sohailahmedkhan / flood-detection-from-images-using-deep-learning Goto Github PK

Flood detection from images using deep learning. Deep learning library KERAS was employed and MobileNet architecture was fine-tuned for image classification task.

Jupyter Notebook 100.00%

flood detection flood-detection deep-learning keras-tensorflow fine-tuning transfer-learning mobilenet image-processing flood-detection-using-images

flood-detection-from-images-using-deep-learning's People

Stargazers

Watchers

Forkers

ravindurra smithakolan i-vishnuraj greg-schussman leenajuliet-cc aatwum davidchoi76 drroad dnzengou uditi1002 tejjusbhat harshpal007 fitsumw

flood-detection-from-images-using-deep-learning's Issues

do u have other model structure weights

segmentation

Thanks for the repo.

The paper performs Semantic Segmentation as well as image classification, while you do image classification only. Did you manage to perform Semantic segmentation as well or should I start a new project to get that done?

Also, when trained again I don't get the same values on evaluation:

Precision:  0.8
F1 Score:  0.888888888888889
Accuracy:  0.9014084507042254

Nevertheless, using your model it works as you said :)

ValueError: Shapes (None, None) and (None, 7, 7, 2) are incompatible

Hi thanks for your training model and codes, I tried it but I got an error:
ValueError: Shapes (None, None) and (None, 7, 7, 2) are incompatible

Do you know how to fix it? Thanks.