TommyNgx

/

YOLOv10-Fire-and-Smoke-Detection

like 5

same can't load the safetensors file too

same

docs are incomplete, missing critical information!

Revert to the earlier commit to find and download the best.pt file.

from ultralytics import YOLO
from PIL import Image

model = YOLO('best.pt')
image = Image.open("path/to/image.jpg")
results = model.predict(image, conf=0.25, iou=0.45)
results[0].show()

The model loads and predicts fire and smoke objects. At a glance, it works.

p.s. - I also couldn't get the bin and safetensors model weight files working, even after renaming OrderedDicts keys, there were missing keys, as required by yolo.load_state_dict() function.

1) Error with pytorch_model.bin

model_path = "pytorch_model.bin"
state_dict = torch.load(model_path, map_location="cpu")
state_dict = replace_OrderedDict(state_dict, prepend='model.')
model = YOLO()
model.load_state_dict(state_dict, strict=False)
> RuntimeError: Error(s) in loading state_dict for YOLO:
    size mismatch for model.model.0.conv.weight: copying a param with shape torch.Size([80, 3, 3, 3]) from checkpoint, the shape in current model is torch.Size([16, 3, 3, 3]).)

2) Error with model.safetensors

model_path = "model.safetensors"
state_dict = torch.load(model_path, map_location="cpu")
model = YOLO()
model.load_state_dict(state_dict, strict=False)
> UnpicklingError: could not find MARK