TerrafYassin
TerrafYassin
Hi , I need to modify the aspect ratio and scale to cover small object detection problem , and i see in your project you import RPN network from Torchvision...
config : # coding=utf-8 DATA_PATH = "/content/drive/MyDrive/HRSC2016"#"F:/Datasets/DOTAx/test/"# PROJECT_PATH = "/content/drive/MyDrive/GGHL/" DATA = {"CLASSES": [ 'ship', ], "NUM": 1} DATASET_NAME = "train_HRSC2016" MODEL = {"STRIDES":[8, 16, 32]} MAX_LABEL = 1000 SHOW_HEATMAP...
for the input images i select some images from test folder of HRSC2016 dataset
Yes sir , i used darknet53.weights and the training epochs stopped on epoch 130 , after tested the best model on Test dataset i got 0.54 as mAP.
Hello sir , Thank you for the reply , i sent you authorization request to your mail. My mail is [email protected]
Well received sir but please can you explain to me step by step how you are passed from the following format to GGHL format , I know this is a...
Also sir , you have shared with me your tested data used to test your model not validation data used during model training after 50 epochs ?
can you share with me sir also your config.py content and did you change anything in the lie bellow ? 
> > Well received sir but please can you explain to me step by step how you are passed from the following format to GGHL format , I know this...