tensorflow.python.framework.errors_impl.InvalidArgumentError: indices[0] = 29 is not in [0, 22

[fabioaraujopt]

Hello,

while running the process_video.py i get this error.
Have you an ideia?

Traceback (most recent call last):
File "process_video.py", line 3, in
from visualize_cv2 import model, display_instances, class_names
File "C:\Anaconda3\envs\MaskRCNN\Mask_RCNN\mrcnn\visualize_cv2.py", line 122, in
results = model.detect([frame], verbose=0)
File "C:\Anaconda3\envs\MaskRCNN\Mask_RCNN\mrcnn\model.py", line 2525, in detect
self.keras_model.predict([molded_images, image_metas, anchors], verbose=0)
File "C:\Anaconda3\envs\MaskRCNN\lib\site-packages\keras\engine\training.py", line 1169, in predict
steps=steps)
File "C:\Anaconda3\envs\MaskRCNN\lib\site-packages\keras\engine\training_arrays.py", line 294, in predict_loop
batch_outs = f(ins_batch)
File "C:\Anaconda3\envs\MaskRCNN\lib\site-packages\keras\backend\tensorflow_backend.py", line 2715, in call
return self._call(inputs)
File "C:\Anaconda3\envs\MaskRCNN\lib\site-packages\keras\backend\tensorflow_backend.py", line 2675, in _call
fetched = self._callable_fn(*array_vals)
File "C:\Anaconda3\envs\MaskRCNN\lib\site-packages\tensorflow\python\client\session.py", line 1439, in call
run_metadata_ptr)
File "C:\Anaconda3\envs\MaskRCNN\lib\site-packages\tensorflow\python\framework\errors_impl.py", line 528, in exit
c_api.TF_GetCode(self.status.status))
tensorflow.python.framework.errors_impl.InvalidArgumentError: indices[0] = 29 is not in [0, 22)
[[{{node mrcnn_detection/map/while/GatherV2_2}} = GatherV2[Taxis=DT_INT32, Tindices=DT_INT32, Tparams=DT_INT64, _device="/job:localhost/replica:0/task:0/device:CPU:0"](mrcnn_detection/map/while/strided_slice, mrcnn_detection/map/while/non_max_suppression/NonMaxSuppressionV3, mrcnn_detection/map/while/PadV2/paddings/0/0)]]

[cooleel]

Did you solve the problem?
I Met the same error when trying to run the inference mode on the CPU.
The same script runs well on a GPU machine.
Any ideas?
Thanks.