
CoderDennis
Machine Learning in Elixir: chapter 7 CNN model accuracy no better than MLP (page 160)
When training the cnn_model, I get the following output:
Epoch: 0, Batch: 150, accuracy: 0.4985513 loss: 7.6424022
Epoch: 1, Batch: 163, accuracy: 0.4992854 loss: 7.6783161
Epoch: 2, Batch: 176, accuracy: 0.5000441 loss: 7.6865749
Epoch: 3, Batch: 139, accuracy: 0.4983259 loss: 7.6991839
Epoch: 4, Batch: 152, accuracy: 0.4988766 loss: 7.6995916
%{
"conv_0" => %{
"bias" => #Nx.Tensor<
f32[32]
EXLA.Backend<host:0, 0.1357844422.1979580433.82179>
[NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN]
>,
"kernel" => #Nx.Tensor<
f32[3][3][3][32]
EXLA.Backend<host:0, 0.1357844422.1979580433.82180>
[
[
[
[NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN],
[NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, ...],
...
],
...
],
...
]
>
},
"conv_1" => %{
"bias" => #Nx.Tensor<
f32[64]
EXLA.Backend<host:0, 0.1357844422.1979580433.82181>
[NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, -0.0071477023884654045, NaN, NaN, NaN, NaN, 0.0, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, ...]
>,
"kernel" => #Nx.Tensor<
f32[3][3][32][64]
EXLA.Backend<host:0, 0.1357844422.1979580433.82182>
[
[
[
[NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, ...],
...
],
...
],
...
]
>
},
"conv_2" => %{
"bias" => #Nx.Tensor<
f32[128]
EXLA.Backend<host:0, 0.1357844422.1979580433.82183>
[0.0, NaN, NaN, NaN, NaN, NaN, NaN, NaN, 0.005036031361669302, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, ...]
>,
"kernel" => #Nx.Tensor<
f32[3][3][64][128]
EXLA.Backend<host:0, 0.1357844422.1979580433.82184>
[
[
[
[NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, ...],
...
],
...
],
...
]
>
},
"dense_0" => %{
"bias" => #Nx.Tensor<
f32[128]
EXLA.Backend<host:0, 0.1357844422.1979580433.82185>
[NaN, -0.005992305930703878, -0.006005365401506424, -0.004664595704525709, NaN, NaN, NaN, -5.619042203761637e-4, 0.0, NaN, -0.005999671295285225, -6.131592726887902e-6, NaN, 0.0, NaN, 0.0, 0.0, NaN, NaN, -0.006002828478813171, -0.00600335793569684, 0.0, NaN, NaN, NaN, -0.006002923008054495, -0.006005282513797283, -0.00600528996437788, -0.0060048955492675304, -0.006004981696605682, NaN, -0.006004655733704567, -0.006005233619362116, NaN, -0.006004724185913801, -0.006005335133522749, -0.006005051080137491, -0.006004408933222294, NaN, -0.006005355156958103, 0.0, -0.006005344912409782, 0.0, NaN, -0.005991040728986263, ...]
>,
"kernel" => #Nx.Tensor<
f32[18432][128]
EXLA.Backend<host:0, 0.1357844422.1979580433.82186>
[
[NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, NaN, ...],
...
]
>
},
"dense_1" => %{
"bias" => #Nx.Tensor<
f32[1]
EXLA.Backend<host:0, 0.1357844422.1979580433.82187>
[NaN]
>,
"kernel" => #Nx.Tensor<
f32[128][1]
EXLA.Backend<host:0, 0.1357844422.1979580433.82188>
[
[NaN],
[NaN],
[NaN],
[NaN],
[NaN],
[NaN],
[NaN],
[NaN],
[NaN],
[NaN],
[NaN],
[NaN],
[NaN],
[NaN],
[NaN],
[NaN],
[NaN],
[NaN],
[NaN],
[NaN],
[NaN],
[NaN],
[NaN],
[NaN],
[NaN],
[NaN],
[NaN],
[NaN],
[NaN],
[NaN],
[NaN],
[NaN],
[NaN],
[NaN],
[NaN],
[NaN],
[NaN],
[NaN],
[NaN],
[NaN],
[NaN],
[NaN],
[NaN],
...
]
>
}
}
The accuracy of the mlp_model was Batch: 6, accuracy: 0.5078125
and the accuracy of this cnn_model is Batch: 6, accuracy: 0.4944196
which was slightly worse instead of the expected “significantly better.”
I reviewed all the code to make sure I hadn’t missed anything, but I couldn’t find anything that didn’t match.
I’m guessing the NaN
s in the trained model state are a problem, but I’m not sure how to fix that.
Marked As Solved

