Abstract
The Ash Gourd dataset is valuable since it was collected from the diverse regions within the district of Dhaka in Bangladesh. This dataset represents one of the first attempts to document, elicit, and categorize the health conditions of Ash Gourd (Benincasa hispida) plants in Bangladesh based on healthy samples, aphid plurality, downy mildew, leaf curl, and leaf miner-infested categories. Ash Gourd is one of the region's most important vegetables because of its nutritional and economic value; thus, it is essential to know diseases' manifestation in the improvement of agricultural productivity. The Ash Gourd dataset contains 2676 images, structured into the five categories of Healthy, Aphid, Downy Mildew, Leaf Curl, and Leaf Miner. All images in all categories are raw which can be used flexibly according to the needs of analysis and model training. Concretely, the Healthy class consists of 803 images, while the four other classes contain 1,873 images. This structured way of collecting data will, in turn, enable deeper analysis and help construct machine learning models for disease classification, hence providing worthy insights into Ash Gourd plant health.