Comments (5)
It looks like the issue is related to the use of the Lambda
layer in your code. The error message suggests that there's a mix of tensors and non-tensors in a nested Lambda
call, specifically related to the mask
argument.
The error might be occurring because the Lambda
layer is expecting a tensor for its mask
argument, but it's receiving a list with None
and a tensor instead. To resolve this, you can try modifying the Lambda
layer to explicitly handle the mask
argument. Here's an updated version of the Lambda
layer that should resolve the issue:
attention_context = Lambda(lambda x: tf.einsum('ijk,ijl->ikl', x[0], x[1]), mask=lambda inputs, mask: mask[1])([attention_scores, se3])
In this modification, the mask
argument is explicitly handled to pass the mask from the se3
input to the Lambda
layer.
Please try this modification and see if it resolves the issue. If the error persists, there may be other issues in your code that need to be addressed.
from tensorflow.
@ShahidRRRRRR Please print the shapes of attention_scores and se3 before passing them to the Lambda layer to verify compatibility. If you still face the issue then, could you please ensure to use the latest TF version and share the code in a notebook or colab gist?
Thank you!
from tensorflow.
This issue is stale because it has been open for 7 days with no activity. It will be closed if no further activity occurs. Thank you.
from tensorflow.
This issue was closed because it has been inactive for 7 days since being marked as stale. Please reopen if you'd like to work on this further.
from tensorflow.
Are you satisfied with the resolution of your issue?
Yes
No
from tensorflow.
Related Issues (20)
- model.summary() broken for custom models subclassed from tf.keras.Model HOT 2
- opal_wrapper-wrapper-data.txt not found HOT 2
- Unable to run Object Detection API i.e. AttributeError: module 'keras._tf_keras.keras.layers' has no attribute 'experimental' HOT 3
- loss growing to negative infinity val accuracy remaining constant, testing accuracy above 100% HOT 3
- TFLite Op type not registered (RegexSplitWithOffsets) in Swift
- Unexpected input dimension (tflite C_API library) HOT 5
- Cannot convert model to tflite
- IntegerLookup layer performance issue when inited with vocabulary HOT 5
- `Check failed` in `tf.raw_ops.CropAndResize` when `boxes` and `box_ind` are empty.
- `Check failed` and other errors in `tf.unstack` when dtype of `axis` is `uint64`. HOT 2
- `Check failed` in `tf.strings.unsorted_segment_join` when the rank of `inputs` is larger than 1 and the value of `num_segments` is too large. HOT 1
- Some `Check Failed` errors in `tf.raw_ops.Unbatch` HOT 2
- `Overflow` in `tf.raw_ops.DenseBincount` when the value of `size` is too large. HOT 1
- `Check failed` in `tf.raw_ops.UnbatchGrad` when the input of `original_input` is empty.
- Suggestion: Chatbot Integration for TensorFlow API Assistance HOT 1
- `segmentation fault` in `tf.raw_ops.AddManySparseToTensorsMap` when `sparse_indices` and `sparse_values` are empty and `sparse_shape` is too large.
- Getting [java.lang.IllegalArgumentException: Internal error: Error applying delegate] error while applying GPU Delegate HOT 2
- `Check failed` in `tf.transpose`, `tf.raw_ops.Transpose` and `tf.compat.v1.transpose` when the values of `perm` have negative numbers.
- `Check failed` in `tf.image.crop_and_resize` and `tf.compat.v1.image.crop_and_resize` when `boxes` and `box_indices` are empty. HOT 3
- `Check failed` and `segmentation fault` in `tf.raw_ops.AudioSpectrogram`.
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 tensorflow.