rky0930
commented
6 years ago Sorry for late reply. I think the error occurred at a line i didn't change. I guess non-max-suppression_fn couldn't get the score info. I don't know why .. May i check your code and config file ?
Hi I replaced all the files mentioned and compiled the .proto files. Now when I'm trying start the training process using train.py I get the following error:
Traceback (most recent call last): File "train.py", line 167, in <module> tf.app.run() File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/platform/app.py", line 124, in run _sys.exit(main(argv)) File "train.py", line 163, in main worker_job_name, is_chief, FLAGS.train_dir) File "/git/bda/fridge/fridge/tf_objectdetection_api/object_detection/trainer.py", line 247, in train clones = model_deploy.create_clones(deploy_config, model_fn, [input_queue]) File "/git/bda/fridge/fridge/tf_objectdetection_api/slim/deployment/model_deploy.py", line 193, in create_clones outputs = model_fn(*args, **kwargs) File "/git/bda/fridge/fridge/tf_objectdetection_api/object_detection/trainer.py", line 164, in _create_losses resized_image, true_image_shape = detection_model.preprocess(image) File "/git/bda/fridge/fridge/tf_objectdetection_api/object_detection/meta_architectures/ssd_meta_arch.py", line 262, in preprocess dtype=[tf.float32, tf.int32]) File "/git/bda/fridge/fridge/tf_objectdetection_api/object_detection/utils/shape_utils.py", line 201, in static_or_dynamic_map_fn outputs = [fn(arg) for arg in tf.unstack(elems)] File "/git/bda/fridge/fridge/tf_objectdetection_api/object_detection/utils/shape_utils.py", line 201, in <listcomp> outputs = [fn(arg) for arg in tf.unstack(elems)] TypeError: batch_multiclass_non_max_suppression() missing 1 required positional argument: 'scores'Do you have any ideas what could be wrong?