charmowen
charmowen
多变量线性回归-特征归一化部分,data2 = (data2 - data2.mean()) / data2.std() 代码应改为data2 = (data2 - data2.mean()) / data2.std(ddof=0)吧
 客户端请求后,服务端内存不释放,多次请求后内存一直累加。 Paddle Server版本:0.8.3 代码:https://github.com/PaddlePaddle/PaddleClas/tree/release/2.3/deploy/paddleserving
cascade_rcnn_vgg16_pruned_voc Traceback (most recent call last): File "scripts/detection/cascade_rcnn/train_cascade_rcnn.py", line 490, in net = get_model(net_name, pretrained_base=True) File "/home/cascade_rcnn_gluon/gluoncv/model_zoo/model_zoo.py", line 115, in get_model net = models[name](**kwargs) File "/home/cascade_rcnn_gluon/gluoncv/model_zoo/cascade_rcnn/cascade_rcnn.py", line 672, in cascade_rcnn_vgg16_pruned_voc...
服务化部署不使用高性能推理插件,能够进行并发请求吗?并发数在哪修改