pytorch-semseg

pytorch-semseg copied to clipboard

python-cdo

1

When I run **cdo = cdo()**, it appears TypeError . How can you solve it? ``` # In from cdo import Cdo import os import numpy as np import re...

lixuan-code

Exception: No files for split=[train_aug] found in /home/lxc/datasets/leftImg8bit/train_aug

2

li0128

Update ade20k_loader.py

1

scipy.misc.imread is depreciated. I have changed it to plt.imread (line 49) 

MOAZ47

There isn't a pkl file generated after training

3

Why ？When I finished training， the runs dir have no pkl file generated？Just a events file， a yml file， a log file。

heiheiya

For the validation, we need to pass the path of saved model after training, but i am unable to find the path. Though in config file, i have added `resume:...

talhaanwarch

How to Train FCN8s with CamVid Dataset

1

Hi,Can you release a config.yaml about training fcn8s in camvid? I think i can't set proper parameters such as lr batch_size ,iterations and so on... Thanks!

liqisa

KeyError: 'name'

2

Traceback (most recent call last): File "E:/Semantic Segmentation/pytorch-semseg-master/train.py", line 229, in train(cfg, writer, logger) File "E:/Semantic Segmentation/pytorch-semseg-master/train.py", line 80, in train optimizer_cls = get_optimizer(cfg) File "E:\Semantic Segmentation\pytorch-semseg-master\ptsemseg\optimizers\__init__.py", line 24, in...

lewisxiaoxu

The metrics of computing confusion matrix might be more efficient

2

``` import numpy as np from sklearn.metrics import confusion_matrix class runningScore(object): def __init__(self, n_classes): self.n_classes = n_classes self.confusion_matrix = np.zeros((n_classes, n_classes)) def _fast_hist(self, label_true, label_pred, n_class): mask = (label_true >=...

xyl576807077

I'm currently trying to train HardNet on CamVid but I always get the below error : `Traceback (most recent call last): File "train.py", line 267, in train(cfg, writer, logger) File...

MBKS1

Hi, @meetshah1995 I want to know how to get the pretrained models for pspnet? Can you help me? Best Regards.

xiaoyuamw