测试检测效果infer_det.py 失败无报错
收藏
测试检测效果
python tools/infer_det.py -c configs/det/det_r50_vd_sast_icdar15_1.yml -o Global.infer_img="./data\ch4_test_images\img_1.jpg" Global.pretrained_model="./output/sast_r50_vd_ic15/latest"
log如下:
[2021/09/13 20:59:45] root INFO: train with paddle 2.1.2 and device CUDAPlace(0)
W0913 20:59:45.780572 1232 device_context.cc:404] Please NOTE: device: 0, GPU Compute Capability: 7.5, Driver API Version: 11.1, Runtime API Version: 10.1
W0913 20:59:45.783565 1232 device_context.cc:422] device: 0, cuDNN Version: 7.6.
[2021/09/13 21:00:21] root INFO: load pretrained model from ['./output/sast_r50_vd_ic15/latest']
[2021/09/13 21:00:21] root INFO: infer_img: ./data\ch4_test_images\img_1.jpg
源码是这行执行失败,但无报错
preds = model(images)
求教。。
0
收藏
请登录后评论
先用whl包快速开始试试?看起来有点像windows路径的问题
这是前向计算出错了。输入的images是不是预处理好了呢?归一化之类的做的和训练一样么