About train.py

[Guo-Ling]

When i execute train.py at first time , the program reported an error at 80th epoch：The program reported an error.

Traceback (most recent call last): File "/aiLab/gl/NOCS/NOCS_CVPR2019/model.py", line 3068, in data_generator load_image_gt(dataset, config, image_id, augment=augment, use_mini_mask=config.USE_MINI_MASK) File "/aiLab/gl/NOCS/NOCS_CVPR2019/model.py", line 2634, in load_image_gt mask = utils.minimize_mask(bbox, mask, config.MINI_MASK_SHAPE) File "/aiLab/gl/NOCS/NOCS_CVPR2019/utils.py", line 1155, in minimize_mask m = scipy.misc.imresize(m.astype(np.uint8), mini_shape, interp='nearest') File "/home/ai/anaconda3/envs/nocs/lib/python3.5/site-packages/numpy/lib/utils.py", line 101, in newfunc return func(*args, *kwds) File "/home/ai/anaconda3/envs/nocs/lib/python3.5/site-packages/scipy/misc/pilutil.py", line 555, in imresize im = toimage(arr, mode=mode) File "/home/ai/anaconda3/envs/nocs/lib/python3.5/site-packages/numpy/lib/utils.py", line 101, in newfunc return func(args, **kwds) File "/home/ai/anaconda3/envs/nocs/lib/python3.5/site-packages/scipy/misc/pilutil.py", line 338, in toimage image = Image.frombytes('L', shape, bytedata.tostring()) File "/home/ai/anaconda3/envs/nocs/lib/python3.5/site-packages/PIL/Image.py", line 2650, in frombytes im.frombytes(data, decoder_name, args) File "/home/ai/anaconda3/envs/nocs/lib/python3.5/site-packages/PIL/Image.py", line 797, in frombytes d.setimage(self.im) ValueError: tile cannot extend outside image

During handling of the above exception, another exception occurred:

Traceback (most recent call last): File "/home/ai/anaconda3/envs/nocs/lib/python3.5/multiprocessing/pool.py", line 119, in worker result = (True, func(*args, **kwds)) File "/home/ai/anaconda3/envs/nocs/lib/python3.5/site-packages/keras/utils/data_utils.py", line 650, in next_sample return six.next(_SHARED_SEQUENCES[uid]) File "/aiLab/gl/NOCS/NOCS_CVPR2019/model.py", line 3165, in data_generator logging.exception("Error processing image {}".format(dataset.image_info[draw_source_ids])) TypeError: only integer scalar arrays can be converted to a scalar index """

The above exception was the direct cause of the following exception:

Traceback (most recent call last): File "train.py", line 226, in layers_name='all') File "/aiLab/gl/NOCS/NOCS_CVPR2019/model.py", line 4234, in train *fit_kwargs File "/home/ai/anaconda3/envs/nocs/lib/python3.5/site-packages/keras/legacy/interfaces.py", line 91, in wrapper return func(args, *kwargs) File "/home/ai/anaconda3/envs/nocs/lib/python3.5/site-packages/keras/engine/training.py", line 1732, in fit_generator initial_epoch=initial_epoch) File "/home/ai/anaconda3/envs/nocs/lib/python3.5/site-packages/keras/engine/training_generator.py", line 185, in fit_generator generator_output = next(output_generator) File "/home/ai/anaconda3/envs/nocs/lib/python3.5/site-packages/keras/utils/data_utils.py", line 742, in get six.reraise(sys.exc_info()) File "/home/ai/anaconda3/envs/nocs/lib/python3.5/site-packages/six.py", line 703, in reraise raise value File "/home/ai/anaconda3/envs/nocs/lib/python3.5/site-packages/keras/utils/data_utils.py", line 711, in get inputs = future.get(timeout=30) File "/home/ai/anaconda3/envs/nocs/lib/python3.5/multiprocessing/pool.py", line 644, in get raise self._value TypeError: only integer scalar arrays can be converted to a scalar index

[liupenglei]

Have you solved this problem? I also encountered the same problem. How did you solve it?

