adrien-jacquot

Hey, I found a way to properly load the model (don't ask me why it works): ```python model = Yolov4(yolov4conv137weight=None, n_classes=1, inference=True) device = torch.device('cuda' if torch.cuda.is_available() else 'cpu') if...

Hey, I found a way to properly load the model (don't ask me why it works): ```python model = Yolov4(yolov4conv137weight=None, n_classes=1, inference=True) device = torch.device('cuda' if torch.cuda.is_available() else 'cpu') if...

Here's a slightly different version: ```python device = torch.device('cuda' if torch.cuda.is_available() else 'cpu') def load_model(model, pretrained_dict, parallelize): if parallelize: model = torch.nn.DataParallel(model) model.to(device=device) model.load_state_dict(pretrained_dict) return model def init(model_path): model =...

Not really, sorry. What is the error you're getting?

Used the following in my case: ```python def get_image_id(filename: str) -> int: """ Convert a string to a integer.... """ _, no = os.path.splitext(os.path.basename(filename))[0].split("_") no = f"{int(no):04d}" return int(no) ```...

Try the following config (suggested in https://github.com/Tianxiaomo/pytorch-YOLOv4/blob/master/Use_yolov4_to_train_your_own_data.md) ```python Cfg.batch = 4 Cfg.subdivisions = 1 ```

Hey, I found a way to properly load the model (don't ask me why it works): ```python model = Yolov4(yolov4conv137weight=None, n_classes=1, inference=True) device = torch.device('cuda' if torch.cuda.is_available() else 'cpu') if...

Hey, I found a way to properly load the model (don't ask me why it works): ```python model = Yolov4(yolov4conv137weight=None, n_classes=1, inference=True) device = torch.device('cuda' if torch.cuda.is_available() else 'cpu') if...

Hello! Can you add French to the list? Thanks :)

2.2.0