LeoRainly

Warning: Encountered known unsupported method torch.Tensor.__new__

1

I encountered these warnings when converting my model, and the results of the trt model are not right. Warning: Encountered known unsupported method torch.Tensor.clone Warning: Encountered known unsupported method torch.Tensor.__new__...

WARNING: Myelin graph with multiple dynamic values may have poor performance if they differ. Dynamic values are: (+ (FLOOR_DIV (FLOOR_DIV (FLOOR_DIV (FLOOR_DIV (FLOOR_DIV (+ (# 3 (SHAPE input_0)) -1) 2) 2) 2) 2) 2) 1) (+ (FLOOR_DIV (FLOOR_DIV (FLOOR_DIV (FLOOR_DIV (FLOOR_DIV (+ (# 2 (SHAPE input_0)) -1) 2) 2) 2) 2) 2) 1)

4

Hi, the error I got: [TensorRT] INFO: Some tactics do not have sufficient workspace memory to run. Increasing workspace size may increase performance, please check verbose output. [TensorRT] WARNING: Myelin...

万年bug:用gpu推理Segmentation fault(core dumped)

3

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：CentOS Linux release 7.9.2009 (Core） - CUDA 10,2, cudnn 8.0.4 - 版本号/Version：Paddle：2.3.2 PaddleOCR：2.6.1.0 问题相关组件/Related components： - 运行指令/Command Code：示例paddleocr...

### Prerequisite - [X] I have searched [the existing and past issues](https://github.com/open-mmlab/mmyolo/issues) but cannot get the expected help. - [X] I have read the [FAQ documentation](https://mmyolo.readthedocs.io/en/latest/faq.html) but cannot get the...

萌新请教作者一个问题，为什么当NYU_DATA=True时，焦距使用FL=715.0873，以及这里FL的单位是什么。 nyudepthv2_train_files_with_gt.txt 中， /kitchen_0028b/rgb_00027.jpg /kitchen_0028b/sync_depth_00027.png 518.8579 /printer_room_0001/rgb_00065.jpg /printer_room_0001/sync_depth_00065.png 518.8579 这里的518.8579指的是焦距吗？ 劳烦作者指教，不胜感激~

SER+RE联合推理报错:InvalidArgumentError: The type of data we are trying to retrieve does not match the type of data currently contained in the container.

2

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：CentOS Linux release 7.9.2009 (Core) - 版本号/Version：Paddle： PaddleOCR： 问题相关组件/Related components： paddleclas 2.5.1 paddlefsl 1.1.0 paddlenlp 2.2.1 paddleocr 2.6.1.0...

ValueError: (InvalidArgument) Broadcast dimension mismatch. Operands could not be broadcast together with the shape of X = [3, 1152, 64] and the shape of Y = [1, 960, 64]. Received [1152] in X is not equal to [960] in Y at i:1. [Hint: Expected x_dims_array[i] == y_dims_array[i] || x_dims_array[i] <= 1 || y_dims_array[i] <= 1 == true, but received x_dims_array[i] == y_dims_array[i] || x_dims_array[i] <= 1 || y_dims_array[i] <= 1:0 != true:1.] (at ../paddle/phi/kernels/funcs/common_shape.h:86) [operator < elementwise_add > error]

1

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：centos7 - 版本号/Version：Paddle：paddlepaddle-gpu 2.5.2.post112 PaddleOCR：2.7.0.3 问题相关组件/Related components： - 运行指令/Command Code： ocr = PaddleOCR(use_angle_cls=False, lang="ch", det_model_dir = det_model_dir, rec_model_dir...

from utils.io import prepare_input_image data_dir = 'focal stack images directory' ####Load the focal stack images focal_stack, rgb_img, focus_dist = prepare_input_image(data_dir) 使用prepare_input_image进行预处理时，如 focus_dist = np.append(focus_dist, float(image_files[0].split("_")[-1].removesuffix(".png"))) 这里把第一这张图片名作为焦距是为什么呢，另外可以解释下预处理流程吗 （萌新请教 谢谢大佬）