PaddleSeg win10下环境搭建
d:anaconda3 conda create --name paddle_seg python=3.8 --channel https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/free/ conda activate paddle_seg conda install paddlepaddle-gpu==2.4.2 cudatoolkit=10.2 --channel https://mirrors.tuna.tsinghua.edu.cn/anaconda/cloud/Paddle/ # 在Python解释器中顺利执行如下命令(python) import paddle paddle.utils.run_check() pip install paddleseg==2.7 -i http://mirrors.aliyun.com/pypi/simple --trusted-host mirrors.aliyun.com set CUDA_VISIBLE_DEVICES=1 python tools/predict.py --config configs/quick_start/pp_liteseg_optic_disc_512x512_1k.yml --model_path https://paddleseg.bj.bcebos.com/dygraph/optic_disc/pp_liteseg_optic_disc_512x512_1k/model.pdparams --image_path docs/images/optic_test_image.jpg --save_dir output/result cd D:PaddleSegMatting pip install -r requirements.txt set CUDA_VISIBLE_DEVICES=1 python ./tools/predict.py --config ./configs/ppmatting/ppmatting-hrnet_w18-human_512.yml --model_path ppmatting-hrnet_w18-human_512.pdparams --image_path ./input/200645066-6898ec5a-f1c5-4bf7-aa41-473a29977a86.jpeg --save_dir ./output/results --fg_estimate True
上一篇:
JS实现多线程数据分片下载
下一篇:
ELK安装过程中一些注意的地方