-
For certain tensors (e.g. multiply with a scalar (constant) tensor, such as 1/6 at the output of hard sigmoid), the shape attribute might be None/undefined and hence, flatbuffer.shape() returns a null…
-
## Bug Description
When trying to compile MobileNetV3 from torchvision with the dynamic shape, it fails with following error
```
DEBUG: [Torch-TensorRT] - Pairing 0: x.1 : Input(shape: [-1, 3,…
-
```
python tools/train.py -c configs/rec/rec_icdar15_train.yml
[2022/03/26 17:09:54] root INFO: Architecture :
[2022/03/26 17:09:54] root INFO: Backbone :
[2022/03/26 17:09:54] root INFO: …
-
环境:
OS: macOS 12.6 (Apple M1)
测试集:仅一张 1440*960 的 jpg 人像图片
----
FastDeploy C++ infer.cc 代码修改:
``` C++
for(auto i = 0; i < 100; i++)
{
clock_t start,end;
start = clock();
…
-
按照文档跑icdar2015检测模型的训练
python3 tools/train.py -c configs/det/det_mv3_db.yml -o Global.pretrained_model=./pretrain_models/MobileNetV3_large_x0_5_pretrained
报错:
Out of memory error on GPU 0. Cannot …
-
请提供下述完整信息以便快速定位问题/Please provide the following information to quickly locate the problem
- 系统环境/System Environment:
- 版本号/Version:Paddle: PaddleOCR: 问题相关组件/Related components:
- 运行指令/Command Cod…
-
Thanks for your issue. To help us solve the issue better, please provide following information:
1. PaddleSeg version: (please specify the branch as well,e.g. PaddleSeg release/2.3)
2. PaddlePaddle…
-
2022-10-24 10:24:42 [INFO] There are 262/262 variables loaded into MobileNetV3.
/home/dell/anaconda3/envs/d2l/lib/python3.6/site-packages/paddle/nn/layer/norm.py:653: UserWarning: When training,…
-
*********************************************
开源不易,工程师每天有大量研发工作,请直接按此issue模版进行提问
这会大大减少工程师与你确认使用环境,编译过程中的基础信息时间
*********************************************
## 环境
- FastDeploy版本: 最新版本
- 如…
-
# 平台(如果交叉编译请再附上交叉编译目标平台):
# Platform(Include target platform as well if cross-compiling):
Python 3.8.5 on Windows 10
Python 3.7.6 on Ubuntu 18.04.5 LTS
# Github版本:
# Github Version:
1.0…