Unable to use pretrained model

[justaduck]

Unable to use pretrained model

[pengzhou1108]

When attempting to do a dry run of the network using the pretrained model checkpoint from Google Drive I am met with the traceback below. I am using Tensorflow 1.4 and Python 3.4 on Ubuntu 18.04.

Command: python3.4 dry_run.py --model_weights='./ckpt/model.ckpt-pretrained' --vis=True --dataset='single_img' --save-dir='./output'

WARNING:tensorflow:From dry_run.py:300: calling argmax (from tensorflow.python.ops.math_ops) with dimension is deprecated and will be removed in a future version.
Instructions for updating:
Use the `axis` argument instead
2020-10-27 22:17:21.911705: I tensorflow/core/platform/cpu_feature_guard.cc:137] Your CPU supports instructions that this TensorFlow binary was not compiled to use: SSE4.1 SSE4.2 AVX AVX2 FMA
Traceback (most recent call last):
  File "/usr/local/lib/python3.4/dist-packages/tensorflow/python/client/session.py", line 1323, in _do_call
    return fn(*args)
  File "/usr/local/lib/python3.4/dist-packages/tensorflow/python/client/session.py", line 1302, in _run_fn
    status, run_metadata)
  File "/usr/local/lib/python3.4/dist-packages/tensorflow/python/framework/errors_impl.py", line 473, in __exit__
    c_api.TF_GetCode(self.status.status))
tensorflow.python.framework.errors_impl.NotFoundError: Tensor name "discriminator/conv1_batchnorm1/pop_var" not found in checkpoint files ./ckpt/model.ckpt-pretrained
	 [[Node: save/RestoreV2_6 = RestoreV2[dtypes=[DT_FLOAT], _device="/job:localhost/replica:0/task:0/device:CPU:0"](_arg_save/Const_0_0, save/RestoreV2_6/tensor_names, save/RestoreV2_6/shape_and_slices)]]

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "dry_run.py", line 443, in <module>
    main()
  File "dry_run.py", line 325, in main
    load(loader, sess, args.model_weights)
  File "dry_run.py", line 89, in load
    saver.restore(sess, ckpt_path)
  File "/usr/local/lib/python3.4/dist-packages/tensorflow/python/training/saver.py", line 1666, in restore
    {self.saver_def.filename_tensor_name: save_path})
  File "/usr/local/lib/python3.4/dist-packages/tensorflow/python/client/session.py", line 889, in run
    run_metadata_ptr)
  File "/usr/local/lib/python3.4/dist-packages/tensorflow/python/client/session.py", line 1120, in _run
    feed_dict_tensor, options, run_metadata)
  File "/usr/local/lib/python3.4/dist-packages/tensorflow/python/client/session.py", line 1317, in _do_run
    options, run_metadata)
  File "/usr/local/lib/python3.4/dist-packages/tensorflow/python/client/session.py", line 1336, in _do_call
    raise type(e)(node_def, op, message)
tensorflow.python.framework.errors_impl.NotFoundError: Tensor name "discriminator/conv1_batchnorm1/pop_var" not found in checkpoint files ./ckpt/model.ckpt-pretrained
	 [[Node: save/RestoreV2_6 = RestoreV2[dtypes=[DT_FLOAT], _device="/job:localhost/replica:0/task:0/device:CPU:0"](_arg_save/Const_0_0, save/RestoreV2_6/tensor_names, save/RestoreV2_6/shape_and_slices)]]

Caused by op 'save/RestoreV2_6', defined at:
  File "dry_run.py", line 443, in <module>
    main()
  File "dry_run.py", line 324, in main
    loader = tf.train.Saver(var_list=restore_var_2)
  File "/usr/local/lib/python3.4/dist-packages/tensorflow/python/training/saver.py", line 1218, in __init__
    self.build()
  File "/usr/local/lib/python3.4/dist-packages/tensorflow/python/training/saver.py", line 1227, in build
    self._build(self._filename, build_save=True, build_restore=True)
  File "/usr/local/lib/python3.4/dist-packages/tensorflow/python/training/saver.py", line 1263, in _build
    build_save=build_save, build_restore=build_restore)
  File "/usr/local/lib/python3.4/dist-packages/tensorflow/python/training/saver.py", line 751, in _build_internal
    restore_sequentially, reshape)
  File "/usr/local/lib/python3.4/dist-packages/tensorflow/python/training/saver.py", line 427, in _AddRestoreOps
    tensors = self.restore_op(filename_tensor, saveable, preferred_shard)
  File "/usr/local/lib/python3.4/dist-packages/tensorflow/python/training/saver.py", line 267, in restore_op
    [spec.tensor.dtype])[0])
  File "/usr/local/lib/python3.4/dist-packages/tensorflow/python/ops/gen_io_ops.py", line 1021, in restore_v2
    shape_and_slices=shape_and_slices, dtypes=dtypes, name=name)
  File "/usr/local/lib/python3.4/dist-packages/tensorflow/python/framework/op_def_library.py", line 787, in _apply_op_helper
    op_def=op_def)
  File "/usr/local/lib/python3.4/dist-packages/tensorflow/python/framework/ops.py", line 2956, in create_op
    op_def=op_def)
  File "/usr/local/lib/python3.4/dist-packages/tensorflow/python/framework/ops.py", line 1470, in __init__
    self._traceback = self._graph._extract_stack()  # pylint: disable=protected-access

NotFoundError (see above for traceback): Tensor name "discriminator/conv1_batchnorm1/pop_var" not found in checkpoint files ./ckpt/model.ckpt-pretrained
	 [[Node: save/RestoreV2_6 = RestoreV2[dtypes=[DT_FLOAT], _device="/job:localhost/replica:0/task:0/device:CPU:0"](_arg_save/Const_0_0, save/RestoreV2_6/tensor_names, save/RestoreV2_6/shape_and_slices)]]

It is worth noting that the tensor not being found is not always the same. I have also gotten this error for "discriminator/conv1_1/b", "discriminator/conv5_batchnorm1/scale", "discriminator/fc9_voc12/filter", and "discriminator/conv5_batchnorm2/pop_mean" to name a few.

The model.ckpt-pretrained you are referring is only for deeplab checkpoint. To dry run the model, you might need to train GSR-Net and use it's checkpoint.