hanshuning的专栏

显存充足，但是却出现CUDA error:out of memory错误添加：import os# 设置程序使用的GPU编号：我用6号和7号显卡os.environ['CUDA_VISIBLE_DEVICES'] = '0,1'import numpy as npimport kerasimport keras.backend as Kimport tensorflow.compat.v1 as tftf.disable_v2_behavior()import keras.b

Could not load library cudnn_cnn_infer64_8.dll. Error code 126Please make sure cudnn_cnn_infer64_8.dll is in your library path!C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.5\lib下有对应文件，但是依旧报错。解决：cudnn版本从8.3改为8.2Index of /anaconda/pkgs/main/

https://pytorch-geometric.readthedocs.io/en/latest/index.htmlINTRODUCTION BY EXAMPLEhttps://pytorch-geometric.readthedocs.io/en/latest/notes/introduction.htmlA graph is used to model pairwise relations (edges) between objects (nodes). A single graph in

https://github.com/rusty1s/pytorch_sparseYou can now install pytorch-sparse via Anaconda for all major OS/PyTorch/CUDA combinations ???? Given that you have pytorch >= 1.8.0 installed, simply runconda install pytorch-sparse -c pyg

import tensorflow as tf改为：import tensorflow.compat.v1 as tftf.disable_v2_behavior()

arguments = docopt(doc) 报错：docopt.DocoptLanguageError: “usage:” (case-insensitive) not found.在“”"“”"直接添加Usage:，Options:等说明。例：“”"Using multilayer perceptron (MLP) and ensemble learning to classify the ASD and TC based on single brain atlas.Usage:n

import onnximport mlagentsimport onnxruntime as ortimport numpy as npimport timeimport torchimport mathimport gymimport tensorflow as tffrom gym_unity.envs import UnityToGymWrapperfrom mlagents_envs.environment import UnityEnvironmentfrom mlagen

官网：https://github.com/onnx/onnxpip install onnx读取.onnx文件：import onnxmodel = onnx.load(r’C:\Users\Win10\Desktop\Pyramids.onnx’ )print(model)