-
I developed a simple python script to transform annotations from [LabelImg tool ](https://github.com/tzutalin/labelImg) to Keras-Retinanet [annotations format](https://github.com/fizyr/keras-retinanet…
-
if I activate the b_train_cnn, the codes will run into the training process, however, dirs_groundtruth is an empty list, how did you design it to go???
or could you plz tell me the what is dirs_grou…
-
Hello,
Having prepared the dataset properly, I tested an example image and got the following result,
 and width(about 50) are not equal.
So i wan't change the resize and intput size length=200,resize width=50, and c…
-
The current label map used in our algorithm randomly classifies all cones in the dataset.
It's necessary to retrain a new model and patch the cone label into:
**models/research/object-detection…
-
Hi AlexeAB，
I have about 2000 sheep images , which one sheep in a image or manys sheep in a image, I have label them and training(number of train about 1600, and val number about 400，change the wid…
-
There is a huge gap in all of these docs around the step of creating the region map for each image. This is not the way that these are done or coded for real. You would use a tool like LabelImg https:…
-
Rectlabel can only convert to XML format and does not support conversion to JSON anymore. Also support for conversion to Kitti format for NVIDIA Digits would be great as well.
-
Hello,
As I realized, if we decided to use DIGITS and Caffe to **detect** objects then we can use a suitable `.caffemodel` in accompany with DetectNet.
Anyway, it seems we have to make our Data…
-
I am trying to save the annotation files into xml file. But each time the following error code occurs:
`Traceback (most recent call last):
File "labelImg.py", line 1291, in saveFile
self._…