(1) Crop disease is a widespread problem in the productivity and quality of agricultural production. It adversely affects the quality of crops. The cucumber is a frequently grown creeping vine plant that has few calories but is high in water and several vital vitamins and minerals. Due to the non-biological circumstances, cucumber diseases will adversely harm the yield and quality of cucumber and cause heavy economic losses to farmers. The traditional diagnosis of crop diseases is often time-consuming, laborious, ineffective, and subjective.

(2) In the recent era, computer vision approaches are very promising for handling these kinds of classification and detection tasks.

(3) To develop machine vision-based algorithms, a major cucumber dataset is illustrated containing eight types of cucumber classes, namely Anthracnose, Bacterial Wilt, Belly Rot, Downy Mildew, Pythium Fruit Rot, Gummy Stem Blight, Fresh leaves, and Fresh cucumber. Cucumber disease classifications are done with the cooperation of an expert from an agricultural institute.

(4) A total of 1280 images of cucumbers are collected from real fields. Then from these original images, a total of 6400 augmented images are produced using flipping, shearing, zooming, and rotation techniques to increase the data number. Sultana, Nusrat; Shorif, Sumaita Binte ; Akter, Morium ; Uddin, Mohammad Shorif (2022), “Cucumber Disease Recognition Dataset”, Mendeley Data, V1, doi: 10.17632/y6d3z6f8z9.1

Description

Dataset of TFRecords files made from Plant Pathology 2021 original competition data. Changes: * labels column of the initial train.csv DataFrame was binarized to multi-label format columns: complex, frog_eye_leaf_spot, healthy, powdery_mildew, rust, and scab * images were scaled to 512x512 * 77 duplicate images having different labels were removed (see the context in this notebook) * samples were stratified and split into 5 folds (see corresponding folders fold_0:fold_4) * images were heavily augmented with albumentations library (for raw images see this dataset) * each folder contains 5 copies of randomly augmented initial images (so that the model never meets the same images)

I suggest adding all 5 datasets to your notebook: 4 augmented datasets = 20 epochs of unique images (1, 2, 3, 4) + 1 raw dataset for validation here.

For a complete example see my TPU Training Notebook

Contents:

• preprocessed DataFrame train.csv
• fold indexes DataFrame folds.csv
• fold_0:fold_4 folders containing 64 .tfrec files, respectively, with feature map shown below: feature_map = { 'image': tf.io.FixedLenFeature([], tf.string), 'name': tf.io.FixedLenFeature([], tf.string), 'complex': tf.io.FixedLenFeature([], tf.int64), 'frog_eye_leaf_spot': tf.io.FixedLenFeature([], tf.int64), 'healthy': tf.io.FixedLenFeature([], tf.int64), 'powdery_mildew': tf.io.FixedLenFeature([], tf.int64), 'rust': tf.io.FixedLenFeature([], tf.int64), 'scab': tf.io.FixedLenFeature([], tf.int64)} ### Acknowledgements
• photo from Unsplash here