Pruned Yolov8 model not loading? about torch-pruning HOT 3 OPEN

have you solove this question? i had met same problem

from torch-pruning.

have you solove this question? i had met same problem

@luoshiyong Not yet. How did you saved your model ?

from torch-pruning.

Hi,

I managed to use the example demo of Yolov8.
Then I'm able to load and run the pruned model by using :

from ultralytics.nn.tasks import attempt_load_one_weight
model, _ = attempt_load_one_weight(weights)

But for that I need to import the C2f_v2 class as it's not part of ultralytics YOLOV8 :
class C2f_v2(nn.Module):
# CSP Bottleneck with 2 convolutions
def init(self, c1, c2, n=1, shortcut=False, g=1, e=0.5): # ch_in, ch_out, number, shortcut, groups, expansion
super().init()
self.c = int(c2 * e) # hidden channels
self.cv0 = Conv(c1, self.c, 1, 1)
self.cv1 = Conv(c1, self.c, 1, 1)
self.cv2 = Conv((2 + n) * self.c, c2, 1) # optional act=FReLU(c2)
self.m = nn.ModuleList(Bottleneck(self.c, self.c, shortcut, g, k=((3, 3), (3, 3)), e=1.0) for _ in range(n))

def forward(self, x):
    # y = list(self.cv1(x).chunk(2, 1))
    y = [self.cv0(x), self.cv1(x)]
    y.extend(m(y[-1]) for m in self.m)
    return self.cv2(torch.cat(y, 1))

Hope it will help!

from torch-pruning.