Comments (5)
While training the model I am getting the error
InvalidArgumentError (see above for traceback): Incompatible shapes: [80,1] vs. [160,1] [[Node: prediction/logistic_loss/mul = Mul[T=DT_FLOAT, _device="/job:localhost/replica:0/task:0/cpu:0"](prediction/Squeeze, prediction/ToFloat)]]
I am running it with python3, any idea what might be causing the issue?
from chatbot-retrieval.
same error for me.
tensorflow.python.framework.errors_impl.InvalidArgumentError: Incompatible shapes: [80,1] vs. [160,1]
[[Node: prediction/logistic_loss/mul = Mul[T=DT_FLOAT, _device="/job:localhost/replica:0/task:0/cpu:0"](prediction/Squeeze, prediction/ToFloat)]]
from chatbot-retrieval.
I just had this strange issue as well. Occurred after calling evaluate on a just-trained Estimator passing in the following metrics dict:
{'auc': <function streaming_auc at 0x49226e0>, 'recall': <function streaming_recall at 0x49225f0>, 'precision': <function streaming_precision at 0x4922578>, 'confusion_matrix': <function confusion_matrix at 0x4730d70>, 'accuracy': <function streaming_accuracy at 0x4922500>}
Traceback is below:
Traceback (most recent call last):
File "main.py", line 301, in <module>
tf.app.run()
File "/usr/lib/python2.7/dist-packages/tensorflow/python/platform/app.py", line 30, in run
sys.exit(main(sys.argv))
File "main.py", line 220, in main
eval_steps=1
File "/opt/projects/tensorflow/cross_validation/evaluate.py", line 54, in evaluate
metrics=metrics
File "/usr/lib/python2.7/dist-packages/tensorflow/contrib/learn/python/learn/estimators/estimator.py", line 356, in evaluate
name=name)
File "/usr/lib/python2.7/dist-packages/tensorflow/contrib/learn/python/learn/estimators/estimator.py", line 641, in _evaluate_model
max_steps=steps)
File "/usr/lib/python2.7/dist-packages/tensorflow/contrib/learn/python/learn/graph_actions.py", line 773, in evaluate
_write_summary_results(output_dir, eval_results, current_global_step)
File "/usr/lib/python2.7/dist-packages/tensorflow/contrib/learn/python/learn/graph_actions.py", line 613, in _write_summary_results
_eval_results_to_str(eval_results))
File "/usr/lib/python2.7/dist-packages/tensorflow/contrib/learn/python/learn/graph_actions.py", line 607, in _eval_results_to_str
return ', '.join('%s = %s' % (k, v) for k, v in eval_results.items())
AttributeError: 'NoneType' object has no attribute 'items'
from chatbot-retrieval.
Never mind, this is a direct result from having a model that hasn't been trained, i.e. no weights or other variables saved. This can result from trying to use training files that don't exist when fit
is called. If you need help debugging this, use tf.logging.set_verbosity(tf.logging.DEBUG)
and look at the logs carefully to see what's going on. The Estimator will not fail due to user misconfiguration
from chatbot-retrieval.
Some error for me.
InvalidArgumentError (see above for traceback): Incompatible shapes: [80,1] vs. [160,1]
[[Node: prediction/logistic_loss/mul = Mul[T=DT_FLOAT, _device="/job:localhost/replica:0/task:0/cpu:0"](prediction/Squeeze, prediction/ToFloat)]]
from chatbot-retrieval.
Related Issues (20)
- any code for tensoflow > 2.0
- 这个代码是否可以用于中文状态下的封闭域问答? HOT 6
- How to solve AttributeError: module 'tensorflow.contrib.learn' has no attribute 'estimators' HOT 4
- Derive actual response from the probability? Just wondering how do I generate actual response from this model? HOT 1
- Gettin error while running idc_train.py HOT 3
- How to select candidate answers when predict HOT 1
- How to Deal with Context of multiple column ?
- How can I export/serve this model using saved_model_cli ?
- How to stops training after specied number of steps? HOT 1
- InvalidArgumentError (see above for traceback): indices[24,12] = 135816 is not in [0, 91620)
- InvalidArgumentError: Name: <unknown>, Feature: distractor_1 (data type: int64) is required but could not be found. [[{{node read_batch_features_eval/ParseExample/ParseExample}}]]
- InvalidArgumentError (see above for traceback): indices[7,16] = 99296 is not in [0, 91620)
- ValueError: Shapes (10, ?, 160) and () are incompatible
- Incompatible shapes: [20,1] vs. [80,1] HOT 2
- UnicodeDecodeError: 'gbk' codec can't decode byte 0xbf in position 2: illegal multibyte sequence HOT 1
- The question about Tensorflow about Incompatible shapes: [730,5] vs. [30,5]
- udc_test.py出错
- Data missing from drive
- any examples of chatbot conversation?
- InvalidArgumentError: Incompatible shapes: [128,14,14,16] vs. [8] [[{{node max_unpooling2d_4/max_unpooling2d_4/mul_4}}]] [[{{node Mean_1}}]] HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from chatbot-retrieval.