detail::variant::void_, boost::detail::variant::void_, boost::detail::variant::void_, boost::detail::variant::void_, boost::detail::variant::void_, boost::detail::variant::void_> const&) const
5 paddle::framework::OperatorBase::Run(paddle::framework::Scope const&, boost::variant<paddle::platform::CUDAPlace, paddle::platform::CPUPlace, paddle::platform::CUDAPinnedPlace, boost::detail::variant::void_, boost::detail::variant::void_, boost::detail::variant::void_, boost::detail::variant::void_, boost::detail::variant::void_, boost::detail::variant::void_, boost::detail::variant::void_, boost::detail::variant::void_, boost::detail::variant::void_, boost::detail::variant::void_, boost::detail::variant::void_, boost::detail::variant::void_, boost::detail::variant::void_, boost::detail::variant::void_, boost::detail::variant::void_, boost::detail::variant::void_, boost::detail::variant::void_> const&)
6 paddle::framework::Executor::RunPreparedContext(paddle::framework::ExecutorPrepareContext*, paddle::framework::Scope*, bool, bool, bool)
7 paddle::framework::Executor::Run(paddle::framework::ProgramDesc const&, paddle::framework::Scope*, int, bool, bool, std::vector<std::string, std::allocator<std::string> > const&, bool)
------------------------------------------
Python Call Stacks (More useful to users):
------------------------------------------
File "/home/shuxsu/anaconda3/lib/python3.7/site-packages/paddle/fluid/framework.py", line 2423, in append_op
attrs=kwargs.get("attrs", None))
File "/home/shuxsu/anaconda3/lib/python3.7/site-packages/paddle/fluid/layer_helper.py", line 43, in append_op
return self.main_program.current_block().append_op(*args, **kwargs)
File "/home/shuxsu/anaconda3/lib/python3.7/site-packages/paddle/fluid/layers/nn.py", line 2800, in conv2d
"data_format": data_format,
File "/home/shuxsu/models-develop/PaddleCV/PaddleDetection/ppdet/modeling/backbones/resnet.py", line 138, in _conv_norm
name=_name + '.conv2d.output.1')
File "/home/shuxsu/models-develop/PaddleCV/PaddleDetection/ppdet/modeling/backbones/resnet.py", line 380, in c1_stage
name=_name)
File "/home/shuxsu/models-develop/PaddleCV/PaddleDetection/ppdet/modeling/backbones/resnet.py", line 401, in __call__
res = self.c1_stage(res)
File "/home/shuxsu/models-develop/PaddleCV/PaddleDetection/ppdet/modeling/architectures/mask_rcnn.py", line 88, in build
body_feats = self.backbone(im)
File "/home/shuxsu/models-develop/PaddleCV/PaddleDetection/ppdet/modeling/architectures/mask_rcnn.py", line 285, in test
return self.build(feed_vars, 'test')
File "infer.py", line 132, in main
test_fetches = model.test(feed_vars)
File "infer.py", line 270, in <module>
main()
----------------------
Error Message Summary:
----------------------
PaddleCheckError: Expected input_channels == filter_dims[1] * groups, but received input_channels:666 != filter_dims[1] * groups:3.
