cwq159 / PyTorch-Spiking-YOLOv3

A PyTorch implementation of Spiking-YOLOv3. Two branches are provided, based on two common PyTorch implementation of YOLOv3(ultralytics/yolov3 & eriklindernoren/PyTorch-YOLOv3), with support for Spiking-YOLOv3-Tiny at present.
GNU General Public License v3.0
207 stars 58 forks source link

寻求大佬帮助,这个问题怎么解决 #56

Open 123456ZF opened 1 year ago

123456ZF commented 1 year ago

Start Tensorboard with "tensorboard --logdir=runs", view at http://localhost:6006/ Model Summary: 225 layers, 6.29987e+07 parameters, 6.29987e+07 gradients Optimizer groups: 76 .bias, 76 Conv2d.weight, 73 other Traceback (most recent call last): File "/home/chenqq/anaconda3/envs/smoke/Spiking_YOLOv3/train.py", line 435, in train(hyp) # train normally File "/home/chenqq/anaconda3/envs/smoke/Spiking_YOLOv3/train.py", line 199, in train single_cls=opt.single_cls) File "/home/chenqq/anaconda3/envs/smoke/Spiking_YOLOv3/utils/datasets.py", line 278, in init assert n > 0, 'No images found in %s. See %s' % (path, help_url) AssertionError: No images found in /home/chenqq/anaconda3/envs/smoke/Spiking_YOLOv3/data/coco2017/train.txt. See https://github.com/ultralytics/yolov3/wiki/Train-Custom-Data

Bender-long commented 1 year ago

路径问题或者是数据集没处理好。

Bender-long commented 1 year ago

数据集处理可以看这个视频https://www.bilibili.com/video/BV1t54y1C7ra

Bender-long commented 1 year ago

数据集处理可以看这个视频https://www.bilibili.com/video/BV1t54y1C7ra

123456ZF commented 1 year ago

@Bender-long 请问您跑通了ann-snn吗,我用的gtx3060,环境torch 1.7.1+cu101 python3.7 出现了问题:ValueError:too many values to unpack(expected 2) 报错的位置是snn_evaluate.py,line 97 ( output_snn1,output_snn2=snn(data) 这个位置),请问有什么解决办法吗?

123456ZF commented 1 year ago

@Bender-long非常感谢您的回答

sun133233 commented 5 months ago

@Bender-long 请问您跑通了ann-snn吗,我用的gtx3060,环境torch 1.7.1+cu101 python3.7 出现了问题:ValueError:too many values to unpack(expected 2) 报错的位置是snn_evaluate.py,line 97 ( output_snn1,output_snn2=snn(data) 这个位置),请问有什么解决办法吗?

遇到了同样的问题,请问解决了吗

Bender-long commented 5 months ago

您好,该问题是torch版本太高导致的,我当时使用torch1.4就没有报错了

------------------ 原始邮件 ------------------ 发件人: "cwq159/PyTorch-Spiking-YOLOv3" @.>; 发送时间: 2024年3月20日(星期三) 下午4:44 @.>; @.**@.>; 主题: Re: [cwq159/PyTorch-Spiking-YOLOv3] 寻求大佬帮助,这个问题怎么解决 (Issue #56)

@Bender-long 请问您跑通了ann-snn吗,我用的gtx3060,环境torch 1.7.1+cu101 python3.7 出现了问题:ValueError:too many values to unpack(expected 2) 报错的位置是snn_evaluate.py,line 97 ( output_snn1,output_snn2=snn(data) 这个位置),请问有什么解决办法吗?

遇到了同样的问题,请问解决了吗

— Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you were mentioned.Message ID: @.***>

123456ZF commented 5 months ago

@sun133233 gtx3060你这太高了,你可以考虑降低显卡版本,然后下载torch1.6可以的,我是1660ti的

sun133233 commented 5 months ago

@Bender-long 解决了真的太感谢了!

sun133233 commented 5 months ago

@sun133233 gtx3060你这太高了,你可以考虑降低显卡版本,然后下载torch1.6可以的,我是1660ti的

@123456ZF 解决了真的太感谢了!