experiment test_different_tl_models | brookeryan Workspace – Weights & Biases

Skip to main content

Brookeryan's group workspace

Group: experiment test_different_tl_models

1-6

of 6

Tags

Notes

Author

State

Crashed

Start time

June 14th, 2021 5:32:30 AM

Runtime

43m 44s

Tracked hours

-

Run path

brookeryan/Visual_Acuity/3kquaiaf

OS

Linux-3.10.0-1160.24.1.el7.x86_64-x86_64-with-glibc2.31

Python version

3.9.4

Command

/home/brooker/VisualAcuity/src/main.py test_different_tl_models

System Hardware

CPU count	128
GPU count	4
GPU type	NVIDIA GeForce RTX 3090

W&B CLI Version

0.10.31

Group

experiment test_different_tl_models

Config parameters are your model's inputs. Learn more

▶
Config parameters:{} 13 keys
- activation:
  "softmax"
- batch_size:
  32
- channels:
  3
- epochs:
  50
- height:
  400
- loss:
  "sparse_categorical_crossentropy"
- metrics:
  "accuracy"
- num_optotypes:
  59
- optimizer:
  "adam"
- project:
  "Visual_Acuity"
- validation_split:
  0.2
- weights:
  "imagenet"
- width:
  400

Summary metrics are your model's outputs. Learn more

▶
Summary metrics:{} 9 keys
- global_step:
  11,253
- train/epoch_accuracy:
  0.90988427400589
- train/epoch_loss:
  0.24866187572479248
- train/global_step:
  31
- validation/epoch_accuracy:
  0.9228508472442628
- validation/epoch_loss:
  0.23643171787261963
- validation/evaluation_accuracy_vs_iterations:
  0.9228508472442628
- validation/evaluation_loss_vs_iterations:
  0.23643171787261963
- validation/global_step:
  32

This run produced these artifacts as outputs. Total: 1. Learn more

run-3kquaiaf-history:v0

Loading...