Hi there,
thanks for the work. We are trying to reproduce the experiments, however, both training and validation top1 accuracy were closed to 0. We followed the configuration in another issue #3 , with batch_size adjusted:
python main.py --root_path ~/ --video_path ~/datasets/jester --annotation_path Efficient-3DCNNs/annotation_UCF101/ucf101_01.json --result_path Efficient-3DCNNs/results --pretrain_path Efficient-3DCNNs/results/kinetics_shufflenet_0.5x_G3_RGB_16_best.pth --dataset ucf101 --n_classes 600 --n_finetune_classes 101 --ft_portion last_layer --model shufflenet --groups 3 --width_mult 0.5 --train_crop random --learning_rate 0.1 --sample_duration 16 --batch_size 64 --n_threads 16 --checkpoint 1 --n_val_samples 1 \ Anyone could provide any thoughts? Thanks
Hi there, thanks for the work. We are trying to reproduce the experiments, however, both training and validation top1 accuracy were closed to 0. We followed the configuration in another issue #3 , with
batch_sizeadjusted:python main.py --root_path ~/ --video_path ~/datasets/jester --annotation_path Efficient-3DCNNs/annotation_UCF101/ucf101_01.json --result_path Efficient-3DCNNs/results --pretrain_path Efficient-3DCNNs/results/kinetics_shufflenet_0.5x_G3_RGB_16_best.pth --dataset ucf101 --n_classes 600 --n_finetune_classes 101 --ft_portion last_layer --model shufflenet --groups 3 --width_mult 0.5 --train_crop random --learning_rate 0.1 --sample_duration 16 --batch_size 64 --n_threads 16 --checkpoint 1 --n_val_samples 1 \Anyone could provide any thoughts? Thanks