CoderDennis
Switching to Axon 0.7 resolved the issue.
Popular Pragmatic Bookshelf topics

page 37
ANTLRInputStream input = new ANTLRInputStream(is);
as of ANTLR 4 .8 should be:
CharStream stream = CharStreams.fromStream(i...
New

your book suggests to use Image.toByteData() to convert image to bytes, however I get the following error: "the getter ‘toByteData’ isn’t...
New

This is as much a suggestion as a question, as a note for others.
Locally the SGP30 wasn’t available, so I ordered a SGP40. On page 53, ...
New

I think I might have found a problem involving SwitchCompat, thumbTint, and trackTint.
As entered, the SwitchCompat changes color to hol...
New

When running tox for the first time, I got the following error:
ERROR: InterpreterNotFound: python3.10
I realised that I was running ...
New

The markup used to display the uploaded image results in a Phoenix.LiveView.HTMLTokenizer.ParseError error.
lib/pento_web/live/product_l...
New

I’m a newbie to Rails 7 and have hit an issue with the bin/Dev script mentioned on pages 112-113.
Iteration A1 - Seeing the list of prod...
New

The allprojects block listed on page 245 produces the following error when syncing gradle:
“org.gradle.api.GradleScriptException: A prob...
New

I got this error when executing the plot files on macOS Ventura 13.0.1 with Python 3.10.8 and matplotlib 3.6.1:
programming_ML/code/03_...
New

Hello faithful readers! If you have tried to follow along in the book, you are asked to start up the dev environment via dx/build and ar...
New
Other popular topics

Please tell us what is your preferred monitor setup for programming(not gaming) and why you have chosen it.
Does your monitor have eye p...
New
New

I have seen the keycaps I want - they are due for a group-buy this week but won’t be delivered until October next year!!! :rofl:
The Ser...
New

The V Programming Language
Simple language for building maintainable programs
V is already mentioned couple of times in the forum, but I...
New

Think Again 50% Off Sale »
The theme of this sale is new perspectives on familiar topics.
Enter coupon code ThinkAgain2021 at checkout t...
New

Build efficient applications that exploit the unique benefits of a pure functional language, learning from an engineer who uses Haskell t...
New

The File System Access API with Origin Private File System.
WebKit supports new API that makes it possible for web apps to create, open,...
New

I am trying to crate a game for the Nintendo switch, I wanted to use Java as I am comfortable with that programming language. Can you use...
New

Will Swifties’ war on AI fakes spark a deepfake porn reckoning?
New

When agile experimentation at startups becomes a p-hacking trap
New
Categories:
Sub Categories:
Popular Portals
- /elixir
- /rust
- /wasm
- /ruby
- /erlang
- /phoenix
- /keyboards
- /rails
- /js
- /python
- /security
- /go
- /swift
- /vim
- /clojure
- /emacs
- /java
- /haskell
- /onivim
- /svelte
- /typescript
- /crystal
- /c-plus-plus
- /kotlin
- /tailwind
- /gleam
- /react
- /flutter
- /elm
- /ocaml
- /vscode
- /ash
- /opensuse
- /centos
- /php
- /deepseek
- /html
- /zig
- /scala
- /sublime-text
- /textmate
- /debian
- /nixos
- /lisp
- /agda
- /react-native
- /kubuntu
- /arch-linux
- /revery
- /ubuntu
- /spring
- /manjaro
- /django
- /diversity
- /nodejs
- /lua
- /julia
- /c
- /slackware
- /neovim