awesome-semantic-segmentation-pytorch

awesome-semantic-segmentation-pytorch copied to clipboard

I run the train with "python -m torch.distributed.launch --nproc_per_node=4" and using dataset=cityscape backbone=resnet50 batchsize=4 my GPU is Nvidia Titan X *4 12GB memory per card, and CUDA out of memory...

littlecay

RuntimeError: Given groups=1, weight of size [128, 512, 1, 1], expected input[4, 2048, 1, 1] to have 512 channels, but got 2048 channels instead

4

大神你好，我是个初学者，在用voc训练psp的时候默认设置可以跑通，但是我想把Ci弄小一点，于是改成了： class _PSPHead(nn.Module): def __init__(self, nclass, norm_layer=nn.BatchNorm2d, norm_kwargs=None, **kwargs): super(_PSPHead, self).__init__() self.psp = _PyramidPooling(512, norm_layer=norm_layer, norm_kwargs=norm_kwargs) self.block = nn.Sequential( nn.Conv2d(1024, 128, 3, padding=1, bias=False),#Ci，Co，kernelsize norm_layer(128, **({} if norm_kwargs is None...

AngLancer

please help me! ValueError: Model file is not found. Downloading or trainning.

4

amax@amax:/data/yh/awesome-semantic-segmentation-pytorch/scripts$ ./dfanet_resnet18_pascal_voc.sh /home/amax/anaconda3/lib/python3.6/site-packages/requests/__init__.py:80: RequestsDependencyWarning: urllib3 (1.25.3) or chardet (3.0.4) doesn't match a supported version! RequestsDependencyWarning) 2019-08-21 14:15:23,071 semantic_segmentation INFO: Using 1 GPUs 2019-08-21 14:15:23,071 semantic_segmentation INFO: Namespace(aux=False, aux_weight=0.4, backbone='resnet18', base_size=520,...

electronicYH

RuntimeError: CUDA out of memory.

1

Please,How to solve this problem? RuntimeError: CUDA out of memory. Tried to allocate 74.00 MiB (GPU 0; 1.96 GiB total capacity; 1.46 GiB already allocated; 71.50 MiB free; 38.53 MiB...

wuwangtingfeng

大家有没有遇到用自己数据集训练的时候 损失特别低 所有测试图像的准确率和miou都一模一样？如下所示

15

2019-11-20 11:16:10,422 semantic_segmentation INFO: Iters: 880/139700 || Lr: 0.000099 || Loss: 0.0033 || Cost Time: 0:06:46 || Estimated Time: 17:46:33 2019-11-20 11:16:15,154 semantic_segmentation INFO: Iters: 890/139700 || Lr: 0.000099 ||...

anqin5211314

Training on pascal voc 2012 with resnet50-based-pspnet, the acc grows normally but the miou converge 0.038....Is it the reason with the dataset? I don't make any change to the source code.

4

bppps

> There might be something wrong with the version of `pillow`. Try this : `border=(0, 0, padw, padh)` -> `border=20`

3

> There might be something wrong with the version of `pillow`. Try this : `border=(0, 0, padw, padh)` -> `border=20` Thank you very much, I solved it. But I don't...

bea-CC

danet

1

attention_new = torch.max(attention, dim=-1, keepdim=True)[0].expand_as(attention) - attention I don't understand

web3-panpan

Help! TypeError: an integer is required (got type tuple)

6

wenwu@Amax:~ /chenyao/awesome-semantic-segmentation-pytorch-master/scripts$ python train.py --model fcn32s --backbone vgg16 --dataset pascal_voc --lr 0.0001 --epochs 50 2021-09-08 18:06:48,524 semantic_segmentation INFO: Using 1 GPUs 2021-09-08 18:06:48,524 semantic_segmentation INFO: Namespace(aux=False, aux_weight=0.4, backbone='vgg16', base_size=520, batch_size=4,...

cy998412

OSError: [Errno 40] Too many levels of symbolic links:

3

ggw@vip-workstation1:~/guoanXu/awesome/core/data/downloader$ python ade20k.py --download-dir ../datasets/citys Traceback (most recent call last): File "ade20k.py", line 51, in download_ade(_TARGET_DIR, overwrite=False) File "ade20k.py", line 35, in download_ade makedirs(download_dir) File "/home/ggw/guoanXu/awesome/core/utils/filesystem.py", line 16, in makedirs...

XU-GITHUB-curry