stereomatchingkiss / blogcodes2 Goto Github PK

C++ 41.08% QMake 2.43% Python 5.49% C 0.05% MATLAB 1.39% Assembly 0.04% Batchfile 0.20% CMake 0.67% Shell 0.01% Jupyter Notebook 47.79% QML 0.44% Lua 0.38% JavaScript 0.04%

blogcodes2's People

Contributors

Stargazers

Watchers

blogcodes2's Issues

train_yolo3_custom.py run failed.

So I want to know what training command and the version of gluoncv you used ? Did you run successfully about the script？

INFO:root:Start training from [Epoch 0]
epoch  0 , batch  0
infer_shape error. Arguments:
  data0: (16, 3, 544, 544)
  data4: (16, 18207, 2)
  data6: (16, 18207, 80)
  data3: (16, 18207, 2)
  data1: (16, 33, 4)
  data5: (16, 18207, 2)
  data2: (16, 18207, 1)
Traceback (most recent call last):
  File "/home/peichao/.virtualenvs/py3/lib/python3.5/site-packages/mxnet/gluon/block.py", line 805, in _call_cached_op
    for is_arg, i in self._cached_op_args]
  File "/home/peichao/.virtualenvs/py3/lib/python3.5/site-packages/mxnet/gluon/block.py", line 805, in <listcomp>
    for is_arg, i in self._cached_op_args]
  File "/home/peichao/.virtualenvs/py3/lib/python3.5/site-packages/mxnet/gluon/parameter.py", line 494, in data
    return self._check_and_get(self._data, ctx)
  File "/home/peichao/.virtualenvs/py3/lib/python3.5/site-packages/mxnet/gluon/parameter.py", line 208, in _check_and_get
    "num_features, etc., for network layers."%(self.name))
mxnet.gluon.parameter.DeferredInitializationError: Parameter 'yolov30_yolooutputv30_conv0_weight' has not been initialized yet because initialization was deferred. Actual initialization happens during the
 first forward pass. Please pass one batch of data through the network before accessing Parameters. You can also avoid deferred initialization by specifying in_units, num_features, etc., for network layer
s.

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "/home/peichao/.virtualenvs/py3/lib/python3.5/site-packages/mxnet/gluon/block.py", line 791, in _deferred_infer_shape
    self.infer_shape(*args)
  File "/home/peichao/.virtualenvs/py3/lib/python3.5/site-packages/mxnet/gluon/block.py", line 864, in infer_shape
    self._infer_attrs('infer_shape', 'shape', *args)
  File "/home/peichao/.virtualenvs/py3/lib/python3.5/site-packages/mxnet/gluon/block.py", line 853, in _infer_attrs
    **{i.name: getattr(j, attr) for i, j in zip(inputs, args)})
  File "/home/peichao/.virtualenvs/py3/lib/python3.5/site-packages/mxnet/symbol/symbol.py", line 996, in infer_shape
    res = self._infer_shape_impl(False, *args, **kwargs)
  File "/home/peichao/.virtualenvs/py3/lib/python3.5/site-packages/mxnet/symbol/symbol.py", line 1126, in _infer_shape_impl
    ctypes.byref(complete)))
  File "/home/peichao/.virtualenvs/py3/lib/python3.5/site-packages/mxnet/base.py", line 251, in check_call
mxnet.base.MXNetError: Error in operator sigmoidbinarycrossentropyloss0_reshape_like0: [14:41:02] src/operator/tensor/elemwise_unary_op_basic.cc:371: Check failed: (*cbegin < *cend) Invalid begin, end, ge
t lhs_begin=None, lhs_end=None

