File size: 1,364 Bytes
ef1c94f
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
dset_name=hl
ctx_mode=video_tef
v_feat_types=slowfast_clip
t_feat_type=clip 
results_root=results
exp_id=pt

######## data paths
train_path=data/subs_train.jsonl
eval_path=data/highlight_val_release.jsonl
eval_split_name=val

######## setup video+text features
feat_root=features

# video features
v_feat_dim=0
v_feat_dirs=()
if [[ ${v_feat_types} == *"slowfast"* ]]; then
  v_feat_dirs+=(${feat_root}/slowfast_features)
  (( v_feat_dim += 2304 ))  # double brackets for arithmetic op, no need to use ${v_feat_dim}
fi
if [[ ${v_feat_types} == *"clip"* ]]; then
  v_feat_dirs+=(${feat_root}/clip_features)
  (( v_feat_dim += 512 ))
fi

# text features
if [[ ${t_feat_type} == "clip" ]]; then
  t_feat_dir=${feat_root}/clip_sub_features/
  t_feat_dim=512
else
  echo "Wrong arg for t_feat_type."
  exit 1
fi

#### training
bsz=256
num_workers=8
n_epoch=100
max_es_cnt=100
exp_id=pt


PYTHONPATH=$PYTHONPATH:. python moment_detr/train.py \
--dset_name ${dset_name} \
--ctx_mode ${ctx_mode} \
--train_path ${train_path} \
--eval_path ${eval_path} \
--eval_split_name ${eval_split_name} \
--v_feat_dirs ${v_feat_dirs[@]} \
--v_feat_dim ${v_feat_dim} \
--t_feat_dir ${t_feat_dir} \
--t_feat_dim ${t_feat_dim} \
--bsz ${bsz} \
--results_root ${results_root} \
--num_workers ${num_workers} \
--exp_id ${exp_id} \
--n_epoch ${n_epoch} \
--max_es_cnt ${max_es_cnt} \
${@:1}