An Error when load the pretrained model?

[idealboy]

when I load the pretrained model trained on ml-images(ckpt-resnet101-mlimages), an error occur as follow:

KeyError: u'TfplusAllreduce

my loaded code is:
saver = tf.train.import_meta_graph("./pretrain_model/ckpt-resnet101-mlimages/model.ckpt.meta")
saver.restore(sess, "./pretrain_model/ckpt-resnet101-mlimages")

my tensorflow version is 1.10.0

thank you for your advision, sincerely!

[Baoyuan Wu]

@idealboy Maybe you should try "saver = tf.train.Saver(tf.global_variables())
saver.restore(sess, FLAGS.model_dir)". Please refer to image_classification.py and image_classification.sh for details.

[PapaMadeleine]

get the same error. my tensorflow version is 1.6

[Willing Chen]

same error, my tf version is 1.10.0

[Willing Chen]

@idealboy Maybe you should try "saver = tf.train.Saver(tf.global_variables())
saver.restore(sess, FLAGS.model_dir)". Please refer to image_classification.py and image_classification.sh for details.

I try,but fail

[xyy19920105]

I have the same error

[potter]

有谁解决了这个问题吗

[Xiaoqi Li]

�I downloaded the pretrained-checkpoint and figured out the checkpiont-file absenced, then I manually created a checkpoint file
with the following code, it works!!
######################
ckpt =tf.train.get_checkpoint_state(checkpoint_dir)
sess = tf.Session()
saver = tf.train.Saver(tf.global_variables())
if ckpt and ckpt.model_checkpoint_path:
saver.restore(sess,ckpt.model_checkpoint_path)
#####################
my ENV:
linux
tensorflow-gpu==1.13.1
python==3.6.3