Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,69 @@
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- image-classification
|
| 5 |
+
- other-image-classification
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
datasets:
|
| 8 |
+
- beans
|
| 9 |
+
metrics:
|
| 10 |
+
- accuracy
|
| 11 |
+
model-index:
|
| 12 |
+
- name: vit-base-beans-demo-v2
|
| 13 |
+
results:
|
| 14 |
+
- task:
|
| 15 |
+
name: Image Classification
|
| 16 |
+
type: image-classification
|
| 17 |
+
dataset:
|
| 18 |
+
name: beans
|
| 19 |
+
type: beans
|
| 20 |
+
args: default
|
| 21 |
+
metrics:
|
| 22 |
+
- name: Accuracy
|
| 23 |
+
type: accuracy
|
| 24 |
+
value: 1.0
|
| 25 |
---
|
| 26 |
+
|
| 27 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 28 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 29 |
+
|
| 30 |
+
# vit-base-beans-demo-v2
|
| 31 |
+
|
| 32 |
+
Este modelo es una versión mejorada de [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) en el conjunto de datos beans.
|
| 33 |
+
Obtiene los siguientes resultados en el conjunto de evaluación:
|
| 34 |
+
|
| 35 |
+
- Pérdida: 0,0099
|
| 36 |
+
|
| 37 |
+
- Precisión: 1,0
|
| 38 |
+
|
| 39 |
+
## Descripción del modelo
|
| 40 |
+
|
| 41 |
+
Al procesar imágenes de hojas, la IA puede realizar análisis y comparaciones con una base de datos de imágenes previamente etiquetadas para identificar patrones y características distintivas asociadas con diferentes enfermedades o daños.
|
| 42 |
+
|
| 43 |
+
### Hiperparámetros de entrenamiento
|
| 44 |
+
|
| 45 |
+
Durante el entrenamiento se utilizaron los siguientes hiperparámetros:
|
| 46 |
+
- learning_rate 0.0002
|
| 47 |
+
- tamaño_lote_entrenamiento: 16
|
| 48 |
+
- tamaño_lote_evaluación: 8
|
| 49 |
+
- semilla: 42
|
| 50 |
+
- optimizador: Adam con betas=(0.9,0.999) y epsilon=1e-08
|
| 51 |
+
- lr_scheduler_type: lineal
|
| 52 |
+
- número de épocas: 5
|
| 53 |
+
- entrenamiento_precisión_mezclada: Native AMP
|
| 54 |
+
|
| 55 |
+
### Resultados del entrenamiento
|
| 56 |
+
|
| 57 |
+
| Pérdida de entrenamiento| Epoca | Paso | Pérdida de Validación | Precisión |
|
| 58 |
+
|:-----------------------:|:-----:|:----:|:---------------------:|:---------:|
|
| 59 |
+
| 0.0705 | 1.54 | 100 | 0.0562 | 0.9925 |
|
| 60 |
+
| 0.0123 | 3.08 | 200 | 0.0124 | 1.0 |
|
| 61 |
+
| 0.008 | 4.62 | 300 | 0.0099 | 1.0 |
|
| 62 |
+
|
| 63 |
+
|
| 64 |
+
### Framework versions
|
| 65 |
+
|
| 66 |
+
- Transformers 4.10.0.dev0
|
| 67 |
+
- Pytorch 1.9.0+cu102
|
| 68 |
+
- Conjuntos de datos 1.11.0
|
| 69 |
+
- Tokenizadores 0.10.3
|