[NeurIPS 2022 Spotlight] VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training
1.32k
stars
131
forks
source link
TypeError: __init__() got an unexpected keyword argument 'all_frames' #77
Open
rahulstupa opened 1 year ago
Hello
I am getting following error while choosing the model type "vit_small_patch16_384".
command:
python run_class_finetuning.py \ --model vit_small_patch16_384 \ --data_set Kinetics-400 \ --nb_classes 2 \ --data_path ${DATA_PATH} \ --finetune ${MODEL_PATH} \ --log_dir ${OUTPUT_DIR} \ --output_dir ${OUTPUT_DIR} \ --batch_size 2 \ --num_sample 1 \ --input_size 384 \ --short_side_size 384 \ --save_ckpt_freq 10 \ --num_frames 16 \ --sampling_rate 1 \ --opt adamw \ --lr 1e-3 \ --opt_betas 0.9 0.999 \ --weight_decay 0.05 \ --epochs 100 \ --dist_eval \ --test_num_segment 5 \ --test_num_crop 3 \