-
#模型评估
!cd work/PaddleSeg && python pdseg/eval.py --use_gpu \
--cfg configs/deeplabv3p_mobilenetv3_large_cityscapes.yaml \
TEST.TEST_MODEL saved_model/deepl…
-
请问，configs/deeplabv3p_mobilenetv3_large_cityscapes.yaml中的 MODEL.DEEPLAB.ENCODER.ASPP_WITH_SE参数的含义是什么呢，是决定是否使用Squeeze-and-Excitation模块吗？但我在pdseg/models/modeling/deeplab.py里没找到这个参数，而在pdseg/models/backbo…
-
**1. 使用环境（environment）**
- OS: Centos
- OS Version: 7
**2. Github版本**
- branch：
- commit(optional):
**3. 详细描述bug 情况 (Describe the bug)**
A clear and concise description of what the…
-
Thank you for your great work and sharing it!
Do you have any recommendation to use your models to label audio at a higher resolution, say 1 sec or lower? Or even mel frame level?
I've tried app…
-
Hi,
I have CUDA 10.1 installed on my machine and I was looking for instruction on how to build the model with GPU.
Is CUDA 10.1 OK for building the model ?
step 1:
I installed PaddlePaddle …
-
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…
-
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();
…
-
你好，我在训练表格结构识别模型的时候，设置`num_workers > 0`就会报错，`num_workers : 0`没有这个报错
训练使用命令：`python3 tools/train.py -c configs/table/table_mv3.yml`
GPU环境信息：单卡`cuda=10.1 cudnn=7.6`
Paddle版本信息：`paddleocr=2.3.0.2 pa…
-
## 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,…
-
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 …