-
1.
# 评估预训练模型
python tools/eval.py -c configs/det/ch_PP-OCRv3/ch_PP-OCRv3_det_cml.yml -o Global.pretrained_model="./pretrained_models/ch_PP-OCRv3_det_distill_train/best_accuracy"
结果如下：
方案 hmeans
…
-
Platform Jetpack 5, Jetson Xavier, Cuda 11.4, TRT 8.4.1
Latest branch
Mobilenetv3 - Getting strange results
Hi,
Getting strange results:
Step 1: D/n https://github.com/chufei1995/mobilenetv3…
-
## 环境
- 【FastDeploy版本】： fastdeploy-gpu-python-1.0.1
- 【系统平台】: Windows x64(Windows10)
- 【硬件】：TITAN X ， CUDA 11.3 CUDNN 8.2
- 【编译语言】：Python3.8
PaddleOCR检测模型训练配置文件：
```
Global:
use_gpu:…
-
Hello,
How to create the mobilenet .wts file ?
I tried load the model from torchvision.models and load the weights supplied,
but got errors when trying to convert.
Is there any sample script …
-
**Describe the issue**:
[2022-12-02 16:25:47] start to speedup the model
[2022-12-02 16:25:48] infer module masks...
[2022-12-02 16:25:48] Update mask for .prim::TupleUnpack.162
[2022-12-02 16:25:…
-
aistudio环境， paddleseg2.2
model的配置如下
model:
type: OCRNet
backbone:
type: MobileNetV3_small_x1_0
pretrained: https://paddle-imagenet-models-name.bj.bcebos.com/MobileNetV3_small_x1_0_…
-
Hello Marco,
Great work you have done here.
I am looking forward to use the cs-flow model on an edge device (jetson). However, the EfficientNet backbone is very computationally expensive, will it be…
-
- 系统环境/System Environment：Windows 10 家庭版 64位
- 版本号/Version：Paddle：paddlepaddle-gpu 2.4.2.post112 PaddleOCR：2.6.1.3 问题相关组件/Related components：模型量化
- 运行指令/Command Code：
python deploy/slim/quantizati…
-
**问题1：**
对rec模型使用知识蒸馏，ch_PP-OCRv2_rec_distillation.yml配置文件中Backbone为MobileNetV3、MobileNetV1Enhance时不会报错。
将backbone修改为ResNet_系列时，会出现参数已经已经在使用的情况。
![image](https://user-images.githubusercontent.com/3…
-
使用VGG16作为faster rcnn的骨干网络，文件内容如下：
```
architecture: FasterRCNN
use_gpu: true
max_iters: 16000
log_iter: 50
save_dir: output
snapshot_iter: 200
pretrain_weights: https://paddle-imagenet-model…