DeepLabV3Plus-Pytorch

DeepLabV3Plus-Pytorch copied to clipboard

load pretrained model error

1

RuntimeError: Error(s) in loading state_dict for DeepLabV3: size mismatch for classifier.classifier.3.weight: copying a param with shape torch.Size([21, 256, 1, 1]) from checkpoint, the shape in current model is torch.Size([3, 256,...

onenerve

hrnetv2_32 as model

5

sorry to bother you again, when I use hrnetv2_32 as model without pretrained wights,I get a problem.can you tell me how to modify. ...... x_fused[branch_output_index] = x_fused[branch_output_index] + self.fuse_layers[branch_output_index][ RuntimeError:The...

lcr9875

Xception as Network Backbone

7

Thank you again,I want to know if you will add Xception as Backbone in this repo?

lcr9875

Xception checkpoint

1

Hi! First of all, I want to thank you for your implementation, it works like a charm. I want to ask you if you by any chance have an Xception...

andreyroizin

DeepLabV3Plus-ResNet101 pretrained weight on CityScape cannot be extracted from the .tar file

2

The .tar file for the CityScape pretrained weight of DeepLabV3Plus-ResNet101 model seems to be invalid. I wonder if anyone had success extract the weight file from it.

Coronal-Halo

Error when running main.py with default parameters

1

The error message is as follows: ```python Traceback (most recent call last): File "main.py", line 383, in main() File "main.py", line 327, in main for (images, labels) in train_loader: File...

ChangzhenZhang

I changed some simple lines to gain better Python syntax.

Nourollah

cityscapes data set

1

Hello, can deeplabv3PLus_HRnetV2_32 be used to train Cityscapes datasets in the project

254038lqq

Hi! I saw you add the dropout layer in ASPP with p=0.1, but in pytorch official implement p=0.5(https://github.com/pytorch/vision/blob/main/torchvision/models/segmentation/deeplabv3.py, Line 105). Moreover, I can't find any sign of using dropout in...

Unqua

customizing dataset

2

how can we train our own datasets?

jbh1998