create_dataset.py

[PythonImageDeveloper]

hi
when i run python create_dataset.py , i get this error : ImportError: No module named 'object_detection.kitti_to_voc'
i have this module my directory . and i followed tree kitti_dataset , this is ok , but i dont know that error what is it ?

[sshleifer]

Dont know windows well, but i would guess problem is with PYTHONPATH
What is your pythonpath, where are you running code from?

[PythonImageDeveloper]

no i switch to ubuntu 16.04 , i running this code from object_detection folder with command python3 create_dataset.py
in this folder i have kitti_data

[sshleifer]

Hmm. can you paste a traceback?

…

On Wed, Jan 24, 2018 at 5:13 PM zeynali ***@***.***> wrote: no i switch to ubuntu 16.04 , i running this code from object_detection folder with command python3 create_dataset.py in this folder i have kitti_data — You are receiving this because you commented. Reply to this email directly, view it on GitHub <#3 (comment)>, or mute the thread <https://github.com/notifications/unsubscribe-auth/AFw9YdXJFu8rCrYOkf_c8rQitLr1L_pwks5tN6sPgaJpZM4Rr7c1> .

[PythonImageDeveloper]

mm@mm:~/object_detection_kitti-master/object_detection$ python3 create_dataset.py
Traceback (most recent call last):
File "create_dataset.py", line 16, in
from object_detection.kitti_to_voc import kitti_to_voc
ImportError: No module named 'object_detection.kitti_to_voc'

[PythonImageDeveloper]

Hi sshleife
this code don't work . ImportError: No module named 'object_detection.kitti_to_voc'
please step by step go through. and ubuntu 16 or 14 ?

[PythonImageDeveloper]

is this correct ?

mm@mm:~/object_detection_kitti/object_detection$ python3 create_dataset.py
Traceback (most recent call last):
File "create_dataset.py", line 182, in
do_kitti_ingest()
File "/home/mm/.local/lib/python3.5/site-packages/click/core.py", line 722, in call
return self.main(*args, **kwargs)
File "/home/mm/.local/lib/python3.5/site-packages/click/core.py", line 697, in main
rv = self.invoke(ctx)
File "/home/mm/.local/lib/python3.5/site-packages/click/core.py", line 895, in invoke
return ctx.invoke(self.callback, **ctx.params)
File "/home/mm/.local/lib/python3.5/site-packages/click/core.py", line 535, in invoke
return callback(*args, **kwargs)
File "create_dataset.py", line 173, in do_kitti_ingest
VOC_TRAIN_DIR, os.path.join(data_dir, 'train.txt'))
File "/home/mm/object_detection_kitti/object_detection/kitti_to_voc.py", line 15, in kitti_to_voc
train_ids=train_id_path)
File "/home/mm/object_detection_kitti/object_detection/vod_converter/converter.py", line 136, in convert
image_detections = ingestor.ingest(from_path, train_ids)
File "/home/mm/object_detection_kitti/object_detection/vod_converter/kitti.py", line 64, in ingest
image_ext = self.find_image_ext(path, first_image_id)
File "/home/mm/object_detection_kitti/object_detection/vod_converter/kitti.py", line 74, in find_image_ext
raise Exception("could not find jpg or png for %s at %s/image_2" % (image_id, root))
Exception: could not find jpg or png for 000000
000001
000002
000003
[................................]
007477
007478
007479
007480 at kitti_data/training/image_2

why can't create tfrecord ?

what are these ? I got confused . what did you do ? why VOC ?
VOC_TRAIN_DIR = 'voc_kitti'
VOC_VALID_DIR = 'voc_kitti_valid'

[sshleifer]

Yeah!

…

On Sat, Feb 10, 2018 at 7:42 AM zeynali ***@***.***> wrote: is this correct ? ***@***.***:~/object_detection_kitti/object_detection$ python3 create_dataset.py Traceback (most recent call last): File "create_dataset.py", line 182, in do_kitti_ingest() File "/home/mm/.local/lib/python3.5/site-packages/click/core.py", line 722, in *call* return self.main(*args, **kwargs) File "/home/mm/.local/lib/python3.5/site-packages/click/core.py", line 697, in main rv = self.invoke(ctx) File "/home/mm/.local/lib/python3.5/site-packages/click/core.py", line 895, in invoke return ctx.invoke(self.callback, **ctx.params) File "/home/mm/.local/lib/python3.5/site-packages/click/core.py", line 535, in invoke return callback(*args, **kwargs) File "create_dataset.py", line 173, in do_kitti_ingest VOC_TRAIN_DIR, os.path.join(data_dir, 'train.txt')) File "/home/mm/object_detection_kitti/object_detection/kitti_to_voc.py", line 15, in kitti_to_voc train_ids=train_id_path) File "/home/mm/object_detection_kitti/object_detection/vod_converter/converter.py", line 136, in convert image_detections = ingestor.ingest(from_path, train_ids) File "/home/mm/object_detection_kitti/object_detection/vod_converter/kitti.py", line 64, in ingest image_ext = self.find_image_ext(path, first_image_id) File "/home/mm/object_detection_kitti/object_detection/vod_converter/kitti.py", line 74, in find_image_ext raise Exception("could not find jpg or png for %s at %s/image_2" % (image_id, root)) Exception: could not find jpg or png for 000000 000001 000002 000003 [................................] 007477 007478 007479 007480 at kitti_data/training/image_2 — You are receiving this because you commented. Reply to this email directly, view it on GitHub <#3 (comment)>, or mute the thread <https://github.com/notifications/unsubscribe-auth/AFw9YeEp-nEI5I0n9wyIGmxZMFag0i2Dks5tTY6vgaJpZM4Rr7c1> .

[PythonImageDeveloper]

So what do i do then؟

[sshleifer]

what does echo $PATH in terminal produce?

…

On Sun, Feb 11, 2018 at 12:24 AM zeynali ***@***.***> wrote: So what do i do then؟ — You are receiving this because you commented. Reply to this email directly, view it on GitHub <#3 (comment)>, or mute the thread <https://github.com/notifications/unsubscribe-auth/AFw9Ybd36NSCyM2hwLSGSz7QddUgE4Baks5tTnmTgaJpZM4Rr7c1> .

[ghimiremukti]

I think the problem is that root directory is not in PYTHONPATH. put it and try running. e.g.

$ export PYTHONPATH=absolute-path-to-repo/object_detection_kitti:$PYTHONPATH
$ source .bashrc

CLUE:
absolute-path-to-repo/object_detection_kitti directory contains adv_imagenet_models, adversarial_crypto....etc.

Hi @sshleifer , could you plz take a look on other issue I just created. Thanks in advance.