[liupenglei]

When i execute train.py at first time , the program reported an error at 80th epoch：The program reported an error.

Traceback (most recent call last): File "/aiLab/gl/NOCS/NOCS_CVPR2019/model.py", line 3068, in data_generator load_image_gt(dataset, config, image_id, augment=augment, use_mini_mask=config.USE_MINI_MASK) File "/aiLab/gl/NOCS/NOCS_CVPR2019/model.py", line 2634, in load_image_gt mask = utils.minimize_mask(bbox, mask, config.MINI_MASK_SHAPE) File "/aiLab/gl/NOCS/NOCS_CVPR2019/utils.py", line 1155, in minimize_mask m = scipy.misc.imresize(m.astype(np.uint8), mini_shape, interp='nearest') File "/home/ai/anaconda3/envs/nocs/lib/python3.5/site-packages/numpy/lib/utils.py", line 101, in newfunc return func(*args, *kwds) File "/home/ai/anaconda3/envs/nocs/lib/python3.5/site-packages/scipy/misc/pilutil.py", line 555, in imresize im = toimage(arr, mode=mode) File "/home/ai/anaconda3/envs/nocs/lib/python3.5/site-packages/numpy/lib/utils.py", line 101, in newfunc return func(args, **kwds) File "/home/ai/anaconda3/envs/nocs/lib/python3.5/site-packages/scipy/misc/pilutil.py", line 338, in toimage image = Image.frombytes('L', shape, bytedata.tostring()) File "/home/ai/anaconda3/envs/nocs/lib/python3.5/site-packages/PIL/Image.py", line 2650, in frombytes im.frombytes(data, decoder_name, args) File "/home/ai/anaconda3/envs/nocs/lib/python3.5/site-packages/PIL/Image.py", line 797, in frombytes d.setimage(self.im) ValueError: tile cannot extend outside image

During handling of the above exception, another exception occurred:

Traceback (most recent call last): File "/home/ai/anaconda3/envs/nocs/lib/python3.5/multiprocessing/pool.py", line 119, in worker result = (True, func(*args, **kwds)) File "/home/ai/anaconda3/envs/nocs/lib/python3.5/site-packages/keras/utils/data_utils.py", line 650, in next_sample return six.next(_SHARED_SEQUENCES[uid]) File "/aiLab/gl/NOCS/NOCS_CVPR2019/model.py", line 3165, in data_generator logging.exception("Error processing image {}".format(dataset.image_info[draw_source_ids])) TypeError: only integer scalar arrays can be converted to a scalar index """

The above exception was the direct cause of the following exception:

Traceback (most recent call last): File "train.py", line 226, in layers_name='all') File "/aiLab/gl/NOCS/NOCS_CVPR2019/model.py", line 4234, in train *fit_kwargs File "/home/ai/anaconda3/envs/nocs/lib/python3.5/site-packages/keras/legacy/interfaces.py", line 91, in wrapper return func(args, *kwargs) File "/home/ai/anaconda3/envs/nocs/lib/python3.5/site-packages/keras/engine/training.py", line 1732, in fit_generator initial_epoch=initial_epoch) File "/home/ai/anaconda3/envs/nocs/lib/python3.5/site-packages/keras/engine/training_generator.py", line 185, in fit_generator generator_output = next(output_generator) File "/home/ai/anaconda3/envs/nocs/lib/python3.5/site-packages/keras/utils/data_utils.py", line 742, in get six.reraise(sys.exc_info()) File "/home/ai/anaconda3/envs/nocs/lib/python3.5/site-packages/six.py", line 703, in reraise raise value File "/home/ai/anaconda3/envs/nocs/lib/python3.5/site-packages/keras/utils/data_utils.py", line 711, in get inputs = future.get(timeout=30) File "/home/ai/anaconda3/envs/nocs/lib/python3.5/multiprocessing/pool.py", line 644, in get raise self._value TypeError: only integer scalar arrays can be converted to a scalar index

Have you solved this problem? I also encountered the same problem. How did you solve it?