AI-liu

a GPU with 8 GB of memory , GTX 1070 , is it enough memory to run test ?

import os import torch import torch.nn as nn import argparse import cv2 import numpy as np from upsnet.config.config import * from upsnet.config.parse_args import parse_args from upsnet.models import * from PIL...

import os import torch import torch.nn as nn import argparse import cv2 import numpy as np from upsnet.config.config import * from upsnet.config.parse_args import parse_args from upsnet.models import * from PIL...

import os import torch import torch.nn as nn import argparse import cv2 import numpy as np from upsnet.config.config import * from upsnet.config.parse_args import parse_args from upsnet.models import * from PIL...

you can change to your image. im = cv2.imread("lindau_000000_000019_leftImg8bit.png") im = cv2.imread("your_imgae_XXXX.png") ------------------ 原始邮件 ------------------ 发件人: "lfdeep"; 发送时间: 2019年7月19日(星期五) 上午10:11 收件人: "uber-research/UPSNet"; 抄送: "136758759";"Comment"; 主题: Re: [uber-research/UPSNet] test my images...

no rotated rectangle here , I did not evaluate mAP on the KITTI.I will try to fix rotated rectangle problem.

The pretrained weights is trained by Darknet.There are two version here. pytorch version has some problem.

在darknet上修改的细节比较多，网站上的结果就是在darknet上训练的结果图。建议还是在pytorch框架上实现，我的代码可以训练的，如果显存不够可以修改一下bashsize ---Original--- From: "MA-JIE" Date: Sat, Jun 8, 2019 00:00 AM To: "AI-liu/Complex-YOLO"; Cc: "Comment";"AI-liu"; Subject: Re: [AI-liu/Complex-YOLO] Cann't load pretrained .weights file (#4) 前辈您好，最近在做comolexyolo的课题，由于电脑显存有限，计算能力不足，借鉴您的代码后无法训练出模型，您使用darknet训练出的模型应该不能用在pytorch上，请问您可以发一下darknet的代码或pytorch训练出的模型吗 — You are receiving this...

no rotated rectangle here , I will try .

https://pan.baidu.com/s/1yeU3Q-Oyozv7qFqrVhzj0A