Fashionpedia: Not able to restore model from given checkpoint

[mitraavi]

Thanks! for sharing the model training and inference codes, however, model restoration issue still persisting, here is what error I'm getting when I'm just trying to restore model from spinenet-143 ckpt:

CODE used to restore:

saver = tf.train.Saver()
with tf.Session() as sess:
saver.restore(sess, './model_spinenet_143/model.ckpt')

ERROR:

NotFoundError: Restoring from checkpoint failed. This is most likely due to a Variable name or other graph key that is missing from the checkpoint. Please ensure that you have not altered the graph expected based on the checkpoint. Original error:
root error(s) found.
(0) Not found: Key Variable not found in checkpoint
[[node save/RestoreV2 (defined at /usr/local/lib/python3.6/dist-packages/tensorflow_core/python/framework/ops.py:1748) ]]

I'm using tensorflow-gpu 1.15.0 version in colab, any hint as this error is occurring ?
Thanks

[mitraavi]

I'm able to run inference now on CPU after selecting the "spinenet config" file in the command line.

[mitraavi]

@richardaecn thanks! for pointing out the config selection issue

[richardaecn]

@mitraavi
Glad to hear that! Please feel free to close the issue.

[mitraavi]

Able to run inferences with suggestions from @richardaecn, hence closing this issue

[gireek]

@mitraavi Do you please mind sharing the colab where you were able to inference in Colab?

[gireek]

@richardaecn I get this error when running from the detection folder:

/usr/local/lib/python3.6/dist-packages/absl/flags/_validators.py:359: UserWarning: Flag --model has a non-None default value; therefore, mark_flag_as_required will pass even if flag is not specified in the command line!
  'command line!' % flag_name)
/usr/local/lib/python3.6/dist-packages/absl/flags/_validators.py:359: UserWarning: Flag --checkpoint_path has a non-None default value; therefore, mark_flag_as_required will pass even if flag is not specified in the command line!
  'command line!' % flag_name)
/usr/local/lib/python3.6/dist-packages/absl/flags/_validators.py:359: UserWarning: Flag --label_map_file has a non-None default value; therefore, mark_flag_as_required will pass even if flag is not specified in the command line!
  'command line!' % flag_name)
/usr/local/lib/python3.6/dist-packages/absl/flags/_validators.py:359: UserWarning: Flag --image_file_pattern has a non-None default value; therefore, mark_flag_as_required will pass even if flag is not specified in the command line!
  'command line!' % flag_name)
/usr/local/lib/python3.6/dist-packages/absl/flags/_validators.py:359: UserWarning: Flag --output_html has a non-None default value; therefore, mark_flag_as_required will pass even if flag is not specified in the command line!
  'command line!' % flag_name)
 - Loading the label map...
Traceback (most recent call last):
  File "inference.py", line 221, in <module>
    tf.app.run(main)
  File "/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/platform/app.py", line 40, in run
    _run(main=main, argv=argv, flags_parser=_parse_flags_tolerate_undef)
  File "/usr/local/lib/python3.6/dist-packages/absl/app.py", line 299, in run
    _run_main(main, args)
  File "/usr/local/lib/python3.6/dist-packages/absl/app.py", line 250, in _run_main
    sys.exit(main(argv))
  File "inference.py", line 102, in main
    params = config_factory.config_generator(FLAGS.model)
  File "/content/tpu/models/official/detection/configs/factory.py", line 43, in config_generator
    raise ValueError('Model %s is not supported.' % model)
ValueError: Model attribute_mask_rcnn is not supported.

How will it know to call the inference.py in the fashionpedia folder?

[mitraavi]

@gireek i did not run in colab, but i could run it in laptop without error and steps to run i already shared earlier.

[mitraavi]

@gireek further to the running env ...initially i tried to run it in colab, but due to path setting issue i was facing in colab similar to issue you reported earlier i switched to using laptop to run the same.