-
I am wondering how loss value looks like. Could you give some pictures of the loss during training?
-
Is there an example of having arraymancer look at a folder containing multiple classes in their own folders, specifying a train / test split, and generating a model based on that? Finally saving the m…
-
The comment of pseudo_cost() says: "This cost should have the same gradient but hopefully theano will use a more stable implementation of it." What does this mean actually? Is this implementation not…
ghost updated
9 years ago
-
Implement various feedback methods.
* How to handle looped layer outputs
* Specify scaling method wrt. `loops`
* How to handle backprop
- `unwrap` backprop
* And how to combine weights aft…
-
## Why
Machine Learning 輪講は最新の技術や論文を追うことで、エンジニアが「技術で解決できること」のレベルをあげていくことを目的にした会です。
prev.
## What
話したいことがある人はここにコメントしましょう！
面白いものを見つけた時点でとりあえず話すという宣言だけでもしましょう！
-
As of now it takes 12 hours to train on all 60,000 MNIST images...
tmerr updated
11 years ago
-
I was wondering if any of you has been using the **DAG** module of matconvnet? I have been mainly training **linear CNNs** and would like to train now **DAG networks**. Could anyone share their experi…
-
From the paper:
> During training we use sum of squared error loss. If the ground truth for some coordinate prediction is _tˆ*_ our gradient is the ground truth value (computed from the ground trut…
-
-
After installing the package, I attempted to train using the default config to train the TruFor. However, I encountered significant issues when trying to train on more than 2 GPUs. The training proces…