# pomelo_single-aug2
###### tags: `紀錄`

## dataset
categories 6
tain 27144
test 530

## fig explanation
b Training accurarcy
g Validation accurarcy
r Training loss
y Validation loss

## Eff B0 `爆了`


batch size 16
epochs 90
Loss 6.133
Accc 0.653

:::warning
validation_split=0.2 -> 會over fitting
所以改為 x_train, x_valid, y_train, y_valid = train_test_split(x_train , y_train , test_size=0.2, shuffle= True)
:::

---

## EfficientNet B0

Loss 0.210
Accc 0.943

## DenseNet 121

Loss 0.405
Accc 0.921