Cannot use yolov8-lite-s

[aifanboylearner]

Hi,

I can use yolov8n but cannot seem to be able to use the other checkpoints: yolov8-lite-s and yolov8-lite-t

I tried installing latest version of ultralytics but then the weigths cannot be loaded.

I also tried using the custom folder ultralytics from this repo. In that case the weights can be loaded but inference then does not work.

[Vincent-Stragier]

@aifanboylearner,

Same issue here. I'm using Python 3.10 on Windows 11.

I have this kind of error:

    results = face_detector.predict(img, verbose=False, show=True, conf=0.25)[0]
  File "C:\Users\Vincent\AppData\Local\Programs\Python\Python310\lib\site-packages\torch\utils\_contextlib.py", line 115, in decorate_context
    return func(*args, **kwargs)
  File "C:\Users\Vincent\AppData\Local\Programs\Python\Python310\lib\site-packages\ultralytics\yolo\engine\model.py", line 252, in predict
    return self.predictor.predict_cli(source=source) if is_cli else self.predictor(source=source, stream=stream)
  File "C:\Users\Vincent\AppData\Local\Programs\Python\Python310\lib\site-packages\ultralytics\yolo\engine\predictor.py", line 157, in __call__
    return list(self.stream_inference(source, model))  # merge list of Result into one
  File "C:\Users\Vincent\AppData\Local\Programs\Python\Python310\lib\site-packages\torch\utils\_contextlib.py", line 35, in generator_context
    response = gen.send(None)
  File "C:\Users\Vincent\AppData\Local\Programs\Python\Python310\lib\site-packages\ultralytics\yolo\engine\predictor.py", line 221, in stream_inference
    preds = self.model(im, augment=self.args.augment, visualize=visualize)
  File "C:\Users\Vincent\AppData\Local\Programs\Python\Python310\lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl
    return forward_call(*args, **kwargs)
  File "C:\Users\Vincent\AppData\Local\Programs\Python\Python310\lib\site-packages\ultralytics\nn\autobackend.py", line 313, in forward
    y = self.model(im, augment=augment, visualize=visualize) if augment or visualize else self.model(im)
  File "C:\Users\Vincent\AppData\Local\Programs\Python\Python310\lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl
    return forward_call(*args, **kwargs)
  File "C:\Users\Vincent\AppData\Local\Programs\Python\Python310\lib\site-packages\ultralytics\nn\tasks.py", line 203, in forward
    return self._forward_once(x, profile, visualize)  # single-scale inference, train
  File "C:\Users\Vincent\AppData\Local\Programs\Python\Python310\lib\site-packages\ultralytics\nn\tasks.py", line 58, in _forward_once
    x = m(x)  # run
  File "C:\Users\Vincent\AppData\Local\Programs\Python\Python310\lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl
    return forward_call(*args, **kwargs)
  File "C:\Users\Vincent\AppData\Local\Programs\Python\Python310\lib\site-packages\ultralytics\nn\modules.py", line 479, in forward
    stem_1_out  = self.stem_1(x)
  File "C:\Users\Vincent\AppData\Local\Programs\Python\Python310\lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl
    return forward_call(*args, **kwargs)
  File "C:\Users\Vincent\AppData\Local\Programs\Python\Python310\lib\site-packages\ultralytics\nn\modules.py", line 66, in forward_fuse
    return self.act(self.conv(x))
  File "C:\Users\Vincent\AppData\Local\Programs\Python\Python310\lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl
    return forward_call(*args, **kwargs)
  File "C:\Users\Vincent\AppData\Local\Programs\Python\Python310\lib\site-packages\torch\nn\modules\conv.py", line 463, in forward
    return self._conv_forward(input, self.weight, self.bias)
  File "C:\Users\Vincent\AppData\Local\Programs\Python\Python310\lib\site-packages\torch\nn\modules\conv.py", line 459, in _conv_forward
    return F.conv2d(input, weight, bias, self.stride,
TypeError: conv2d() received an invalid combination of arguments - got (Tensor, Parameter, Parameter, tuple, tuple, tuple, int), but expected one of:
 * (Tensor input, Tensor weight, Tensor bias, tuple of ints stride, tuple of ints padding, tuple of ints dilation, int groups)
      didn't match because some of the arguments have invalid types: (Tensor, Parameter, Parameter, tuple of (int, int), tuple of (int, int), tuple of (bool, bool), int)
 * (Tensor input, Tensor weight, Tensor bias, tuple of ints stride, str padding, tuple of ints dilation, int groups)
      didn't match because some of the arguments have invalid types: (Tensor, Parameter, Parameter, tuple of (int, int), tuple of (int, int), tuple of (bool, bool), int)

[YSGFF]

I also have this problem, have you solved it？

[Vincent-Stragier]

@YSGFF,

Only yolov8n is working, nobody managed to work with the two others. So there is no solution, just use yolov8n.

