AttributeError: 'Detect' object has no attribute 'nm'

[Sheen23]

when I want to train segment/train.py, this problem comes out. how can I solve it...please

[glenn-jocher]

@Sheen23 👋 hi, thanks for letting us know about this possible problem with YOLOv5 🚀. We've created a few short guidelines below to help users provide what we need in order to start investigating a possible problem.

Also see the Segmentation notebook for examples:
https://github.com/ultralytics/yolov5/blob/master/segment/tutorial.ipynb

How to create a Minimal, Reproducible Example

When asking a question, people will be better able to provide help if you provide code that they can easily understand and use to reproduce the problem. This is referred to by community members as creating a minimum reproducible example. Your code that reproduces the problem should be:

• ✅ Minimal – Use as little code as possible to produce the problem
• ✅ Complete – Provide all parts someone else needs to reproduce the problem
• ✅ Reproducible – Test the code you're about to provide to make sure it reproduces the problem

For Ultralytics to provide assistance your code should also be:

• ✅ Current – Verify that your code is up-to-date with GitHub master, and if necessary git pull or git clone a new copy to ensure your problem has not already been solved in master.
• ✅ Unmodified – Your problem must be reproducible using official YOLOv5 code without changes. Ultralytics does not provide support for custom code ⚠️.

If you believe your problem meets all the above criteria, please close this issue and raise a new one using the 🐛 Bug Report template with a minimum reproducible example to help us better understand and diagnose your problem.

Thank you! 😃

[Wouter1]

Same problem here.

This how-to-reproduce is pretty complex unfortunately as you need so many files and handwork is involved in configuring.

I have 5 train images.
I created a dataset using labelme.

Then I used labelme2yolo to create a yolo dataset.
cd data_annotated
labelme2yolo --json_dir .

I copied the dataset to yolov5/datasets/YOLODataset

dataset.yaml inside there:

train: ./YOLODataset/images/train/
val: ./YOLODataset/images/val/
test: ./YOLODataset/images/test/
nc: 9
names: ['9 bracket', '7 plate', '6 bar', '3 sphere', '8 transparentplate', '1 pyramid', '4 halfsphere', '2 cube', '5 ring']

I copied dataset.yaml to the root of the yolov5 folder. Actually it's not clear where you should run yolo5 and what pythonpath should be set at. So I run from root of yolov5 and make all paths relative to there

So I make a root copy of dataset.yaml with modified content

train: datasets/YOLODataset/images/train/
val: datasets/YOLODataset/images/val/
test: datasets/YOLODataset/images/test/
nc: 9
names: ['9 bracket', '7 plate', '6 bar', '3 sphere', '8 transparentplate', '1 pyramid', '4 halfsphere', '2 cube', '5 ring']

Then I creates a models/set1.yaml file with this

# YOLOv5 🚀 by Ultralytics, GPL-3.0 license

# Parameters
nc: 9  # number of classes
depth_multiple: 0.33  # model depth multiple
width_multiple: 0.50  # layer channel multiple
anchors:
  - [10,13, 16,30, 33,23]  # P3/8
  - [30,61, 62,45, 59,119]  # P4/16
  - [116,90, 156,198, 373,326]  # P5/32

# YOLOv5 v6.0 backbone
backbone:
  # [from, number, module, args]
  [[-1, 1, Conv, [64, 6, 2, 2]],  # 0-P1/2
   [-1, 1, Conv, [128, 3, 2]],  # 1-P2/4
   [-1, 3, C3, [128]],
   [-1, 1, Conv, [256, 3, 2]],  # 3-P3/8
   [-1, 6, C3, [256]],
   [-1, 1, Conv, [512, 3, 2]],  # 5-P4/16
   [-1, 9, C3, [512]],
   [-1, 1, Conv, [1024, 3, 2]],  # 7-P5/32
   [-1, 3, C3, [1024]],
   [-1, 1, SPPF, [1024, 5]],  # 9
  ]

# YOLOv5 v6.0 head
head:
  [[-1, 1, Conv, [512, 1, 1]],
   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
   [[-1, 6], 1, Concat, [1]],  # cat backbone P4
   [-1, 3, C3, [512, False]],  # 13

   [-1, 1, Conv, [256, 1, 1]],
   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
   [[-1, 4], 1, Concat, [1]],  # cat backbone P3
   [-1, 3, C3, [256, False]],  # 17 (P3/8-small)

   [-1, 1, Conv, [256, 3, 2]],
   [[-1, 14], 1, Concat, [1]],  # cat head P4
   [-1, 3, C3, [512, False]],  # 20 (P4/16-medium)

   [-1, 1, Conv, [512, 3, 2]],
   [[-1, 10], 1, Concat, [1]],  # cat head P5
   [-1, 3, C3, [1024, False]],  # 23 (P5/32-large)

   [[17, 20, 23], 1, Detect, [nc, anchors]],  # Detect(P3, P4, P5)
  ]

It's basically a copy of a yolov.yaml file with the nc modified.

Now you can go to root of yolov5 and run

python segment/train.py --img 640 --batch 16 --epochs 5 --data dataset.yaml --cfg models/set1.yaml

Some example from your wiki also used a --weights option. Some other example specifies --weights but without argument, and that one fails right away. I found that completely leaving out --weights at least starts the training.

