Efficient-Segmentation-Networks

Efficient-Segmentation-Networks copied to clipboard

Bumps [numpy](https://github.com/numpy/numpy) from 1.15.0 to 1.22.0. Release notes Sourced from numpy's releases. v1.22.0 NumPy 1.22.0 Release Notes NumPy 1.22.0 is a big release featuring the work of 153 contributors spread...

dependabot[bot]

cityscapes data set processing

2

After downloading cityscapes data sets, put them in the corresponding folder, which will be displayed during training：NotImplementedError: This repository now supports two datasets: cityscapes and camvid, cityscapes is not included。What...

254038lqq

About metric mistake, recall and precison

1

https://github.com/xiaoyufenfei/Efficient-Segmentation-Networks/blob/0f0c32e7af3463d381cb184a158ff60e16f7fb9a/utils/metric/metric.py#L43-L56 it's reverse. ` # 理解混淆矩阵生成的代码的关键，行为真实值，列为预测值 # Pii为预测正确的数量，Pij=FN, Pji=FP # 每一列之和表示被预测为该类别的样本数量 = TP+FP, precision = TP/(TP+FP), 所有被预测为正类中真正正类的比例 # 每一行之和表示该类别的真实样本数量 = TP+FN, recall = TP/TP+FN , 所有正类中，被找出的正类的比例 def recall(self): recall =...

DCC-lzhy

I have a question to consult you. I want to add three categories (water, bridge and others) to the cityscapes data sets; Should I attribute "the else class" to "ignore_...

niuxiaoming1983

(-215:Assertion failed) !ssize.empty() in function 'resize'

1

/home/ll/anaconda3/envs/t1.2/bin/python /media/ll/L/Efficient-Segmentation-Networks/train.py 1.2 =====> input size:(512, 1024) Namespace(batch_size=4, classes=19, cuda=True, dataset='cityscapes', gpus='0', input_size='512,1024', logFile='log.txt', lr=0.0005, lr_schedule='warmpoly', max_epochs=1000, model='FastSCNN', num_cycles=1, num_workers=4, optim='adam', poly_exp=0.9, random_mirror=True, random_scale=True, resume='', savedir='./checkpoint/', train_type='trainval', use_focal=True, use_label_smoothing=False, use_lovaszsoftmax=False,...

Linda-L

why ValueError: num_samples should be a positive integer value, but got num_samples=0 I use the cityscapes dataset,it can't get it.But directory is true

GitHubmalajava

Hello Great Work ! I did training using the provided ENet and ERFNet Models. I am facing a problem, while testing the Models, ENet inference speed is very low, it...

Abdul-Nasir11

I can't find chekpoint['modle'],how to test?

ZHUANGMINGXI

dear sir, is unet+backbone suported(such as resnet50)?

LeeNannaner

hi, every time i train a model, after some epochs, this error occurs: Traceback (most recent call last): File "/home/thu‑microe/anaconda3/envs/tensorflow/lib/python3.6/runpy.py", line 193, in _run_module_as_main "__main__", mod_spec) File "/home/thu‑microe/anaconda3/envs/tensorflow/lib/python3.6/runpy.py", line 85,...

gothic22