Differences in Validation results when training in Pascal Context Dataset

Hi Hang Zhang!

First I want to thank you for the amazing repository.

I'm trying to train DeepLabv3 with ResNeSt-101 backbone (DeepLab_ResNeSt101_PContext) for the task of semantic segmentation in Pascal Context Dataset. I'm running the code without any issue, however, I'm still under you results from the pre-trained model that you provide in https://hangzhang.org/PyTorch-Encoding/model_zoo/segmentation.html :

I'm using the exact same hyperparameters as you and using the following training command:
python train.py --dataset pcontext --model deeplab --aux --backbone resnest101

Is there something that I'm missing for reaching you results? I assume that your model is trained using Auxiliary Loss but not Semantic Encoding Loss. Are you using some pretraining data maybe?

Thanks in advance!

Alex.

Start with the reported command, python train.py --dataset pcontext --model deeplab --aux --backbone resnest101, and compare its validation metrics with the published pretrained-model results at the linked model-zoo page. Determine whether the discrepancy comes from training settings or pretraining data; done means identifying the missing factor or reproducing the published 81.9% pixel accuracy and 56.5% mIoU.