Weiwenliang123
Weiwenliang123
def build_cotracker(checkpoint=None, offline=True, window_len=16, v2=False): if offline: cotracker = CoTrackerThreeOffline( stride=4, corr_radius=3, window_len=window_len ) else: if v2: cotracker = CoTracker2(stride=4, window_len=window_len) else: cotracker = CoTrackerThreeOnline( stride=4, corr_radius=3, window_len=window_len ) if...
When I run the command "accelerate launch train_inference.py --config configs/car_forest.yml", the problem of "torch.distributed.elastic.multiprocessing.errors.ChildFailedError" occurs, making it impossible to conduct training and inference simultaneously. Therefore, I want to carry them...