Closed yghcats closed 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.
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
@zdx3578 Create RUNS dir under MultiNet cloud solve this problem.
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~
@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;
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.
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!