ShapeError: The number of input channels should be equal to filter channels * groups. But received: the input channels is [666], the shapeof input is [1, 666, 1333, 3], the filter channel is [3], the shape of filter is [64, 3, 7, 7],the groups is [1] at [/paddle/paddle/fluid/operators/conv_op.cc:90]
[operator < conv2d > error]
terminate called without an active exception
W1203 12:19:14.752770 21342 init.cc:212] *** Aborted at 1575346754 (unix time) try "date -d @1575346754" if you are using GNU date ***
W1203 12:19:14.757767 21342 init.cc:212] PC: @ 0x0 (unknown)
W1203 12:19:14.757959 21342 init.cc:212] *** SIGABRT (@0x3e800005352) received by PID 21330 (TID 0x7faa18d96700) from PID 21330; stack trace: ***
W1203 12:19:14.762604 21342 init.cc:212] @ 0x7faa6a747890 (unknown)
W1203 12:19:14.765628 21342 init.cc:212] @ 0x7faa6a382e97 gsignal
W1203 12:19:14.768391 21342 init.cc:212] @ 0x7faa6a384801 abort
W1203 12:19:14.770934 21342 init.cc:212] @ 0x7faa58c4284a __gnu_cxx::__verbose_terminate_handler()
W1203 12:19:14.772892 21342 init.cc:212] @ 0x7faa58c40f47 __cxxabiv1::__terminate()
W1203 12:19:14.774785 21342 init.cc:212] @ 0x7faa58c40f7d std::terminate()
W1203 12:19:14.776237 21342 init.cc:212] @ 0x7faa58c40c5a __gxx_personality_v0
W1203 12:19:14.778208 21342 init.cc:212] @ 0x7faa681e6b97 _Unwind_ForcedUnwind_Phase2
W1203 12:19:14.781105 21342 init.cc:212] @ 0x7faa681e6e7d _Unwind_ForcedUnwind
W1203 12:19:14.782873 21342 init.cc:212] @ 0x7faa6a745f10 __GI___pthread_unwind
W1203 12:19:14.784462 21342 init.cc:212] @ 0x7faa6a73dae5 __pthread_exit
W1203 12:19:14.784979 21342 init.cc:212] @ 0x56480c4bce59 PyThread_exit_thread
W1203 12:19:14.785101 21342 init.cc:212] @ 0x56480c342c17 PyEval_RestoreThread.cold.798
W1203 12:19:14.785704 21342 init.cc:212] @ 0x7faa55354b27 pyopencv_cv_imdecode()
W1203 12:19:14.786296 21342 init.cc:212] @ 0x56480c43e744 _PyMethodDef_RawFastCallKeywords
W1203 12:19:14.786861 21342 init.cc:212] @ 0x56480c43e861 _PyCFunction_FastCallKeywords
W1203 12:19:14.787427 21342 init.cc:212] @ 0x56480c4aa2bd _PyEval_EvalFrameDefault
W1203 12:19:14.787945 21342
from paddledetection.
错误信息提示:
ShapeError: The number of input channels should be equal to filter channels * groups. But received: the input channels is [666], the shapeof input is [1, 666, 1333, 3], the filter channel is [3], the shape of filter is [64, 3, 7, 7],the groups is [1] at [/paddle/paddle/fluid/operators/conv_op.cc:90]
[operator < conv2d > error]
表示conv层输入的shape是[1, 666, 1333, 3],而期望的输入数据channel是3,所以是没有数据的Permute,需要在config里加入Permute操作:
sample_transforms:
- !DecodeImage
to_rgb: true
with_mixup: false
- !NormalizeImage
is_channel_first: false
is_scale: true
mean: [0.485,0.456,0.406]
std: [0.229, 0.224,0.225]
- !ResizeImage
interp: 1
max_size: 1333
target_size: 800
use_cv2: true
- !Permute
channel_first: true
to_bgr: false
from paddledetection.
@shuxsu 请问是否解决?
from paddledetection.
@shuxsu 请问是否解决?
已解决
from paddledetection.
Related Issues (20)
- 关键点检测为什么把参数都写死了,只能对person进行检测 HOT 1
- 关于Detection的C++部署 HOT 4
- 运行pp_human pipeline,开启人员跟踪,姿态估计,属性等功能,偶尔会发现图像画面卡住,此时查看cpu占用和GPU都正常,GPU显存占用,但是使用率为0 HOT 6
- 使用pphuman检测到人员,如何实时的通知外部应用。 HOT 4
- PPVehicles Detection Dataset HOT 1
- 请问命令行中的-o 可修改哪些参数呢? HOT 2
- PPYoloe+在PaddleServing上部署报错segmentatioin fault HOT 1
- 我想手机调用有什么好的办法么?不是用原生开发 HOT 1
- 使用pp-yoloe-r训练自己的数据集报错 HOT 5
- 数据增强 HOT 1
- 修改picodet的激活函数:将hardswish修改为leaky_relu HOT 1
- 教程文档中,快速开始的“三、训练、评估、预测”涉及的config文件可能有问题 HOT 1
- PPYOLOE训练自己的数据集报错 HOT 1
- 通过paddle中maskrcnn训练的模型无法部署在FastDeploy的服务中 HOT 2
- 复现ppyoloe+出错 HOT 1
- 转化onnx时报错 HOT 2
- paddle下的maskrcnn训练转onnx后按照示例运行onnx\deplpy只输出了矩形框没有输出掩膜。且种类错误
- paddle detection 模型c++推理部署output目录为空目录 HOT 4
- 使用海光DCU进行预测时,如何指定DCU的device_id目前通过PaddleDetection/deploy/python /infer.py进行推理,目前默认使用0,手动指定device_id 没有效果 HOT 2
- 导出rtdetr的训练模型时出现错误 HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from paddledetection.