Best,
Vincent

[JYW-SZ]

"ultralytics\nn\modules\block.py",line42

class StemBlock(nn.Module):
    def __init__(self, c1, c2, k=3, s=2, p=None, g=1,d=1, act=True):
        super(StemBlock, self).__init__()
        self.stem_1 = Conv(c1, c2, k, s, p, g, d, act)
        self.stem_2a = Conv(c2, c2 // 2, 1, 1, 0)
        self.stem_2b = Conv(c2 // 2, c2, 3, 2, 1)
        self.stem_2p = nn.MaxPool2d(kernel_size=2,stride=2,ceil_mode=True)
        self.stem_3 = Conv(c2 * 2, c2, 1, 1, 0)

[ganquan0513]

"ultralytics\nn\modules\block.py",line42

class StemBlock(nn.Module):
    def __init__(self, c1, c2, k=3, s=2, p=None, g=1,d=1, act=True):
        super(StemBlock, self).__init__()
        self.stem_1 = Conv(c1, c2, k, s, p, g, d, act)
        self.stem_2a = Conv(c2, c2 // 2, 1, 1, 0)
        self.stem_2b = Conv(c2 // 2, c2, 3, 2, 1)
        self.stem_2p = nn.MaxPool2d(kernel_size=2,stride=2,ceil_mode=True)
        self.stem_3 = Conv(c2 * 2, c2, 1, 1, 0)

This is helpful ,but you need modify the yolov8-lite-s-pose.yaml and yolov8-lite-t-pose.yaml config file ；

here the yaml `backbone:

[from, number, module, args]

[ [ -1, 1, StemBlock, [32, 3, 2,None,1] ], # 0-P2/4
[ -1, 1, Shuffle_Block, [96, 2]], # 1-P3/8
[ -1, 3, Shuffle_Block, [96, 1]], # 2
[ -1, 1, Shuffle_Block, [192, 2]], # 3-P4/16
[ -1, 7, Shuffle_Block, [192, 1]], # 4
[ -1, 1, Shuffle_Block, [384, 2]], # 5-P5/32
[ -1, 3, Shuffle_Block, [384, 1]], # 6
[ -1, 1, SPPF, [384, 5]],
]

v5lite-e head

head:
[ [ -1, 1, Conv, [96, 1, 1,None,1]],
[ -1, 1, nn.Upsample, [ None, 2, 'nearest']],
[[ -1, 4], 1, Concat, [1]], # cat backbone P4
[ -1, 1, DWConvblock, [96, 3, 1]], # 11

[ -1, 1, Conv, [96, 1, 1,None,1]],
[ -1, 1, nn.Upsample, [ None, 2, 'nearest']],
[[ -1, 2], 1, Concat, [1]],  # cat backbone P3
[ -1, 1, DWConvblock, [96, 3, 1] ],  # 15 (P3/8-small)

[-1, 1, DWConvblock, [96, 3, 2]],
[[ -1, 12], 1, ADD, [1]],  # cat head P4
[ -1, 1, DWConvblock, [96, 3, 1]],  # 18 (P4/16-medium)

[ -1, 1, DWConvblock, [96, 3, 2]],
[[ -1, 8], 1, ADD, [1]],  # cat head P5
[ -1, 1, DWConvblock, [96, 3, 1]],  # 21 (P5/32-large)

[[ 15, 18, 21], 1, Pose, [nc, kpt_shape]],  # Detect(P3, P4, P5)

]`

lite-t-pose:::`backbone:

[from, number, module, args]

[ [ -1, 1, StemBlock, [16, 3, 2,None,1] ], # 0-P2/4
[ -1, 1, Shuffle_Block, [48, 2]], # 1-P3/8
[ -1, 2, Shuffle_Block, [48, 1]], # 2
[ -1, 1, Shuffle_Block, [96, 2]], # 3-P4/16
[ -1, 5, Shuffle_Block, [96, 1]], # 4
[ -1, 1, Shuffle_Block, [192, 2]], # 5-P5/32
[ -1, 2, Shuffle_Block, [192, 1]], # 6
[ -1, 1, SPPF, [192, 5]],
]

v5lite-e head

head:
[ [ -1, 1, Conv, [48, 1, 1,None,1]],
[ -1, 1, nn.Upsample, [ None, 2, 'nearest']],
[[ -1, 4], 1, Concat, [1]], # cat backbone P4
[ -1, 1, DWConvblock, [48, 3, 1]], # 11

[ -1, 1, Conv, [48, 1, 1,None,1]],
[ -1, 1, nn.Upsample, [ None, 2, 'nearest']],
[[ -1, 2], 1, Concat, [1]],  # cat backbone P3
[ -1, 1, DWConvblock, [48, 3, 1] ],  # 15 (P3/8-small)

[-1, 1, DWConvblock, [48, 3, 2]],
[[ -1, 12], 1, ADD, [1]],  # cat head P4
[ -1, 1, DWConvblock, [48, 3, 1]],  # 18 (P4/16-medium)

[ -1, 1, DWConvblock, [48, 3, 2]],
[[ -1, 8], 1, ADD, [1]],  # cat head P5
[ -1, 1, DWConvblock, [48, 3, 1]],  # 21 (P5/32-large)
[[ 15, 18, 21], 1, Pose, [nc, kpt_shape]],  # Detect(P3, P4, P5)

]
`

[clibdev]

I have created a fork repository clibdev/yolov8-face which contains yolov8-lite-t and yolov8-lite-s models compatibility fixes.