SuperYOLO issues

1

yuan-kai-design

用small_EDSR_fold1进行test报错：ModuleNotFoundError: No module named 'models.deeplabedsr'

1

yuan-kai-design

请问MF模块的输入为什么是256尺寸的，imgsz不是1024吗？

leileilei2000

L1loss里的输入参数问题

sr_loss = 0.1*(torch.nn.L1Loss()(output_sr[:,0:3,:,:,],image)+torch.nn.L1Loss()(output_sr[:,3:,:,:,],ir_image[:,0:1,:,:,])) 请问output_sr、image、ir_image是在哪里引入的？我没有找到具体的位置我在上面找到了pred,output_sr,_ = model(imgs,irs,opt.input_mode)，但是model有好多个我不知道具体是哪个，所以找不到output_sr和imgs,irs的值是什么

leileilei2000

运行SRyolo.py报错

1

您好作者，运行`SRyolo.py`时报错： `IndexError: index 1 is out of bounds for dimension 0 with size 1` 请问下该怎么解决呢？

love-whut

数据类型报错

Plotting labels... Traceback (most recent call last): File "/data1/zhouyanqi/SuperYOLO-main/train.py", line 673, in train(hyp, opt, device, tb_writer) File "/data1/zhouyanqi/SuperYOLO-main/train.py", line 248, in train tb_writer.add_histogram('classes', c, 0) File "/home/zminghang/anaconda3/envs/mmdet/lib/python3.8/site-packages/torch/utils/tensorboard/writer.py", line 484, in...

fanfanqiqi

执行测试指令torch报错AttributeError: 'Upsample' object has no attribute 'recompute_scale_factor'

1

执行python3 test.py --weight ./weights/small_EDSR_MF_fold1.pt --input_mode RGB+IR+MF打印报错如下： Namespace(augment=False, batch_size=1, conf_thres=0.001, data='data/SRvedai.yaml', device='1', exist_ok=False, img_size=512, input_mode='RGB+IR+MF', iou_thres=0.6, name='exp', project='runs/test', save_conf=False, save_hybrid=False, save_json=False, save_txt=False, single_cls=False, task='val', verbose=False, weights=['./weights/small_EDSR_MF_fold1.pt']) YOLOv5 🚀 2024-3-13 torch 1.13.0+cu116...

Joys001