代码拉取完成，页面将自动刷新
!mkdir ../checkpoints
!wget https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x1024_40k_cityscapes/pspnet_r50-d8_512x1024_40k_cityscapes_20200605_003338-2966598c.pth -P ../checkpointsmkdir: ../checkpoints: File exists --2023-02-23 19:23:01-- https://download.openmmlab.com/mmsegmentation/v0.5/pspnet/pspnet_r50-d8_512x1024_40k_cityscapes/pspnet_r50-d8_512x1024_40k_cityscapes_20200605_003338-2966598c.pth 正在解析主机 download.openmmlab.com (download.openmmlab.com)... 116.0.89.205, 116.0.89.209, 116.0.89.207, ... 正在连接 download.openmmlab.com (download.openmmlab.com)|116.0.89.205|:443... 已连接。 已发出 HTTP 请求，正在等待回应... 200 OK 长度：196205945 (187M) [application/octet-stream] 正在保存至: “../checkpoints/pspnet_r50-d8_512x1024_40k_cityscapes_20200605_003338-2966598c.pth.3” pspnet_r50-d8_512x1 100%[===================>] 187.12M 861KB/s 用时 2m 56s 2023-02-23 19:25:57 (1.06 MB/s) - 已保存 “../checkpoints/pspnet_r50-d8_512x1024_40k_cityscapes_20200605_003338-2966598c.pth.3” [196205945/196205945])
import torch
import mmcv
import matplotlib.pyplot as plt
from mmengine.model.utils import revert_sync_batchnorm
from mmseg.apis import init_model, inference_model, show_result_pyplotconfig_file = '../configs/pspnet/pspnet_r50-d8_4xb2-40k_cityscapes-512x1024.py'
checkpoint_file = '../checkpoints/pspnet_r50-d8_512x1024_40k_cityscapes_20200605_003338-2966598c.pth'# build the model from a config file and a checkpoint file
model = init_model(config_file, checkpoint_file, device='cuda:0')/Users/xxc/Desktop/pjlab/mmsegv2/mmseg/models/builder.py:36: UserWarning: ``build_loss`` would be deprecated soon, please use ``mmseg.registry.MODELS.build()``
warnings.warn('``build_loss`` would be deprecated soon, please use '
/Users/xxc/Desktop/pjlab/mmsegv2/mmseg/models/losses/cross_entropy_loss.py:235: UserWarning: Default ``avg_non_ignore`` is False, if you would like to ignore the certain label and average loss over non-ignore labels, which is the same with PyTorch official cross_entropy, set ``avg_non_ignore=True``.
warnings.warn(
Loads checkpoint by local backend from path: ../checkpoints/pspnet_r50-d8_512x1024_40k_cityscapes_20200605_003338-2966598c.pth
# test a single image
img = 'demo.png'
if not torch.cuda.is_available():
model = revert_sync_batchnorm(model)
result = inference_model(model, img)# show the results
vis_result = show_result_pyplot(model, img, result)
plt.imshow(mmcv.bgr2rgb(vis_result))/opt/anaconda3/envs/pt1.13/lib/python3.10/site-packages/mmengine/visualization/visualizer.py:163: UserWarning: `Visualizer` backend is not initialized because save_dir is None.
warnings.warn('`Visualizer` backend is not initialized '
<matplotlib.image.AxesImage at 0x7fbd89380160>
此处可能存在不合适展示的内容，页面不予展示。您可通过相关编辑功能自查并修改。
如您确认内容无涉及 不当用语 / 纯广告导流 / 暴力 / 低俗色情 / 侵权 / 盗版 / 虚假 / 无价值内容或违法国家有关法律法规的内容，可点击提交进行申诉，我们将尽快为您处理。
马建仓 AI 助手