wucng / tensorexpand

集成包

TensorExpand

集成sklearn，tensorflow，keras，pytorch，tflearn，tensorlayer，tf-slim，opencv，spark，dlib等

安装：

git clone https://github.com/fengzhongyouxia/TensorExpand.git
cd TensorExpand
python setup.py sdist     # 生成类似 bee-0.0.1.tar.gz，支持 pip 
pip install TensorExpand-0.1.tar.gz

tensorexpand's Issues

Gender Script return error

i am testing the gender script put when i start it after 1 min of working

error
error
error
error
error
error
error
error
error
error
error
Traceback (most recent call last):
  File "train5.py", line 283, in <module>
    neural_network(len(vocabulary_list))
  File "train5.py", line 192, in neural_network
    initializer=tf.contrib.layers.xavier_initializer()) # [128*3,2]
  File "/usr/lib/python2.7/site-packages/tensorflow/python/ops/variable_scope.py", line 1336, in get_variable
    constraint=constraint)
  File "/usr/lib/python2.7/site-packages/tensorflow/python/ops/variable_scope.py", line 1098, in get_variable
    constraint=constraint)
  File "/usr/lib/python2.7/site-packages/tensorflow/python/ops/variable_scope.py", line 435, in get_variable
    constraint=constraint)
  File "/usr/lib/python2.7/site-packages/tensorflow/python/ops/variable_scope.py", line 404, in _true_getter
    use_resource=use_resource, constraint=constraint)
  File "/usr/lib/python2.7/site-packages/tensorflow/python/ops/variable_scope.py", line 743, in _get_single_variable
    name, "".join(traceback.format_list(tb))))
ValueError: Variable W already exists, disallowed. Did you mean to set reuse=True or reuse=tf.AUTO_REUSE in VarScope? Originally defined at:

  File "train5.py", line 192, in neural_network
    initializer=tf.contrib.layers.xavier_initializer()) # [128*3,2]
  File "train5.py", line 200, in train_neural_network
    output = neural_network(len(vocabulary_list)) # [-1,2]
  File "train5.py", line 280, in <module>
    train_neural_network()

Please advice

AttributeError: 'module' object has no attribute 'img_b64_to_array'

When I run python labelme2COCO.py, I have a following bug:
Traceback (most recent call last):
File "labelme2COCO.py", line 144, in
labelme2coco(labelme_json,'new.json')
File "labelme2COCO.py", line 31, in init
self.save_json()
File "labelme2COCO.py", line 136, in save_json
self.data_transfer()
File "labelme2COCO.py", line 37, in data_transfer
self.images.append(self.image(data,num))
File "labelme2COCO.py", line 49, in image
img = utils.img_b64_to_array(data['imageData'])

I don't know how to fix this error, help me

对于单个物体被遮挡的问题

同一个物体被遮挡分裂成两个多边形，在labelme中标注成同一个名字，但根据这个脚本输出的却是两个物体。还有要请教下这种情况下，"segmentation"这个字段的格式应该是怎么样的

keypoint标注 用什么工具

我看了你里面主要是labelme用于实例分割。那么keypoint标注用什么工具？？

Dose this project support maskrcnn to directly read voc data instead of voc to coco data?

The train.py file at this location “TensorExpand/TensorExpand/Object detection/Mask RCNN/Mask_RCNN Exercise/” can directly identify voc data or convert voc data into coco data for training.I know the voc is transformed into coco in Pascal_VOC_2007_Segmentation/coco.py

question about voc2coco.py

in voc2coco.py, it has this:
obj_path = glob.glob(os.path.join(path, 'SegmentationObject', '*.png'))
however, in general, making voc-style dataset will form 3 dirs:
Annotations、ImageSets、JPEGImages
it has not SegmentationObject(we all knows official voc dataset has SegmentationObject and SegmentationClass)
how can i solve this problem? thank you very much!

运行报错,list越界?

我使用labelme2coco.py把我用labelme生成的json文件转成Coco的json报错,提示在data_tranfer函数中,label[1]越界?我分析了一下,确实会越界,因为第一次label仅有一个值label[0].有遇到同样问题的小伙伴吗?

voc2coco

annotation['area']=abs(cv2.contourArea(contour,True))
cv2.error: OpenCV(3.4.2) /io/opencv/modules/imgproc/src/shapedescr.cpp:272: error: (-215:Assertion failed) npoints >= 0 && (depth == 5 || depth == 4) in function 'contourArea'

category id有问题吧

if self.supercategory not in self.label: self.categories.append(self.categorie()) self.label.append(self.supercategory)
这句话在后来添加id的时候 如果已经都见过了怎么办呢

请问我需要将KITTI数据集做成csv格式么

请问我需要将KITTI数据集做成csv格式么

json.decoder.JSONDecodeError: Expecting value: line 16 column 8 (char 416)

运行one_image_json时报错。
json.decoder.JSONDecodeError: Expecting value: line 16 column 8 (char 416)
请问博主是什么问题？

为什么voc2coco生成的json文件是空的？

TypeError: Object of type 'int64' is not JSON serializable

我在运行代码的时候抛出了这个错误，大家有没有遇到过，怎么解决？！
when running the codes , it occurs the error as below, how to fix ?

不能输出mask

你好，我用您的直接识别voc数据的代码进行训练，训练过程十分顺利，然而在测试的时候，结果图中只有bbox，没有mask，请问一下这是什么问题呢？

pascalvoc2coco.py 运行结果为空，怎么成功将voc转为coco数据集格式？

运行结果：
{ "images": [], "annotations": [], "categories": [] }

关于命名规则

请问父类_子类_num的这个num是每张图片的对象都从1开始标吗？还是说要沿着之前打的图片的序号递增？

数据集中 “area” 数据问题

我在使用你的labelme2coco的代码进行数据转化，以训练官方版Mask-Rcnn，但是在你的代码中没有 annotation['area'] 数据的计算，而MASK-RCNN的训练中是需要这个数据的，请问有相关的计算代码可参考学习？

类别一定要fuper类 然后子类吗？

类别一定要Super类 然后子类吗？我的数据没有这个样子，那要怎么办？