That will give you the reported error

$ python segment/train.py --img 640 --batch 16 --epochs 5 --data dataset.yaml --cfg models/set1.yaml --weights ''
segment/train: weights=, cfg=models/set1.yaml, data=dataset.yaml, hyp=data/hyps/hyp.scratch-low.yaml, epochs=5, batch_size=16, imgsz=640, rect=False, resume=False, nosave=False, noval=False, noautoanchor=False, noplots=False, evolve=None, bucket=, cache=None, image_weights=False, device=, multi_scale=False, single_cls=False, optimizer=SGD, sync_bn=False, workers=8, project=runs/train-seg, name=exp, exist_ok=False, quad=False, cos_lr=False, label_smoothing=0.0, patience=100, freeze=[0], save_period=-1, seed=0, local_rank=-1, mask_ratio=4, no_overlap=False
github: up to date with https://github.com/ultralytics/yolov5 ✅
YOLOv5 🚀 v7.0-53-g65071da Python-3.10.6 torch-1.13.1+cu117 CUDA:0 (NVIDIA GeForce RTX 2070, 7967MiB)

hyperparameters: lr0=0.01, lrf=0.01, 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, 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=0.0
TensorBoard: Start with 'tensorboard --logdir runs/train-seg', view at http://localhost:6006/

                 from  n    params  module                                  arguments                     
  0                -1  1      3520  models.common.Conv                      [3, 32, 6, 2, 2]              
  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  2    115712  models.common.C3                        [128, 128, 2]                 
  5                -1  1    295424  models.common.Conv                      [128, 256, 3, 2]              
  6                -1  3    625152  models.common.C3                        [256, 256, 3]                 
  7                -1  1   1180672  models.common.Conv                      [256, 512, 3, 2]              
  8                -1  1   1182720  models.common.C3                        [512, 512, 1]                 
  9                -1  1    656896  models.common.SPPF                      [512, 512, 5]                 
 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     37758  models.yolo.Detect                      [9, [[10, 13, 16, 30, 33, 23], [30, 61, 62, 45, 59, 119], [116, 90, 156, 198, 373, 326]], [128, 256, 512]]
set1 summary: 214 layers, 7043902 parameters, 7043902 gradients, 16.0 GFLOPs

AMP: checks passed ✅
optimizer: SGD(lr=0.01) with parameter groups 57 weight(decay=0.0), 60 weight(decay=0.0005), 60 bias
train: Scanning /home/wouter/Desktop/yolov5/datasets/YOLODataset/labels/train.cache... 5 images, 0 backgrounds, 
val: Scanning /home/wouter/Desktop/yolov5/datasets/YOLODataset/labels/val.cache... 2 images, 0 backgrounds, 0 co

AutoAnchor: 5.23 anchors/target, 1.000 Best Possible Recall (BPR). Current anchors are a good fit to dataset ✅
Plotting labels to runs/train-seg/exp15/labels.jpg... 
Traceback (most recent call last):
  File "/home/wouter/Desktop/yolov5/segment/train.py", line 658, in <module>
    main(opt)
  File "/home/wouter/Desktop/yolov5/segment/train.py", line 554, in main
    train(opt.hyp, opt, device, callbacks)
  File "/home/wouter/Desktop/yolov5/segment/train.py", line 254, in train
    compute_loss = ComputeLoss(model, overlap=overlap)  # init loss class
  File "/home/wouter/Desktop/yolov5/utils/segment/loss.py", line 40, in __init__
    self.nm = m.nm  # number of masks
  File "/home/wouter/Desktop/yolov5/venv/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1269, in __getattr__
    raise AttributeError("'{}' object has no attribute '{}'".format(
AttributeError: 'Detect' object has no attribute 'nm'. Did you mean: 'm'?

I hope I got everything,I tried a lot of things

[Polaris-Zhang]

hey bro,now,I have face the same question:
AutoAnchor: 2.77 anchors/target, 1.000 Best Possible Recall (BPR). Current anchors are a good fit to dataset
Plotting labels to ..\runs\train-seg\exp25\labels.jpg...
Traceback (most recent call last):
File "D:\DL\yolov5-7.0\yolov5-7.0\segment\train.py", line 658, in
main(opt)
File "D:\DL\yolov5-7.0\yolov5-7.0\segment\train.py", line 554, in main
train(opt.hyp, opt, device, callbacks)
File "D:\DL\yolov5-7.0\yolov5-7.0\segment\train.py", line 254, in train
compute_loss = ComputeLoss(model, overlap=overlap) # init loss class
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\DL\yolov5-7.0\yolov5-7.0\utils\segment\loss.py", line 40, in init
self.nm = m.nm # number of masks
^^^^
File "C:\Users\15401.conda\envs\pytorch\Lib\site-packages\torch\nn\modules\module.py", line 1614, in getattr
raise AttributeError("'{}' object has no attribute '{}'".format(
AttributeError: 'Detect' object has no attribute 'nm'. Did you mean: 'm'?
thus，Have you solved this problem? If so, could you please reply to me? thanks!

[Zerohertz]

I also got the same error.

--cfg makes that problem!

Exclude --cfg when running segment/train.py

[jehan88]

i had the same problem then i solved it by using --weights yolov5s-seg.pt

[acderem123]

thank you very much

[WtElio]

The same error happened to me,The following is my solution:
make sure your model.yaml is a segment yaml file

[Tina291]

Thanks,it's helpful