-
Notifications
You must be signed in to change notification settings - Fork 174
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Error while executing demo.py #82
Comments
I am experiencing the same issue while trying to run the demo in Google Colab, @chanchalIITP - were you able to resolve this by any chance ? |
same question |
this is related to ? |
Here's an idea for anyone else who is having this error and stumbles across this issue: this may be due to not modifying the path in Line 20 in 9d1ee19
|
Hi. I have already downloaded all the required files. Execution of demo.py gives model based error(checkpoint issue). I am attaching the error trace. Please help. thank you in advance.
File "demo.py", line 47, in
model.restore(session)
File "/Data/chanchal_1821cs11/e2e-coref-master_fresh/coref_model.py", line 94, in restore
saver.restore(session, checkpoint_path)
File "/Data/chanchal_1821cs11/anaconda3/envs/coref_py2/lib/python2.7/site-packages/tensorflow/python/training/saver.py", line 1312, in restore
err, "a mismatch between the current graph and the graph")
tensorflow.python.framework.errors_impl.InvalidArgumentError: Restoring from checkpoint failed. This is most likely due to a mismatch between the current graph and the graph from the checkpoint. Please ensure that you have not altered the graph expected based on the checkpoint. Original error:
Assign requires shapes of both tensors to match. lhs shape= [1,8] rhs shape= [115,8]
[[node save_2/Assign_4 (defined at /Data/chanchal_1821cs11/e2e-coref-master_fresh/coref_model.py:90) ]]
Caused by op u'save_2/Assign_4', defined at:
File "demo.py", line 47, in
model.restore(session)
File "/Data/chanchal_1821cs11/e2e-coref-master_fresh/coref_model.py", line 90, in restore
saver = tf.train.Saver(vars_to_restore)
File "/Data/chanchal_1821cs11/anaconda3/envs/coref_py2/lib/python2.7/site-packages/tensorflow/python/training/saver.py", line 832, in init
self.build()
File "/Data/chanchal_1821cs11/anaconda3/envs/coref_py2/lib/python2.7/site-packages/tensorflow/python/training/saver.py", line 844, in build
self._build(self._filename, build_save=True, build_restore=True)
File "/Data/chanchal_1821cs11/anaconda3/envs/coref_py2/lib/python2.7/site-packages/tensorflow/python/training/saver.py", line 881, in _build
build_save=build_save, build_restore=build_restore)
File "/Data/chanchal_1821cs11/anaconda3/envs/coref_py2/lib/python2.7/site-packages/tensorflow/python/training/saver.py", line 513, in _build_internal
restore_sequentially, reshape)
File "/Data/chanchal_1821cs11/anaconda3/envs/coref_py2/lib/python2.7/site-packages/tensorflow/python/training/saver.py", line 354, in _AddRestoreOps
assign_ops.append(saveable.restore(saveable_tensors, shapes))
File "/Data/chanchal_1821cs11/anaconda3/envs/coref_py2/lib/python2.7/site-packages/tensorflow/python/training/saving/saveable_object_util.py", line 73, in restore
self.op.get_shape().is_fully_defined())
File "/Data/chanchal_1821cs11/anaconda3/envs/coref_py2/lib/python2.7/site-packages/tensorflow/python/ops/state_ops.py", line 223, in assign
validate_shape=validate_shape)
File "/Data/chanchal_1821cs11/anaconda3/envs/coref_py2/lib/python2.7/site-packages/tensorflow/python/ops/gen_state_ops.py", line 64, in assign
use_locking=use_locking, name=name)
File "/Data/chanchal_1821cs11/anaconda3/envs/coref_py2/lib/python2.7/site-packages/tensorflow/python/framework/op_def_library.py", line 788, in _apply_op_helper
op_def=op_def)
File "/Data/chanchal_1821cs11/anaconda3/envs/coref_py2/lib/python2.7/site-packages/tensorflow/python/util/deprecation.py", line 507, in new_func
return func(*args, **kwargs)
File "/Data/chanchal_1821cs11/anaconda3/envs/coref_py2/lib/python2.7/site-packages/tensorflow/python/framework/ops.py", line 3300, in create_op
op_def=op_def)
File "/Data/chanchal_1821cs11/anaconda3/envs/coref_py2/lib/python2.7/site-packages/tensorflow/python/framework/ops.py", line 1801, in init
self._traceback = tf_stack.extract_stack()
InvalidArgumentError (see above for traceback): Restoring from checkpoint failed. This is most likely due to a mismatch between the current graph and the graph from the checkpoint. Please ensure that you have not altered the graph expected based on the checkpoint. Original error:
Assign requires shapes of both tensors to match. lhs shape= [1,8] rhs shape= [115,8]
[[node save_2/Assign_4 (defined at /Data/chanchal_1821cs11/e2e-coref-master_fresh/coref_model.py:90) ]]
The text was updated successfully, but these errors were encountered: