Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Error while running inference for Part 2 #12

Open
ashishverma03 opened this issue Feb 27, 2021 · 0 comments
Open

Error while running inference for Part 2 #12

ashishverma03 opened this issue Feb 27, 2021 · 0 comments

Comments

@ashishverma03
Copy link

ashishverma03 commented Feb 27, 2021

I am trying to run inference for Part 2 of your code. I am trying to run inference on Google Colab. I followed all the steps and install caffe2 and Detectron and all are running fine. I ran :

python2 tools/infer_simple.py \ --cfg configs/bbox2mask_vg/eval_sw/runtest_clsbox_2_layer_mlp_nograd.yaml \ --output-dir /tmp/detectron-visualizations-vg3k \ --image-ext jpg \ --thresh 0.5 --use-vg3k \ --wts lib/datasets/data/trained_models/33241332_model_final_coco2vg3k_seg.pkl \ demo_vg3k

The code aborted with error:
KeyError: u'Non-existent config key: MRCNN.BBOX2MASK

The logging information is:

Found Detectron ops lib: /usr/local/lib/python2.7/dist-packages/torch/lib/libcaffe2_detectron_ops_gpu.so [E init_intrinsics_check.cc:43] CPU feature avx is present on your machine, but the Caffe2 binary is not compiled with it. It means you may not get the full speed of your CPU. [E init_intrinsics_check.cc:43] CPU feature avx2 is present on your machine, but the Caffe2 binary is not compiled with it. It means you may not get the full speed of your CPU. [E init_intrinsics_check.cc:43] CPU feature fma is present on your machine, but the Caffe2 binary is not compiled with it. It means you may not get the full speed of your CPU. Traceback (most recent call last): File "tools/infer_simple.py", line 162, in <module> main(args) File "tools/infer_simple.py", line 108, in main merge_cfg_from_file(args.cfg) File "/content/drive/My Drive/seg_every_thing/detectron/detectron/core/config.py", line 1152, in merge_cfg_from_file _merge_a_into_b(yaml_cfg, __C) File "/content/drive/My Drive/seg_every_thing/detectron/detectron/core/config.py", line 1212, in _merge_a_into_b _merge_a_into_b(v, b[k], stack=stack_push) File "/content/drive/My Drive/seg_every_thing/detectron/detectron/core/config.py", line 1202, in _merge_a_into_b raise KeyError('Non-existent config key: {}'.format(full_key)) KeyError: u'Non-existent config key: MRCNN.BBOX2MASK'

I was looking for this error and came across another same error issue on your page "#2" which is been closed. I read the solution there. However, I am guessing my problem is due to the new version of Detectron. Now available Detectron folder does not contain the lib folder in it. I have not gone thoroughly into the codes so, please help me to solve this.
Thanks in advance.

  • PYTHONPATH environment variable: /env/python:/content/drive/My Drive/seg_every_thing/detectron/detectron

  • python --version output: 2.7

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant