Comments (2)
The problem is in this statement (duh) in Augment.mirror():
return tf.cond(uniform_random < 0.5, lambda: tf.tuple([image, boxes]), lambda: doMirror(image, boxes))
I think wrapping the false_fn (the last arg in the tf.cond) with a tf.tuple should do the trick.
return tf.cond(uniform_random < 0.5, lambda: tf.tuple([image, boxes]), lambda: tf.tuple(doMirror(image, boxes)))
This same error also appears in RFCN-tensorflow.Utils.MultiGather.gatherTopK():
values, indices = tf.cond(isMoreThanK, lambda: tf.nn.top_k(t, k=k, sorted=sorted), lambda: tf.tuple([t, tf.zeros((0,1), tf.int32)]))
but this change clears the error:
values, indices = tf.cond(isMoreThanK, lambda: tf.tuple(tf.nn.top_k(t, k=k, sorted=sorted)), lambda: tf.tuple([t, tf.zeros((0,1), tf.int32)]))
from rfcn-tensorflow.
Fixed, tested with version 1.4.1, it works.
Thanks for the support :).
from rfcn-tensorflow.
Related Issues (20)
- What is purpose of offset? HOT 2
- How to understanding offset? HOT 2
- Need help badly!!!!!!!!!!!!!
- Helping! error when run test.py HOT 3
- Helping! Why we need add GT boxes when calculating refinement loss??
- tensorflow 1.7.0 jtensorflow.python.framework.errors_impl.InvalidArgumentError: Input to reshape is a tensor with 8218 values, but the requested shape has 9988 HOT 1
- why is not run in cuda9 HOT 1
- How to do fine tune HOT 1
- cannot open shared object file HOT 3
- TF 1.13 says: "The two structures don't have the same nested structure."
- Incompatible shapes: [8873,1] vs. [9432,2] HOT 5
- some Error When train with coco2014 : InvalidArgumentError (see above for traceback): Incompatible shapes: [9645,1] vs. [9988,2] HOT 3
- Windows version
- how to train my own data????????????? HOT 1
- Validation results on cocoval 2014 data set were poor, with Map less than 10%.
- Error make HOT 2
- What is the profile argument
- how to compute val loss during training
- evaluate model
- Tensorflow 2 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 rfcn-tensorflow.