Mido Assran
53 lines
984 B
YAML
53 lines
984 B
YAML
data:
|
|
batch_size: 128
|
|
color_jitter_strength: 0.0
|
|
crop_scale:
|
|
- 0.3
|
|
- 1.0
|
|
crop_size: 224
|
|
image_folder: imagenet_full_size/061417/
|
|
num_workers: 10
|
|
pin_mem: true
|
|
root_path: $replace_this_with_absolute_path_to_your_datasets_directory
|
|
use_color_distortion: false
|
|
use_gaussian_blur: false
|
|
use_horizontal_flip: false
|
|
logging:
|
|
folder: $replace_this_with_path_for_experiment_logs/vith14.224-bs.2048-ep.300/
|
|
write_tag: jepa
|
|
mask:
|
|
allow_overlap: false
|
|
aspect_ratio:
|
|
- 0.75
|
|
- 1.5
|
|
enc_mask_scale:
|
|
- 0.85
|
|
- 1.0
|
|
min_keep: 10
|
|
num_enc_masks: 1
|
|
num_pred_masks: 4
|
|
patch_size: 14
|
|
pred_mask_scale:
|
|
- 0.15
|
|
- 0.2
|
|
meta:
|
|
copy_data: false
|
|
load_checkpoint: false
|
|
model_name: vit_huge
|
|
pred_depth: 12
|
|
pred_emb_dim: 384
|
|
read_checkpoint: null
|
|
use_bfloat16: true
|
|
optimization:
|
|
ema:
|
|
- 0.996
|
|
- 1.0
|
|
epochs: 300
|
|
final_lr: 1.0e-06
|
|
final_weight_decay: 0.4
|
|
ipe_scale: 1.0
|
|
lr: 0.001
|
|
start_lr: 0.0002
|
|
warmup: 40
|
|
weight_decay: 0.04
|