MarvinTeichmann / MultiNet

Real-time Joint Semantic Reasoning for Autonomous Driving
MIT License
545 stars 246 forks source link

python demo.py error #6

Closed yghcats closed 7 years ago

yghcats commented 7 years ago

Run command:python demo.py --gpus 0 --input data/demo/um_000005.png

error info: 2017-03-16 17:08:13,898 INFO f: <open file u'RUNS/MultiNet_pretrained/detection/hypes.json', mode 'r' at 0x7f3579424ed0> Traceback (most recent call last): File "demo.py", line 407, in tf.app.run() File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/platform/app.py", line 43, in run sys.exit(main(sys.argv[:1] + flags_passthrough)) File "demo.py", line 305, in main load_out = load_united_model(logdir) File "demo.py", line 249, in load_united_model postfix=model) File "incl/tensorvision/utils.py", line 213, in load_modules_from_logdir data_input = imp.loadsource("input%s" % postfix, f) File "RUNS/MultiNet_pretrained/detection/data_input.py", line 22, in from utils.data_utils import (annotation_jitter, annotation_to_h5) ImportError: No module named data_utils

What's wrong with this mistake?

thanks!

Dr-LingyunXu commented 7 years ago

I fix this problem by adding

sys.path.append('submodules/KittiBox/submodules/') sys.path.append('submodules/KittiSeg/incl/') in the demo.py, it seems that the KittiBox's utils haven't been added into the sys path.

zdx3578 commented 7 years ago

ubuntu 14

ubuntu@ip-172-30-5-78:~/Downloads/MultiNet$ python demo.py --gpus 0 --input data/demo/um_000005.png 2017-03-17 03:46:15,485 INFO No environment variable 'TV_PLUGIN_DIR' found. Set to '/home/ubuntu/tv-plugins'. 2017-03-17 03:46:15,486 INFO No environment variable 'TV_STEP_SHOW' found. Set to '50'. 2017-03-17 03:46:15,486 INFO No environment variable 'TV_STEP_EVAL' found. Set to '250'. 2017-03-17 03:46:15,486 INFO No environment variable 'TV_STEP_WRITE' found. Set to '1000'. 2017-03-17 03:46:15,486 INFO No environment variable 'TV_MAX_KEEP' found. Set to '10'. 2017-03-17 03:46:15,486 INFO No environment variable 'TV_STEP_STR' found. Set to 'Step {step}/{total_steps}: loss = {loss_value:.2f}; lr = {lr_value:.2e}; {sec_per_batch:.3f} sec (per Batch); {examples_per_sec:.1f} imgs/sec'. 2017-03-17 03:46:15,486 INFO GPUs are set to: 0 2017-03-17 03:46:15,487 INFO Download URL: ftp://mi.eng.cam.ac.uk/pub/mttt2/models/MultiNet_pretrained.zip 2017-03-17 03:46:15,487 INFO Download DIR: ./RUNS/MultiNet

download stop here ; maybe no dir or not create dir

Dr-LingyunXu commented 7 years ago

@zdx3578 Create RUNS dir under MultiNet cloud solve this problem.

wumengfei commented 7 years ago

demo demo2

This log has been clogged for almost 20 minutes. Was it finished downloading? I think a log "Extracting MultiNet_pretrained.zip" should appear, but it doesn't. Could you tell me what's wrong? @maxtom Thanks~

zdx3578 commented 7 years ago

@wumengfei i pull a request ; fix this; https://github.com/MarvinTeichmann/MultiNet/pull/11 ; fixed;

or now see https://github.com/zdx3578/MultiNet/ last commit;

MarvinTeichmann commented 7 years ago

Commit 5ba41b0 should fix the error. The manual include code is not required. The corresponding folders should be added automatically, if base_path is set correctly.

To run the update code do:

git pull
git submodules update

Please let me know whether there are still any issues after pulling the new code.