You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I'm following the guide for serving the inception model with Docker, however I am getting an error when I try to export the downloaded model. When I run this command inside of my docker container:
I get an error: Traceback (most recent call last): File "/serving/bazel-bin/tensorflow_serving/example/inception_export.runfiles/tf_serving/tensorflow_serving/example/inception_export.py", line 169, in <module> tf.app.run() File "/serving/bazel-bin/tensorflow_serving/example/inception_export.runfiles/org_tensorflow/tensorflow/python/platform/app.py", line 44, in run _sys.exit(main(_sys.argv[:1] + flags_passthrough)) File "/serving/bazel-bin/tensorflow_serving/example/inception_export.runfiles/tf_serving/tensorflow_serving/example/inception_export.py", line 165, in main export() File "/serving/bazel-bin/tensorflow_serving/example/inception_export.runfiles/tf_serving/tensorflow_serving/example/inception_export.py", line 79, in export logits, _ = inception_model.inference(images, NUM_CLASSES + 1) File "/serving/bazel-bin/tensorflow_serving/example/inception_export.runfiles/inception_model/inception/inception_model.py", line 90, in inference _activation_summaries(endpoints) File "/serving/bazel-bin/tensorflow_serving/example/inception_export.runfiles/inception_model/inception/inception_model.py", line 157, in _activation_summaries _activation_summary(act) File "/serving/bazel-bin/tensorflow_serving/example/inception_export.runfiles/inception_model/inception/inception_model.py", line 150, in _activation_summary tf.histogram_summary(tensor_name + '/activations', x) AttributeError: 'module' object has no attribute 'histogram_summary'
Has anyone else seen this? Can someone help me move past it? The only modifications that I've made that were not from the walkthrough were to the 2 lines in ops.py described in this issue #250
The text was updated successfully, but these errors were encountered:
Never mind. Leaving this here in case someone else needs it:
The API has changed, the method call in that file (/serving/bazel-bin/tensorflow_serving/example/inception_export.runfiles/inception_model/inception/inception_model.py) now needs to be tf.summary.histogram(... and the one below it (scalar) needs to be tf.summary.scalar(...
I'm following the guide for serving the inception model with Docker, however I am getting an error when I try to export the downloaded model. When I run this command inside of my docker container:
bazel-bin/tensorflow_serving/example/inception_export --checkpoint_dir=inception-v3 --export_dir=inception-export
I get an error:
Traceback (most recent call last): File "/serving/bazel-bin/tensorflow_serving/example/inception_export.runfiles/tf_serving/tensorflow_serving/example/inception_export.py", line 169, in <module> tf.app.run() File "/serving/bazel-bin/tensorflow_serving/example/inception_export.runfiles/org_tensorflow/tensorflow/python/platform/app.py", line 44, in run _sys.exit(main(_sys.argv[:1] + flags_passthrough)) File "/serving/bazel-bin/tensorflow_serving/example/inception_export.runfiles/tf_serving/tensorflow_serving/example/inception_export.py", line 165, in main export() File "/serving/bazel-bin/tensorflow_serving/example/inception_export.runfiles/tf_serving/tensorflow_serving/example/inception_export.py", line 79, in export logits, _ = inception_model.inference(images, NUM_CLASSES + 1) File "/serving/bazel-bin/tensorflow_serving/example/inception_export.runfiles/inception_model/inception/inception_model.py", line 90, in inference _activation_summaries(endpoints) File "/serving/bazel-bin/tensorflow_serving/example/inception_export.runfiles/inception_model/inception/inception_model.py", line 157, in _activation_summaries _activation_summary(act) File "/serving/bazel-bin/tensorflow_serving/example/inception_export.runfiles/inception_model/inception/inception_model.py", line 150, in _activation_summary tf.histogram_summary(tensor_name + '/activations', x) AttributeError: 'module' object has no attribute 'histogram_summary'
Has anyone else seen this? Can someone help me move past it? The only modifications that I've made that were not from the walkthrough were to the 2 lines in ops.py described in this issue
#250
The text was updated successfully, but these errors were encountered: