Use MNIST160 (#10069)

New 160-image MNIST subset composed of first 8 examples of each class. Suitable for fast CI.

Signed-off-by: Glenn Jocher <glenn.jocher@ultralytics.com>

Signed-off-by: Glenn Jocher <glenn.jocher@ultralytics.com>
This commit is contained in:
Glenn Jocher 2022-11-07 23:07:10 +01:00 committed by GitHub
parent 58b3d07854
commit e00d02d78b
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23

View File

@ -155,11 +155,11 @@ jobs:
run: |
m=${{ matrix.model }}-cls.pt # official weights
b=runs/train-cls/exp/weights/best.pt # best.pt checkpoint
python classify/train.py --imgsz 32 --model $m --data mnist2560 --epochs 1 # train
python classify/val.py --imgsz 32 --weights $b --data ../datasets/mnist2560 # val
python classify/predict.py --imgsz 32 --weights $b --source ../datasets/mnist2560/test/7/60.png # predict
python classify/train.py --imgsz 32 --model $m --data mnist160 --epochs 1 # train
python classify/val.py --imgsz 32 --weights $b --data ../datasets/mnist160 # val
python classify/predict.py --imgsz 32 --weights $b --source ../datasets/mnist160/test/7/60.png # predict
python classify/predict.py --imgsz 32 --weights $m --source data/images/bus.jpg # predict
python export.py --weights $b --img 64 --imgsz 224 --include torchscript # export
python export.py --weights $b --img 64 --include torchscript # export
python - <<EOF
import torch
for path in '$m', '$b':