Error when loading MaskRCNN2Go

[hiankun]

When I run the run_eval.sh in the mask_rcnn_2go, the error message shows:

Traceback (most recent call last):
  File "code/eval_seg_cpu.py", line 193, in <module>
    main()
  File "code/eval_seg_cpu.py", line 188, in main
    net = load_model(args)
  File "code/eval_seg_cpu.py", line 73, in load_model
    args.net, args.init_net, is_run_init=True, is_create_net=True
  File "/home/thk/gitlab_proj/caffe2_models/mask_rcnn_2go/code/model_utils.py", line 19, in load_model_pb
    net.Proto().ParseFromString(open(net_file, "rb").read())
google.protobuf.message.DecodeError: Error parsing message

The content of my run_eval.sh is:

DATASET_IM_DIR="~/Downloads/val2014/" #"path_to_/coco_val2014"
DATASET_ANN="~/Downloads/instances_minival2014.json" #"path_to_/coco/instances_minival2014.json"

python code/eval_seg_cpu.py \
    --net "model/fp32/model.pb" \
    --init_net "model/fp32/model_init.pb" \
    --dataset "coco_2014_minival" \
    --dataset_dir "$DATASET_IM_DIR" \
    --dataset_ann "$DATASET_ANN" \
    --output_dir output \
    --min_size 320 \
    --max_size 640 \

The load_model_pb() has received the net_file path correctly, so the error seems to be caused by the model when it's been loaded.

Is the models given in the mask_rcnn_2go are bug free? Or did I do something wrong when trying the sample code?

[GBagley]

I'm having exactly the same problem. When I examine the model/fp32/model.pb file it looks like this:

version https://git-lfs.github.com/spec/v1
oid sha256:4bcdabf3da95da012922b85c52aa8508cf0b80b997ce26367811665b5dcf86d5
size 21840

Some searching online indicates that this may stem from an issue with unresolved merges and lfs in git, which can be resolved by the owner of the git package. If you could fix/update the files that would be great. I suspect that they are unusable as they are now. Thanks!

[RickLogi]

Ran into the same issue. FAIR also contributed the model to MLperf https://mlperf.org/ as part of the edge benchmarking https://github.com/mlperf/inference/tree/master/edge/object_segmentation/maskrcnn2go . I was able to get this model to run but had to modify run_eval.sh slightly to remove the extra -- from python code/eval_seg_cpu.py -- \ to python code/eval_seg_cpu.py \

[liangmuren]

Same problem, too

[mathpopo]

@RickLogi YES , i replace the pb file in https://github.com/mlperf/inference/tree/master/edge/object_segmentation/maskrcnn2go .so should the model pb model is error!

[mathpopo]

https://github.com/mlperf/inference/blob/master/others/edge/object_segmentation/maskrcnn2go/model/fp32/model.pb