Stack trace returned 10 entries:
[bt] (0) /home/peichao/.virtualenvs/py3/lib/python3.5/site-packages/mxnet/libmxnet.so(+0x37f51a) [0x7f465a37a51a]
[bt] (1) /home/peichao/.virtualenvs/py3/lib/python3.5/site-packages/mxnet/libmxnet.so(+0x37fb51) [0x7f465a37ab51]
[bt] (2) /home/peichao/.virtualenvs/py3/lib/python3.5/site-packages/mxnet/libmxnet.so(+0x197b6d8) [0x7f465b9766d8]
[bt] (3) /home/peichao/.virtualenvs/py3/lib/python3.5/site-packages/mxnet/libmxnet.so(+0x197ba19) [0x7f465b976a19]
[bt] (4) /home/peichao/.virtualenvs/py3/lib/python3.5/site-packages/mxnet/libmxnet.so(+0x197bbbc) [0x7f465b976bbc]
[bt] (5) /home/peichao/.virtualenvs/py3/lib/python3.5/site-packages/mxnet/libmxnet.so(+0x2b41d8a) [0x7f465cb3cd8a]
[bt] (6) /home/peichao/.virtualenvs/py3/lib/python3.5/site-packages/mxnet/libmxnet.so(+0x2b4471c) [0x7f465cb3f71c]
[bt] (7) /home/peichao/.virtualenvs/py3/lib/python3.5/site-packages/mxnet/libmxnet.so(MXSymbolInferShape+0x15ba) [0x7f465cab35ba]
[bt] (8) /home/peichao/.virtualenvs/py3/lib/python3.5/lib-dynload/_ctypes.cpython-35m-x86_64-linux-gnu.so(ffi_call_unix64+0x4c) [0x7f4678c4be20]
[bt] (9) /home/peichao/.virtualenvs/py3/lib/python3.5/lib-dynload/_ctypes.cpython-35m-x86_64-linux-gnu.so(ffi_call+0x2eb) [0x7f4678c4b88b]



During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "train_yolo3_custom.py", line 374, in <module>
    train(net, train_data, val_data, eval_metric, ctx, args)
  File "train_yolo3_custom.py", line 273, in train
    *[ft[ix] for ft in fixed_targets])
  File "/home/peichao/.virtualenvs/py3/lib/python3.5/site-packages/mxnet/gluon/block.py", line 542, in __call__
    out = self.forward(*args)
  File "/home/peichao/.virtualenvs/py3/lib/python3.5/site-packages/mxnet/gluon/block.py", line 909, in forward
    return self._call_cached_op(x, *args)
  File "/home/peichao/.virtualenvs/py3/lib/python3.5/site-packages/mxnet/gluon/block.py", line 807, in _call_cached_op
    self._deferred_infer_shape(*args)
  File "/home/peichao/.virtualenvs/py3/lib/python3.5/site-packages/mxnet/gluon/block.py", line 795, in _deferred_infer_shape
    raise ValueError(error_msg)
ValueError: Deferred initialization failed because shape cannot be inferred. Error in operator sigmoidbinarycrossentropyloss0_reshape_like0: [14:41:02] src/operator/tensor/elemwise_unary_op_basic.cc:371: 
Check failed: (*cbegin < *cend) Invalid begin, end, get lhs_begin=None, lhs_end=None

博客的链接打不开

我最近才刚用自己的数据集训练了一个yolo v3的detector，过程写在这里，从资料的准备，训练和测试结果皆有。

你好，试了你的Readme的blog链接，打不开，方便重新发下么？谢谢

invalid size of

Hi,

When I try to compile in Qt 5.12 I have below errors:

/Applications/Xcode.app/Contents/Developer/Toolchains/XcodeDefault.xctoolchain/usr/include/c++/v1/memory:2395:27: error: invalid application of 'sizeof' to an incomplete type 'dlib_tool::face_detector' static_assert(sizeof(_Tp) > 0, "default_delete can not delete incomplete type"); ^~~~~~~~~~~

/Applications/Xcode.app/Contents/Developer/Toolchains/XcodeDefault.xctoolchain/usr/include/c++/v1/memory:2395:27: error: invalid application of 'sizeof' to an incomplete type 'mxnet_tool::face_key_extractor' static_assert(sizeof(_Tp) > 0, "default_delete can not delete incomplete type"); ^~~~~~~~~~~

lst file

can you tell me the format of the lst file like this 'idx 4 5 classid x,y,w,h,classid x,y,w,h xxx.jpg'? thxs

insightface c++的要怎么运行？

我是在ubuntu下运行insightface的人脸识别，对c++不熟悉，想请问下要怎么运行获取最后的512维向量呢

Example of batch processing mxnet

Hi @stereomatchingkiss ,

Where is the example of batch processing in mxnet. In the face recognition demo, the input image is processed sequentially. Thanks

Ask for sobel.png in marble slab

Hi,

Thank you very much for your software development. I am currently working subtracting background with high noise and interested in your program called marbleslab().
In the program there's sobel.png. Could you please tell me what kind of image that i should attach there.

Thank you

missing loss.loss

The project segmentation is missing the file defining cross_entropy_loss_2d

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.