Skip to content

Gnerate jsons for the validation of ek100 #4

@Github0119

Description

@Github0119

Hi, thank you so much for the awesome work! After getting the results, I tried to generate jsons file for the validation set of ek100. However, I have not seen any file under the folder of anticipation. Could you help me with it! Thank you so much!
command line:
python main_anticipation.py --mode validate_json --json_directory ./jsons/anticipation --ek100 --path_to_data ./RULSTM/data/ek100 --path_to_models ./models_anticipation/ek100/ --modality rgb --num_class 3806 --verb_class 97 --noun_class 300

result:
Save file name anti_mod_rgb_span_6_s1_5_s2_3_s3_2_recent_2_r1_1.6_r2_1.2_r3_0.8_r4_0.4_bs_10_drop_0.3_lr_0.0001_dimLa_512_dimLi_512_epoc_15_vb_nn
Printing Arguments
Namespace(add_noun_loss=True, add_verb_loss=True, alpha=1, batch_size=10, best_model='best', debug_on=False, display_every=10, dropout_rate=0.3, ek100=True, epochs=15, img_tmpl='frame_{:010d}.jpg', json_directory='./jsons/anticipation', latent_dim=512, linear_dim=512, lr=0.0001, modality='rgb', mode='validate_json', noun_class=300, noun_loss_weight=1.0, num_class=3806, num_workers=0, past_attention=True, path_to_data='./RULSTM/data/ek100', path_to_models='./models_anticipation/ek100/', recent_dim=2, recent_sec1=1.6, recent_sec2=1.2, recent_sec3=0.8, recent_sec4=0.4, resume=False, scale=True, scale_factor=-0.5, schedule_epoch=10, schedule_on=1, span_dim1=5, span_dim2=3, span_dim3=2, spanning_sec=6, task='action_anticipation', topK=1, trainval=False, verb_class=97, verb_loss_weight=1.0, verb_noun_scores=True, video_feat_dim=352, weight_flow=0.1, weight_obj=0.25, weight_rgb=0.4, weight_roi=0.25)

However, there are no files in the folder.
Thanks

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions