icey-zhang/ghost

GHOST is accepted by TGRS

ghost's Issues

Using custom dataset

Hi and thanks for this great work
I want to use VisDrone dataset, but I don't know how to transform the dataset to the format that your code supports, should I convert it to yolo format? coco format or is there any specific format?

Use YOLOv5 instead of SuperYolo

Hi
Is it possible to use other models like YOLOv5 instead of SuperYolo with GHOST?

Input and output sizes should be greater than 0, but got input (H: 16, W: 16) output (H: 0, W: 0)

Hi
I tried to train an SRyolo model with VisDrone dataset, but this error occurs
any help would be appriciated!

---

Namespace(adam=False, artifact_alias='latest', batch_size=2, bbox_interval=-1, bucket='', cache_images=False, cfg='models/SRyolo_noFocus.yaml', ch=3, ch_steam=3, da
ta='data/VisDrone.yaml', device='0', entity=None, epochs=1, evolve=False, exist_ok=False, global_rank=-1, hr_input=True, hyp='data/hyp.scratch.yaml', image_weights=
False, img_size=[512, 512], input_mode='RGB', linear_lr=False, local_rank=-1, multi_scale=False, name='exp', noautoanchor=False, nosave=False, notest=False, project
='runs/train', quad=False, rect=False, resume=False, save_dir='runs\train\exp4', save_period=-1, single_cls=False, super=True, sync_bn=False, test_img_size=512, total_batch_size=2, train_img_size=512, upload_dataset=False, weights='', workers=4, world_size=1)
tensorboard: Start with 'tensorboard --logdir runs/train', view at http://localhost:6006/
hyperparameters: lr0=0.01, lrf=0.2, momentum=0.937, weight_decay=0.0005, warmup_epochs=3.0, warmup_momentum=0.8, warmup_bias_lr=0.1, box=0.05, cls=0.5, cls_pw=1.0,
obj=1.0, obj_pw=1.0, iou_t=0.2, anchor_t=4.0, kl_pw=1.0, fl_gamma=0.0, hsv_h=0.015, hsv_s=0.7, hsv_v=0.4, degrees=0.0, translate=0.1, scale=0.5, shear=0.0, perspective=0.0, flipud=0.0, fliplr=0.5, mosaic=1.0, mixup=0.0, copy_paste=0.1
wandb: Install Weights & Biases for YOLOv5 logging with 'pip install wandb' (recommended)
Overriding model.yaml nc=8 with nc=10

from n params module arguments
0 -1 1 928 models.common.Conv [3, 32, 3, 1]
1 -1 1 18560 models.common.Conv [32, 64, 3, 2]
2 -1 1 18816 models.common.C3 [64, 64, 1]
3 -1 1 73984 models.common.Conv [64, 128, 3, 2]
4 -1 1 156928 models.common.C3 [128, 128, 3]
5 -1 1 295424 models.common.Conv [128, 256, 3, 2]
6 -1 1 625152 models.common.C3 [256, 256, 3]
7 -1 1 1180672 models.common.Conv [256, 512, 3, 2]
8 -1 1 656896 models.common.SPP [512, 512, [5, 9, 13]]
9 -1 1 1182720 models.common.C3 [512, 512, 1, False]
10 -1 1 131584 models.common.Conv [512, 256, 1, 1]
11 -1 1 0 torch.nn.modules.upsampling.Upsample [None, 2, 'nearest']
12 [-1, 6] 1 0 models.common.Concat [1]
13 -1 1 361984 models.common.C3 [512, 256, 1, False]
14 -1 1 33024 models.common.Conv [256, 128, 1, 1]
15 -1 1 0 torch.nn.modules.upsampling.Upsample [None, 2, 'nearest']
16 [-1, 4] 1 0 models.common.Concat [1]
17 -1 1 90880 models.common.C3 [256, 128, 1, False]
18 -1 1 147712 models.common.Conv [128, 128, 3, 2]
19 [-1, 14] 1 0 models.common.Concat [1]
20 -1 1 296448 models.common.C3 [256, 256, 1, False]
21 -1 1 590336 models.common.Conv [256, 256, 3, 2]
22 [-1, 10] 1 0 models.common.Concat [1]
23 -1 1 1182720 models.common.C3 [512, 512, 1, False]
24 [17, 20, 23] 1 40455 models.SRyolo.Detect [10, [[10, 13, 16, 30, 33, 23], [30, 61, 62, 45, 59, 119], [116, 90, 156, 198, 373, 326]], [128, 256, 512]]
Traceback (most recent call last):
File "train.py", line 674, in
train(hyp, opt, device, tb_writer)
File "train.py", line 103, in train
model = Model(opt.cfg, input_mode = opt.input_mode ,ch_steam=opt.ch_steam,ch=opt.ch, nc=nc, anchors=hyp.get('anchors'),config=None,sr=opt.super,factor=down_factor).to(device) # create
File "N:\Master\Thesis\Code\KD\12row_third_try\GHOST\models\SRyolo.py", line 117, in init
m.stride = torch.tensor([s / x.shape[-2] for x in self.forward(torch.zeros(1, ch_steam, s, s),torch.zeros(1, ch_steam, s, s),input_mode)[0]]) # forward
File "N:\Master\Thesis\Code\KD\12row_third_try\GHOST\models\SRyolo.py", line 190, in forward
y,output_sr,features = self.forward_once(steam,'yolo', profile) #zjq
File "N:\Master\Thesis\Code\KD\12row_third_try\GHOST\models\SRyolo.py", line 243, in forward_once
output_sr = self.model_up(y[self.l1],y[self.l2]) #在超分上加attention
File "C:\Users_Melika_\miniconda3\envs\yolo\lib\site-packages\torch\nn\modules\module.py", line 1501, in call_impl
return forward_call(*args, **kwargs)
File "N:\Master\Thesis\Code\KD\12row_third_try\GHOST\models\deeplabedsr.py", line 60, in forward
x_sr= self.sr_decoder(x, low_level_feat,self.factor)
File "C:\Users_Melika\miniconda3\envs\yolo\lib\site-packages\torch\nn\modules\module.py", line 1501, in call_impl
return forward_call(*args, *kwargs)
File "N:\Master\Thesis\Code\KD\12row_third_try\GHOST\models\sr_decoder_noBN_noD.py", line 38, in forward
x = F.interpolate(x, size=[i(factor//2) for i in low_level_feat.size()[2:]], mode='bilinear', align_corners=True)
File "C:\Users_Melika\miniconda3\envs\yolo\lib\site-packages\torch\nn\functional.py", line 3959, in interpolate
return torch._C._nn.upsample_bilinear2d(input, output_size, align_corners, scale_factors)
RuntimeError: Input and output sizes should be greater than 0, but got input (H: 16, W: 16) output (H: 0, W: 0)

---

想请教作者这几个问题

这个的意思是权重都用train后得到的一样的权重吗？为什么要用两个一样的权重呢？