moritzm00

Moritzm00's group workspace

Group: VGGFace

1-9

of 9

Tags

VGGFace

Author

moritzm00

State

Finished

Start time

May 9th, 2023 10:21:18 AM

Runtime

18m 43s

Tracked hours

18m 38s

Run path

moritzm00/UTKFace-Age-Regression/d3igtat5

Linux-5.4.0-122-generic-x86_64-with-glibc2.31

Python version

3.9.16

Git repository

git clone https://github.com/MoritzM00/AgePrediction-UTKFace.git

Git state

git checkout -b "smooth-deluge-92" 1d5918900c7188d2cd1b9c6e51aae6daa9739841

Command

/usr/local/bin/train model=vggface model.finetune_base=false train.target_size=[224,224] train.batch_size=128 model.top_layer_architecture._target_=src.top_layer_architectures.resnet_top

System Hardware

CPU count	8
Logical CPU count	8
GPU count	1
GPU type	Quadro RTX 5000

W&B CLI Version

0.15.2

Group

VGGFace

Config parameters are your model's inputs. Learn more

▶
Config parameters:{} 12 keys
- ▶
  augment:{} 2 keys
  - active:
    true
  - ▶
    factors:{} 4 keys
    - random_brightness:
      null
    - random_flip:
      "horizontal"
    - random_rotation:
      0.1
    - random_translation:
      null
- ▶
  callbacks:{} 7 keys
- ckpt_dir:
  "ckpts"
- data_dir:
  "data"
- ▶
  dataset:{} 6 keys
- log_dir:
  "logs"
- ▶
  lr_schedule:{} 2 keys
  - ▶
    stage_1:{} 4 keys
    - _target_:
      "tensorflow.keras.optimizers.schedules.ExponentialDecay"
    - decay_rate:
      0.96
    - decay_steps:
      100,000
    - initial_learning_rate:
      0.004
  - ▶
    stage_2:{} 4 keys
    - _target_:
      "tensorflow.keras.optimizers.schedules.ExponentialDecay"
    - decay_rate:
      0.99
    - decay_steps:
      100,000
    - initial_learning_rate:
      0.00005
- ▶
  model:{} 9 keys
- model_dir:
  "models"
- ▶
  optimizer:{} 2 keys
  - _partial_:
    true
  - _target_:
    "tensorflow.keras.optimizers.Adam"
- ▶
  train:{} 10 keys
- ▶
  wandb:{} 9 keys

Summary metrics are your model's outputs. Learn more

▶
Summary metrics:{} 11 keys
- ▶
  age_distribution:{} 4 keys
  - _type:
    "plotly-file"
  - path:
    "media/plotly/age_distribution_13_2e56271ef28639034057.plotly.json"
  - sha256:
    "2e56271ef28639034057d4d986c02ca677ccb372a50523680c1cd60e86427d00"
  - size:
    147,919
- ▶
  empirical_cdfs:{} 4 keys
  - _type:
    "plotly-file"
  - path:
    "media/plotly/empirical_cdfs_13_569126e99f3618125f84.plotly.json"
  - sha256:
    "569126e99f3618125f841a0bd9ab120be0fed3af1fbebaf1bd4a9776da0946a0"
  - size:
    303,448
- epoch/epoch:
  12
- epoch/learning_rate:
  0.003996838349848986
- epoch/loss:
  113.83596801757812
- epoch/mae:
  7.810024261474609
- epoch/val_loss:
  69.30164337158203
- epoch/val_mae:
  6.282585144042969
- ▶
  predictions:{} 7 keys
- ▶
  residuals:{} 4 keys
  - _type:
    "plotly-file"
  - path:
    "media/plotly/residuals_13_841eb11cc6c434038b4f.plotly.json"
  - sha256:
    "841eb11cc6c434038b4f1a3a63043257c1cc3401a273f5d0c5665a1de3774797"
  - size:
    114,081
- test_mae:
  5.9019713454963485

This run produced these artifacts as outputs. Total: 2. Learn more

model

run_d3igtat5_model:v0

wandb-history

run-d3igtat5-history:v0