Rhaegal

I made and trained my own dataset, but I found that there is no `segment_target_classes` parameter when using `custom_segmentation` to predict. How to use `segment_target_classes` in custom_segmentation?

There is a "RuntimeError" when I use this command to run the program, my environment is windows10 64bit system.

3

python test.py --dataroot E:\test_opencv\DeblurGAN-master(fangzhishoudou)\pictest\ --model test --dataset_mode single --learn_residual There is a "RuntimeError" when I use the above command to run the program,how can I fix this error? Error message...

训练自己的数据集的时候，生成train.txt的时候的class_id从0开始还是从1开始？

5

训练自己的数据集的时候，生成train.txt的时候的class_id从0开始还是从1开始？比如我有30个类别的图片，那么做这个train.txt的时候class_id从几开始？

cv2.error: D:\Build\OpenCV\opencv-3.3.1\modules\imgproc\src\color.cpp:11016: error: (-215) scn == 3 || scn == 4 in function cv::cvtColor

8

When I use your code,I find there is a error First,I modified ['-src', '--source', dest='video_source', type=int,……] to ['-src', '--source', dest='video_source', type=str,……] Then I use this command "python object_detection_multithreading.py -src E:C.mp4",but...

运行pretraining.py时出现 tensorflow.python.framework.errors_impl.InvalidArgumentError

6

详细错误是： ``` session.py 1356 _do_call return fn(*args) session.py 1339 _run_fn self._extend_graph() session.py 1374 _extend_graph tf_session.ExtendSession(self._session) tensorflow.python.framework.errors_impl.InvalidArgumentError ------------------------------------------------------------------------------- pretraining.py 164 callbacks=[checkpoint, csv_logger], training.py 649 fit validation_freq=validation_freq) training_distributed.py 143 fit_distributed steps_name='steps_per_epoch') training_arrays.py...

How to deal the problem——Traceback (most recent call last): File "object_detection_tf.py", line 201, in <module> p.start()

6

When I run your code,there is a problem.Traceback (most recent call last): File "object_detection_tf.py", line 201, in p.start() RuntimeError: An attempt has been made to start a new process before...

Some people(object) are not identified in vedio,how to improve the accuracy and let the omission be less?

2

I modified the file"visualization_utils.py", adjusted function "visualize_boxes_and_labels_on_image_array" 's parameter "min_score_thresh=.5" to "min_score_thresh=.3".But some people(object) are still not able to be identified,can you tell me how to fix ?