harleyszhang/detect_steel_number

DCIC 钢筋数量AI识别 baseline 0.98+。

Hi there 👋

Here are few quick facts:

• 🔭 I’m currently working on sensetime shenzhen corporation
• 🌱 I’m currently learning cv、c++、algorithm
• 🤔 I’m looking for help with risc-v
• 📫 How to reach me: [email protected]

Skills 🛠️

• Languages:    C++, Python, Shell, Lua
• CV/ML/DL:     PyTorch, OpenCV, Detection, Quantization
• Develops:       Linux, Git, Docker, CI/CD, VSCode, Markdown/Latex

detect_steel_number's Issues

数据集

您好，比赛链接那个部分，下载总失败，您还有这个数据集吗

怎么将模型改成VGG16或者resnet50呢？

您好，怎么将模型改成VGG16或者resnet50呢？新手刚如坑，不太明白。感激不尽

val放的是什么？

预测结果不对

大佬您好，我训练了一些epoch之后进行测试，但是网络输出一个钢筋都识别不到，可能是哪里的问题呀？

可以提供下数据集吗？

您好，可以提供数据集下载吗？想复现下实验

有些不懂的地方

单独目标检测的数据 转mask rnn 的数据需要其他信息吗

EOFError: Ran out of input

File "E:\miniconda3\envs\yolov4_tf1.14_py3.6\lib\multiprocessing\reduction.py", line 60, in dump
ForkingPickler(file, protocol).dump(obj)
AttributeError: Can't pickle local object 'GeneratorEnqueuer.start..data_generator_task'
{'log_to_stderr': False, 'authkey': b"\xf2'I\xb91k\xc7R\xca,fp\n\xdcV\xf8\x14[h\xd3\xf6\xe6X\xa5\xdb}E:%\xdb\xba)", 'name': 'Process-1', 'sys_path': ['E:\Wuyf\Project\detect_steel_number-master\samples\gangjin', 'E:\miniconda3\envs\yolov4_tf
1.14_py3.6\python36.zip', 'E:\miniconda3\envs\yolov4_tf1.14_py3.6\DLLs', 'E:\miniconda3\envs\yolov4_tf1.14_py3.6\lib', 'E:\miniconda3\envs\yolov4_tf1.14_py3.6', 'E:\miniconda3\envs\yolov4_tf1.14_py3.6\lib\site-packages', 'E:\minico
nda3\envs\yolov4_tf1.14_py3.6\lib\site-packages\mask_rcnn-2.1-py3.6.egg', 'E:\Wuyf\Project\detect_steel_number-master'], 'sys_argv': ['gangjin.py', 'train', '--dataset=./datasets/', '--weights=coco'], 'orig_dir': 'E:\Wuyf\Project\detect_s
teel_number-master\samples\gangjin', 'dir': 'E:\Wuyf\Project\detect_steel_number-master\samples\gangjin', 'start_method': 'spawn', 'init_main_from_path': 'E:\Wuyf\Project\detect_steel_number-master\samples\gangjin\gangjin.py'}
E:\miniconda3\envs\yolov4_tf1.14_py3.6\lib\site-packages\tensorflow\python\framework\dtypes.py:516: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) /
'(1,)type'.
_np_qint8 = np.dtype([("qint8", np.int8, 1)])
E:\miniconda3\envs\yolov4_tf1.14_py3.6\lib\site-packages\tensorflow\python\framework\dtypes.py:517: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) /
'(1,)type'.
_np_quint8 = np.dtype([("quint8", np.uint8, 1)])
E:\miniconda3\envs\yolov4_tf1.14_py3.6\lib\site-packages\tensorflow\python\framework\dtypes.py:518: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) /
'(1,)type'.
_np_qint16 = np.dtype([("qint16", np.int16, 1)])
E:\miniconda3\envs\yolov4_tf1.14_py3.6\lib\site-packages\tensorflow\python\framework\dtypes.py:519: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) /
'(1,)type'.
_np_quint16 = np.dtype([("quint16", np.uint16, 1)])
E:\miniconda3\envs\yolov4_tf1.14_py3.6\lib\site-packages\tensorflow\python\framework\dtypes.py:520: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) /
'(1,)type'.
_np_qint32 = np.dtype([("qint32", np.int32, 1)])
E:\miniconda3\envs\yolov4_tf1.14_py3.6\lib\site-packages\tensorflow\python\framework\dtypes.py:525: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) /
'(1,)type'.
np_resource = np.dtype([("resource", np.ubyte, 1)])

(yolov4_tf1.14_py3.6) E:\Wuyf\Project\detect_steel_number-master\samples\gangjin>E:\miniconda3\envs\yolov4_tf1.14_py3.6\lib\site-packages\tensorboard\compat\tensorflow_stub\dtypes.py:541: FutureWarning: Passing (type, 1) or '1type' as a synonym of t
ype is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.
_np_qint8 = np.dtype([("qint8", np.int8, 1)])
E:\miniconda3\envs\yolov4_tf1.14_py3.6\lib\site-packages\tensorboard\compat\tensorflow_stub\dtypes.py:542: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type,
(1,)) / '(1,)type'.
_np_quint8 = np.dtype([("quint8", np.uint8, 1)])
E:\miniconda3\envs\yolov4_tf1.14_py3.6\lib\site-packages\tensorboard\compat\tensorflow_stub\dtypes.py:543: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type,
(1,)) / '(1,)type'.
_np_qint16 = np.dtype([("qint16", np.int16, 1)])
E:\miniconda3\envs\yolov4_tf1.14_py3.6\lib\site-packages\tensorboard\compat\tensorflow_stub\dtypes.py:544: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type,
(1,)) / '(1,)type'.
_np_quint16 = np.dtype([("quint16", np.uint16, 1)])
E:\miniconda3\envs\yolov4_tf1.14_py3.6\lib\site-packages\tensorboard\compat\tensorflow_stub\dtypes.py:545: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type,
(1,)) / '(1,)type'.
_np_qint32 = np.dtype([("qint32", np.int32, 1)])
E:\miniconda3\envs\yolov4_tf1.14_py3.6\lib\site-packages\tensorboard\compat\tensorflow_stub\dtypes.py:550: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type,
(1,)) / '(1,)type'.
np_resource = np.dtype([("resource", np.ubyte, 1)])
Using TensorFlow backend.
Traceback (most recent call last):
File "", line 1, in
File "E:\miniconda3\envs\yolov4_tf1.14_py3.6\lib\multiprocessing\spawn.py", line 105, in spawn_main
exitcode = _main(fd)
File "E:\miniconda3\envs\yolov4_tf1.14_py3.6\lib\multiprocessing\spawn.py", line 117, in _main
self = reduction.pickle.load(from_parent)
EOFError: Ran out of input

Hello, how did I report this mistake on Windows? Thank you

依赖文件中的环境能不能列下版本号？

现在跑不起来，老是环境有问题，一查都是因为库的版本不对应。