Gaoyiminggithub

Hi, you can obtain the images from the [http://pascallin.ecs.soton.ac.uk/challenges/VOC/voc2010/](http://pascallin.ecs.soton.ac.uk/challenges/VOC/voc2010/), and the annotations from your link, http://roozbehm.info/pascal-parts/pascal-parts.html .

For your convenience, i update the annotations file. You can download from [here](https://drive.google.com/file/d/1uFrK-lpq9yPmw9K1cAVCQwlMm90b_R6v/view?usp=sharing)

hi, 1. &2. The correct pretrained model of CIHP is in [here](https://drive.google.com/file/d/1eUe18HoH05p0yFUd_sN6GXdTj82aW0m9/view?usp=sharing), and the model of PASCAL is in [here](https://drive.google.com/file/d/1E_V_gVDWfAJFPfe-LLu2RQaYQMdhjv9h/view?usp=sharing). 3. Yes, you can use the university model, and later...

Hi, we have not trained the model on the ImageNet. Our model is trained on the COCO. Maybe you can get the Xception pretrained on the ImageNet on [here](https://github.com/tensorflow/models/blob/master/research/deeplab/g3doc/model_zoo.md).

@PkuRainBow Hi, the link `https://github.com/tensorflow/models/blob/master/research/deeplab/g3doc/model_zoo.md` I provided above is the checkpoints of the Aligned Xception :) (you can see and find the imagenet and coco pretrained in it) Maybe you...

@PkuRainBow I could not provide the pytorch version right now, because I delete it after I have trained the model on coco, but maybe I could convert that in next...

you can download the coco pretrained model in [here](https://drive.google.com/file/d/18WiffKnxaJo50sCC9zroNyHjcnTxGCbk/view?usp=sharing). The normalization way should follow [here](https://github.com/tensorflow/models/blob/master/research/deeplab/core/feature_extractor.py#L194-L197).

@PkuRainBow because I put the BN operation in self.conv3/4/5.