PaddleX icon indicating copy to clipboard operation
PaddleX copied to clipboard

PaddlePaddle End-to-End Development Toolkit(『飞桨』深度学习全流程开发工具)

Results 466 PaddleX issues
Sort by recently updated
recently updated
newest added

PaddleSeg is_slide | bool | 是否通过滑动窗口进行评估 | 否 | False -- | -- | -- | -- | -- stride | tuple/list | 设置滑动窗宽的宽度和高度,is_slide为True时生效 | 否 | None crop_size |...

## Checklist: 1. 查找[历史相关issue](https://github.com/PaddlePaddle/PaddleX/issues)寻求解答 2. 翻阅[FAQ常见问题汇总和答疑](https://github.com/PaddlePaddle/PaddleX/blob/develop/docs/FAQ/FAQ.md) 3. 确认bug是否在新版本里还未修复 4. 翻阅[PaddleX 使用文档](https://github.com/PaddlePaddle/PaddleX/tree/develop#paddlex-%E4%BD%BF%E7%94%A8%E6%96%87%E6%A1%A3) ## 描述问题 我用paddlex里面目标检测的案例程序 改了一下数据处理,主要是图片尺寸大小 后面训练批次的大小也该小为4了 但出现了 OSError: (External) CUDA error(700), an illegal memory access was encountered. [Hint: 'cudaErrorIllegalAddress'. The...

报错信息: [ERROR] Exported quantized model can not be loaded, only deployment is supported. 来源应该是这里吧: https://github.com/PaddlePaddle/PaddleX/blob/07ceb75823fd9d4eb1aa9e5fd93ab636e801507c/paddlex/cv/models/load_model.py#L117

PP-YOLOE 什么时候加上去 虽然 PaddleX 不像 PaddleDetection 是亲生儿子 但是也不要太晚了 其他PaddleDetection里面模型是不指望的了 自家模型 还是要更新一下的

1. 您使用的**模型**和**数据集**是? 标题样例默认的模型和数据集 5. 请提供您出现的报错信息及相关log InvalidArgumentError: The tensor Input (Input) of Slice op is not initialized. [Hint: Expected in_tensor.IsInitialized() == true, but received in_tensor.IsInitialized():0 != true:1.] (at ..\paddle/fluid/operators/slice_op.cc:130) [operator <...

## 描述问题 PaddleX 中的model.evaluate 输出的acc1同paddle.metric.accuracy计算得出的结果不一致。batch_size越大,两者差距约明显. 1. batch_size = 1,两者没差距 ![batch 1](https://user-images.githubusercontent.com/31607618/182561835-d026a929-cedc-40ca-a821-9da34ed1878d.png) 2. batch_size=32,开始出现计算结果不一致的情况 ![batch 32](https://user-images.githubusercontent.com/31607618/182562085-5edc142e-6841-45d7-9fae-73241985ec02.png) 3. batch_size=256 ![batch 256](https://user-images.githubusercontent.com/31607618/182562292-dbd17b22-7d96-4590-a21b-4f3c5d3da446.png) 4. batch_size=512 ![batch 512](https://user-images.githubusercontent.com/31607618/182562398-c0fba22d-84a8-4003-9790-f0906297a22c.png) 5. batch_size=626 ![batch 626](https://user-images.githubusercontent.com/31607618/182562428-1835ef9f-b1d4-46fa-85aa-c57ccff1c7e2.png) ## 复现 1....

``` Model: YOLOv3 Transforms: - Resize: interp: CUBIC keep_ratio: false target_size: !!python/tuple - 608 - 608 ``` ``` for ymldata_1_1 in ymlcfg_1_1: File "D:\anaconda3\envs\PaddleX38\lib\site-packages\yaml\__init__.py", line 93, in load_all yield loader.get_data()...

编译paddlex,想使用TesnsorRT加速,仿照 model_infer.cpp 改写 tensorrt_infer.cpp 编译生成 tensorrt_infer.dll,在qt demo中调用时出错。(参考 “基于PaddleInference的推理-Windows环境编译” 的流程) 错误如下: ![image](https://user-images.githubusercontent.com/50402380/181445541-3ec68bcb-178c-4db3-a9ea-9cf8dc31b0f8.png)

## 描述问题 ```python f:/aa.py D:\anaconda3\envs\PaddleX38\lib\site-packages\paddlex\paddleseg\models\losses\decoupledsegnet_relax_boundary_loss.py:19: DeprecationWarning: Please use `shift` from the `scipy.ndimage` namespace, the `scipy.ndimage.interpolation` namespace is deprecated. from scipy.ndimage.interpolation import shift D:\anaconda3\envs\PaddleX38\lib\site-packages\paddlex\paddleseg\transforms\functional.py:18: DeprecationWarning: Please use `distance_transform_edt` from the `scipy.ndimage`...

## Checklist: 1. 查找[历史相关issue](https://github.com/PaddlePaddle/PaddleX/issues)寻求解答 2. 翻阅[FAQ常见问题汇总和答疑](https://github.com/PaddlePaddle/PaddleX/blob/develop/docs/FAQ/FAQ.md) 3. 确认bug是否在新版本里还未修复 4. 翻阅[PaddleX数据准备文档](https://github.com/PaddlePaddle/PaddleX/tree/develop#2-%E6%95%B0%E6%8D%AE%E5%87%86%E5%A4%87) ## 描述问题 使用paddlex进行数据集划分时报错 ## 复现 1. 您使用的命令是? !paddlex --split_dataset --format VOC --dataset_dir squat_detect/DatasetId_215201_1628403652 --val_value 0.2 --test_value 0.01 2. 您使用的数据集是? VOC...