pytorch-deeplab-xception

pytorch-deeplab-xception copied to clipboard

CityScapes Pretrained model

3

Hi, Do you have the pre-trained weights for cityscapes dataset with resnet101 backbone.

vineet-g

hello, a question, can I use my own dataset labeled by labelme to train the model??

4

hello, a question, can I use my own dataset labeled by labelme to train the model?? thx

zhengkai17

https://github.com/jfzhang95/pytorch-deeplab-xception/blob/9135e104a7a51ea9effa9c6676a2fcffe6a6a2e6/dataloaders/custom_transforms.py#L125 在验证阶段还做了数据增强，FixScaleCrop，这是不合理的 Data enhancement is also done in the verification phase -- FixScaleCrop， This is unreasonable

wuzuowuyou

Hi. In [paper](https://arxiv.org/abs/1706.05587) section 3.2.1, You introduced "Multi-grid Method" and Table 5 shows that using Multi-Grid method with rates = (1,2,4) is the best method that the paper used. But...

ghost

Dear authors, Thanks very much for your amazing work! I have some questions about the batch size selection. The batch size is defaulted as 4 per GPU. This is a...

zhiyuanyou

what does best_pred.txt mean? such as 0.3747677837460877

1

zhujiesuper

When running, the first epoch stops at the end. Has anyone encountered this situation?

9711128

If one GPU can run, why not multiple gpus?

3

One GPU can run, but multiple gpus can not run? my pytorch 1.1 and has 4 GPUs One GPU can run, but why can't more than one GPU? I have...

xupine

train images with different width and height sizes?

2

Hi, Can I train images with different width and height sizes? like 1024*512, since my image scale is 2:1 the default size is 513 in this repo, how can I...

SteveIb

How can I get pretrained Model with xception as backbone?

1

neiheih