# 2021/05/12
###### tags: `進度報告`

## 現在進度
### 論文閱讀
* [Survey 2019-2021](https://hackmd.io/PhLvyxlfST22JBgF7vBSxQ?view)
### 農業計畫
#### Dataset
* All labels in train.csv:

| label | count | img |
| ------------------------------- | ----- | ------------------------------------ |
| scab | 4826 |  |
| healthy | 4624 |  |
| frog_eye_leaf_spot | 3181 |  |
| rust | 1860 |  |
| complex | 1602 |  |
| powdery_mildew | 1184 |  |
| scab frog_eye_leaf_spot | 686 |  |
| scab frog_eye_leaf_spot complex | 200 |  |
| frog_eye_leaf_spot complex | 165 |  |
| rust frog_eye_leaf_spot | 120 |  |
| rust complex | 97 |  |
| powdery_mildew complex | 87 |  |

* Labels
There are only 4 diseases and `complex`, `healthy` in this dataset.
`complex` means that the disease is too complicated to be recognized

> Unhealthy leaves with too many diseases to classify visually will have the complex class, and may also have a subset of the diseases identified.

    healthy               4624
    scab                  5712
    frog_eye_leaf_spot    4352
    complex               2151
    rust                  2077
    powdery_mildew        1271

#### Experimental results
* Single-label method + Single-label dataset
Use Label Powerset to define labels.
Contain 12 labels in full dataset.
`ACC `: 0.8026
* Multi-label method + Single-label dataset
Same labels rule as method 1
Only change model into multi-label mode.
`ACC` : 0.8133
* Multi-label method + Mingle-label dataset
6 labels (4 diseases + complex and healthy)
scab frog_eye_leaf_spot complex is seen to 3 labels.
`ACC `: 0.8484
#### 現在問題
* 自己測試ACC還可以 但Kaggle結果不好
* 用single結果不好 `推測是因為有complex 所以會誤判`
### 實驗室
* 影像處理考卷&作業批改
### 專題生進度
* 專題期末報告 (還在改)
* PPT 製作 (還在改)
* 海報 (設計中)
---
## 未來計畫
### 論文閱讀
* Survey 2019-2021論文 (還在看)
### 農業計畫
### 目前想法
* 目前想法
* 改現在常用的架構中的骨幹
* RepVGG (比較新 比較好奇 聽說實驗結果不錯)
* EfficientNet
* 可能看一下mutil - label的東西
* 學Pytorch