monkeycc

mmdeploy_python mask colour

2

``` # https://github.com/open-mmlab/mmdeploy/blob/master/demo/python/object_detection.py # Copyright (c) OpenMMLab. All rights reserved. import argparse import cv2 from mmdeploy_python import Detector def parse_args(): parser = argparse.ArgumentParser( description='show how to use sdk python api')...

There is a problem with own painting mask

1

``` from mmdeploy_python import Detector import cv2 # 读取图片 img = cv2.imread('mmdetection/demo/demo.jpg') # 创建检测器 detector = Detector(model_path='mmdeploy_models/mask-rcnn', device_name='cuda', device_id=0) # 执行推理 bboxes, labels, _ = detector(img) # 使用阈值过滤推理结果，并绘制到原图中 indices =...

``` (open-mmlab) PS E:\MM\mmdetection> python tools/train.py configs\mask_rcnn\mask_rcnn_r50_fpn_2x_coco.py D:\anaconda308\envs\open-mmlab\lib\site-packages\torchvision\io\image.py:13: UserWarning: Failed to load image Python extension: warn(f"Failed to load image Python extension: {e}") D:\anaconda308\envs\open-mmlab\lib\site-packages\mmdet\utils\setup_env.py:39: UserWarning: Setting OMP_NUM_THREADS environment variable for each...

如何实现 重叠滑窗预测,How to realize overlapping sliding window prediction,Add Sahi

1

**Describe the feature** **Motivation** 比如9000*9000 不能直接滑窗裁剪 需要重叠裁剪 有重复部分 原图预测 自动裁剪 也可以批量对文件夹图片进行裁剪 建议增加 Sahi 重叠滑窗预测功能 For example, 9000 * 9000 You cannot directly slide the window to cut If overlapping clipping...

Is it suitable for the outline of the animal

4

 Is it suitable for the outline of the animal I need to know exactly the height and length of each node Is mmpose appropriate

## 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 API文档说明](https://github.com/PaddlePaddle/PaddleX/tree/develop#paddlex-%E4%BD%BF%E7%94%A8%E6%96%87%E6%A1%A3) ## 描述问题 数据集COCO -- Train - 1.jpg - 2.jpg -- Val - 1.jpg - 2.jpg -- Annotation - Train.json...

-- TrainVal - 1.jpg - 2.jpg .... -- Annotation - TrainVal.json 实例分割 怎么转换为paddleX的数据集

C#部署，实例MASK预测报错，其他不会报错

1

C#部署，实例分割 MASK 预测报错， 其他不会报错 预测的时候 选择MASK报错 选择paddleX也报错 分类 目标 都没有报错

## 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 API文档说明](https://github.com/PaddlePaddle/PaddleX/tree/develop#paddlex-%E4%BD%BF%E7%94%A8%E6%96%87%E6%A1%A3) ## 描述问题 ``` 2022-08-23 15:29:51 [INFO] Model[PPYOLOTiny] loaded. Traceback (most recent call last): File "f:/MM/mm.py", line 7163, in deploy_model...

float division by zero

2

PPLCNet_ssld CPU预测 model = pdx.deploy.Predictor("F:/inference_model/",use_gpu=False) GPU也会报错 图片正常 能正常打开 多张图片 都不行 报错 ------------------ Inference Time Info ---------------------- total_time(ms): 0.0, img_num: 1, batch_size: 1 Traceback (most recent call last): File "f:/AI.py", line...