Error while running the training command. Saying 'FasterRcnn' object has no attribute 'first_stage_only'

[hail2m15]

Traceback (most recent call last): File "train.py", line 163, in tf.app.run() File "C:\Users\haiL\Anaconda2\envs\tf15\lib\site-packages\tensorflow\python\platform\app.py", line 125, in run _sys.exit(main(argv)) File "train.py", line 159, in main worker_job_name, is_chief, FLAGS.train_dir) File "C:\tensorflow1\models\research\object_detection\trainer.py", line 193, in train detection_model = create_model_fn() File "C:\tensorflow1\models\research\object_detection\builders\model_builder.py", line 85, in build return _build_faster_rcnn_model(model_config.faster_rcnn, is_training) File "C:\tensorflow1\models\research\object_detection\builders\model_builder.py", line 231, in _build_faster_rcnn_model first_stage_only = frcnn_config.first_stage_only AttributeError: 'FasterRcnn' object has no attribute 'first_stage_only'

[pilaurent]

I do have the same error actually. Running on Windows 10. Trying atm but it is the same with tensorflow-gpu 1.9 as well as 1.5

[pilaurent]

While reading the code, all seems to be due to the model config within model_builder.py.

model_config: A model.proto object containing the config for the desired DetectionModel.

I just ran the protoc command in 2f. Compile Protobufs and run setup.py and the error vanished

For info, this is working with tensorflow-gpu 1.10.0 which depends on protobuf 3.6.1

[youraustin]

While reading the code, all seems to be due to the model config within model_builder.py.

model_config: A model.proto object containing the config for the desired DetectionModel.

I just ran the protoc command in 2f. Compile Protobufs and run setup.py and the error vanished

For info, this is working with tensorflow-gpu 1.10.0 which depends on protobuf 3.6.1

Did you solove it? would you mind help me? I did this project, the system is: windows 10+ anaconda+tensorflow 1.7. same error for me, I try many times but it always appear. Hope you could tell me how to make the error vanished.

[Umraz-Hussain1]

can someone please help to resolve this issue.while loading my .pth model im getting this error kindly help

---

AttributeError Traceback (most recent call last) /tmp/ipykernel_242074/2710145507.py in ----> 1 model.load_state_dict(torch.load('models/fasterrcnn_resnet50_fpn_pneumonia_detection.pth'))

~/anaconda3/envs/pytorch1/lib/python3.9/site-packages/torch/nn/modules/module.py in load_state_dict(self, state_dict, strict) 1453 # copy state_dict so _load_from_state_dict can modify it 1454 metadata = getattr(state_dict, '_metadata', None) -> 1455 state_dict = state_dict.copy() 1456 if metadata is not None: 1457 # mypy isn't aware that "_metadata" exists in state_dict

~/anaconda3/envs/pytorch1/lib/python3.9/site-packages/torch/nn/modules/module.py in getattr(self, name) 1175 if name in modules: 1176 return modules[name] -> 1177 raise AttributeError("'{}' object has no attribute '{}'".format( 1178 type(self).name, name)) 1179

AttributeError: 'FasterRCNN' object has no attribute 'copy'