-
Around 36 seconds into [this YouTube Video](https://www.youtube.com/watch?v=4_TmPA-qw9U), you can see green, yellow and red shading on top of the video feed. How would I go about replicating that? I…
-
I have the newest Keras 2.1.6 and all_methods.py crashes for PatternNet (`TypeError: softmax() got an unexpected keyword argument 'axis'` etc.). However, it works with Keras 2.1.5.
Tensorflow was o…
-
The branch apicaffe_cleanup has a lot of enhancements (segmentation training and full implementation of ProcessDriver for caffe training) while it is supposed to support old features as well. We have…
-
Hello,
I’ve been trying to implementing a deconvolutional network which takes in RGB images (128x128x3) from a dataset (the images contains 21 object classes) and then outputs probability maps of siz…
-
## Introduction
The results from tensorboard are better than the prediction time.
### Loss from tensorboard
Roughly 0.7 after 1 day of training
, so the Softmax operator in mxnet can't handle it(just my opinion);
I want solve it through:
1. add a new…
-
Hi! I am getting the following error when running the code:
`ValueError: Layer weight shape (3, 64, 3, 3) not compatible with provided weight shape (3, 3, 3, 64)`
I wonder if this has to do with…
-
In Pro. Zeiler's paper < Visualizing and Understanding Convolutional Networks >.
http://www.matthewzeiler.com/pubs/arxive2013/arxive2013.pdf
Operation: Switch_pool() and Switch_upppool() are needed …