Skip to content

Create documentation for diamond-classifier module #941

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
ajisutiono wants to merge 1 commit into
base: master
Choose a base branch
from
+20 −0
Open

Create documentation for diamond-classifier module #941

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
20 changes: 20 additions & 0 deletions tfhub_dev/assets/ajisutiono/diamond-classifier/1.md
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,20 @@
# Module ajisutiono/diamond-classifier/1

<!-- metadata -->
asset-path: https://github.com/ajisutiono/diamond-price-savedmodel/releases/download/v1.0.0/my_model.tar.gz
module-type: image-classification
fine-tunable: true
format: saved_model_2
license: apache-2.0
-->

Model Jaringan Saraf Tiruan (Neural Network) modern berbasis Keras 3 untuk memprediksi kategori harga berlian (murah atau mahal) berdasarkan karakteristik dimensi fisiknya.

### Deskripsi Model
Model ini menggunakan arsitektur Keras Sequential dengan pre-processing layer Normalization bawaan TensorFlow versi terbaru untuk menyeragamkan skala fitur angka secara dinamis. Berdasarkan hasil pelatihan selama 10 Epochs, model ini berhasil mencapai akurasi seimbang sebesar 94.5% baik pada data training maupun data validation (kondisi Good Fit).

### Struktur Input
Model menerima input berbentuk tensor numerik float32 dengan dimensi/shape `(None, 5)` yang merepresentasikan fitur fisik berlian secara berurutan: `['carat', 'depth', 'x', 'y', 'z']`.

### Struktur Output
Model mengembalikan skor probabilitas biner lewat 1 output neuron (Dense). Nilai yang mendekati 0 mengindikasikan harga murah (≤ $1000) dan nilai yang mendekati 1 mengindikasikan harga mahal (> $1000).