1. what i mean train/split ratio is that i've very few images to train model on so is it possible to allocate 100% images to train split and ignore test split entirely?

link to project here https://medium.com/@ije_good/object-detection-on-satellite-imagery-using-retinanet-part-1-training-e589975afbd5

  1. Find on page this line - ap.add_argument("-s", "--split", default = 0.8, type = float, help = "train/test split") - basically it's an argument

My initial objective is to test the model aka proof of concept only cuz i don't have a lot of images to start with! currently only 100 but i'll give it a try anyways

Problem: The script is written by someone else -https://towardsdatascience.com/object-detection-on-aerial-imagery-using-retinanet-626130ba2203

but i don't necessarily know the entire workflow/ structure of this script so i want to run it with lowest validation data possible with without breaking the model...just sharpening my coding skill! i'm not a pro but it takes time..

How do you set the following code in colab notebook tobe 100% of my dataset? https://colab.research.google.com/drive/1RVG7MqoGnIku0oXPSMjmT_T-o1aU9y_O

need help! thanks


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.