spnv2
spnv2 copied to clipboard
tpark94
PyTorch implementation of SPNv2
Hi Jeff! I was preprocessing a dataset containing mask and noticed that the bounding box labels I was getting were too small. When I checked tools/preprocessing.py I found that when...
Hey Jeff, I used preprocess.py with --no_labels to generate image lists for sunlamp and lightbox then ran the odr script to run into the following error: ``` 2024/01/08 16:19:00 Random...
The read.me says that "The code is developed and tested with python 3.7...", but when I tried to install the requirements I saw that one of mentioned libraries (scipy>=1.10.0) cannot...
Dear Dr. Park, Thank you for your work and for your contribution to research. From your paper (and the ones you cited) I understand that \phi is an hyperparameter to...
Hi, I am running the code with `offline_train_full_config_phi3_BN.yaml`. Only change I make is train it on a single GPU instead of multiple. However, the metrics that I achieve on lightbox...
hello, thansk for your working, I am trying to test synthetic dataset based on the provided weight "spnv2_efficientnetb3_fullconfig_offline.pth.tar", and using offline_train_full_config_phi3_BN.yaml file. In this .yaml file, i modify the image_size...
The create_anchors() function assumes image_size=(H, W) while the rest of the code defines it as (W, H). This axis swap leaves part of the image without anchors, causing missing positives...
