From 7e5477acf5a58a9a74c73d0ee7528ef7ce1da766 Mon Sep 17 00:00:00 2001 From: Josua Rieder Date: Mon, 4 Nov 2024 12:22:06 +0100 Subject: [PATCH] Replace deprecated positional argument with --data-dir --- bulk_runner.py | 2 +- hfdocs/source/changes.mdx | 12 ++++++------ hfdocs/source/training_script.mdx | 22 +++++++++++----------- 3 files changed, 18 insertions(+), 18 deletions(-) diff --git a/bulk_runner.py b/bulk_runner.py index 286059c2..cb8bc7d1 100755 --- a/bulk_runner.py +++ b/bulk_runner.py @@ -7,7 +7,7 @@ Benchmark all 'vit*' models: python bulk_runner.py --model-list 'vit*' --results-file vit_bench.csv benchmark.py --amp -b 512 Validate all models: -python bulk_runner.py --model-list all --results-file val.csv --pretrained validate.py /imagenet/validation/ --amp -b 512 --retry +python bulk_runner.py --model-list all --results-file val.csv --pretrained validate.py --data-dir /imagenet/validation/ --amp -b 512 --retry Hacked together by Ross Wightman (https://github.com/rwightman) """ diff --git a/hfdocs/source/changes.mdx b/hfdocs/source/changes.mdx index ddcf2dc5..014fa0da 100644 --- a/hfdocs/source/changes.mdx +++ b/hfdocs/source/changes.mdx @@ -228,7 +228,7 @@ Datasets & transform refactoring * Enabling either dynamic mode will break FX tracing unless PatchEmbed module added as leaf. * Existing method of resizing position embedding by passing different `img_size` (interpolate pretrained embed weights once) on creation still works. * Existing method of changing `patch_size` (resize pretrained patch_embed weights once) on creation still works. - * Example validation cmd `python validate.py /imagenet --model vit_base_patch16_224 --amp --amp-dtype bfloat16 --img-size 255 --crop-pct 1.0 --model-kwargs dynamic_img_size=True dyamic_img_pad=True` + * Example validation cmd `python validate.py --data-dir /imagenet --model vit_base_patch16_224 --amp --amp-dtype bfloat16 --img-size 255 --crop-pct 1.0 --model-kwargs dynamic_img_size=True dyamic_img_pad=True` ### Aug 25, 2023 * Many new models since last release @@ -245,8 +245,8 @@ Datasets & transform refactoring ### Aug 11, 2023 * Swin, MaxViT, CoAtNet, and BEiT models support resizing of image/window size on creation with adaptation of pretrained weights -* Example validation cmd to test w/ non-square resize `python validate.py /imagenet --model swin_base_patch4_window7_224.ms_in22k_ft_in1k --amp --amp-dtype bfloat16 --input-size 3 256 320 --model-kwargs window_size=8,10 img_size=256,320` - +* Example validation cmd to test w/ non-square resize `python validate.py --data-dir /imagenet --model swin_base_patch4_window7_224.ms_in22k_ft_in1k --amp --amp-dtype bfloat16 --input-size 3 256 320 --model-kwargs window_size=8,10 img_size=256,320` + ### Aug 3, 2023 * Add GluonCV weights for HRNet w18_small and w18_small_v2. Converted by [SeeFun](https://github.com/seefun) * Fix `selecsls*` model naming regression @@ -385,7 +385,7 @@ Datasets & transform refactoring * Refactor LeViT models to stages, add `features_only=True` support to new `conv` variants, weight remap required. * Move ImageNet meta-data (synsets, indices) from `/results` to [`timm/data/_info`](timm/data/_info/). * Add ImageNetInfo / DatasetInfo classes to provide labelling for various ImageNet classifier layouts in `timm` - * Update `inference.py` to use, try: `python inference.py /folder/to/images --model convnext_small.in12k --label-type detail --topk 5` + * Update `inference.py` to use, try: `python inference.py --data-dir /folder/to/images --model convnext_small.in12k --label-type detail --topk 5` * Ready for 0.8.10 pypi pre-release (final testing). ### Jan 20, 2023 @@ -449,8 +449,8 @@ Datasets & transform refactoring ### Jan 6, 2023 * Finally got around to adding `--model-kwargs` and `--opt-kwargs` to scripts to pass through rare args directly to model classes from cmd line - * `train.py /imagenet --model resnet50 --amp --model-kwargs output_stride=16 act_layer=silu` - * `train.py /imagenet --model vit_base_patch16_clip_224 --img-size 240 --amp --model-kwargs img_size=240 patch_size=12` + * `train.py --data-dir /imagenet --model resnet50 --amp --model-kwargs output_stride=16 act_layer=silu` + * `train.py --data-dir /imagenet --model vit_base_patch16_clip_224 --img-size 240 --amp --model-kwargs img_size=240 patch_size=12` * Cleanup some popular models to better support arg passthrough / merge with model configs, more to go. ### Jan 5, 2023 diff --git a/hfdocs/source/training_script.mdx b/hfdocs/source/training_script.mdx index 3eb772a3..a3641033 100644 --- a/hfdocs/source/training_script.mdx +++ b/hfdocs/source/training_script.mdx @@ -12,7 +12,7 @@ The variety of training args is large and not all combinations of options (or ev To train an SE-ResNet34 on ImageNet, locally distributed, 4 GPUs, one process per GPU w/ cosine schedule, random-erasing prob of 50% and per-pixel random value: ```bash -./distributed_train.sh 4 /data/imagenet --model seresnet34 --sched cosine --epochs 150 --warmup-epochs 5 --lr 0.4 --reprob 0.5 --remode pixel --batch-size 256 --amp -j 4 +./distributed_train.sh 4 --data-dir /data/imagenet --model seresnet34 --sched cosine --epochs 150 --warmup-epochs 5 --lr 0.4 --reprob 0.5 --remode pixel --batch-size 256 --amp -j 4 ``` @@ -27,13 +27,13 @@ Validation and inference scripts are similar in usage. One outputs metrics on a To validate with the model's pretrained weights (if they exist): ```bash -python validate.py /imagenet/validation/ --model seresnext26_32x4d --pretrained +python validate.py --data-dir /imagenet/validation/ --model seresnext26_32x4d --pretrained ``` To run inference from a checkpoint: ```bash -python inference.py /imagenet/validation/ --model mobilenetv3_large_100 --checkpoint ./output/train/model_best.pth.tar +python inference.py --data-dir /imagenet/validation/ --model mobilenetv3_large_100 --checkpoint ./output/train/model_best.pth.tar ``` ## Training Examples @@ -43,7 +43,7 @@ python inference.py /imagenet/validation/ --model mobilenetv3_large_100 --checkp These params are for dual Titan RTX cards with NVIDIA Apex installed: ```bash -./distributed_train.sh 2 /imagenet/ --model efficientnet_b2 -b 128 --sched step --epochs 450 --decay-epochs 2.4 --decay-rate .97 --opt rmsproptf --opt-eps .001 -j 8 --warmup-lr 1e-6 --weight-decay 1e-5 --drop 0.3 --drop-path 0.2 --model-ema --model-ema-decay 0.9999 --aa rand-m9-mstd0.5 --remode pixel --reprob 0.2 --amp --lr .016 +./distributed_train.sh 2 --data-dir /imagenet/ --model efficientnet_b2 -b 128 --sched step --epochs 450 --decay-epochs 2.4 --decay-rate .97 --opt rmsproptf --opt-eps .001 -j 8 --warmup-lr 1e-6 --weight-decay 1e-5 --drop 0.3 --drop-path 0.2 --model-ema --model-ema-decay 0.9999 --aa rand-m9-mstd0.5 --remode pixel --reprob 0.2 --amp --lr .016 ``` ### MixNet-XL with RandAugment - 80.5 top-1, 94.9 top-5 @@ -51,7 +51,7 @@ These params are for dual Titan RTX cards with NVIDIA Apex installed: This params are for dual Titan RTX cards with NVIDIA Apex installed: ```bash -./distributed_train.sh 2 /imagenet/ --model mixnet_xl -b 128 --sched step --epochs 450 --decay-epochs 2.4 --decay-rate .969 --opt rmsproptf --opt-eps .001 -j 8 --warmup-lr 1e-6 --weight-decay 1e-5 --drop 0.3 --drop-path 0.2 --model-ema --model-ema-decay 0.9999 --aa rand-m9-mstd0.5 --remode pixel --reprob 0.3 --amp --lr .016 --dist-bn reduce +./distributed_train.sh 2 --data-dir /imagenet/ --model mixnet_xl -b 128 --sched step --epochs 450 --decay-epochs 2.4 --decay-rate .969 --opt rmsproptf --opt-eps .001 -j 8 --warmup-lr 1e-6 --weight-decay 1e-5 --drop 0.3 --drop-path 0.2 --model-ema --model-ema-decay 0.9999 --aa rand-m9-mstd0.5 --remode pixel --reprob 0.3 --amp --lr .016 --dist-bn reduce ``` ### SE-ResNeXt-26-D and SE-ResNeXt-26-T @@ -59,7 +59,7 @@ This params are for dual Titan RTX cards with NVIDIA Apex installed: These hparams (or similar) work well for a wide range of ResNet architecture, generally a good idea to increase the epoch # as the model size increases... ie approx 180-200 for ResNe(X)t50, and 220+ for larger. Increase batch size and LR proportionally for better GPUs or with AMP enabled. These params were for 2 1080Ti cards: ```bash -./distributed_train.sh 2 /imagenet/ --model seresnext26t_32x4d --lr 0.1 --warmup-epochs 5 --epochs 160 --weight-decay 1e-4 --sched cosine --reprob 0.4 --remode pixel -b 112 +./distributed_train.sh 2 --data-dir /imagenet/ --model seresnext26t_32x4d --lr 0.1 --warmup-epochs 5 --epochs 160 --weight-decay 1e-4 --sched cosine --reprob 0.4 --remode pixel -b 112 ``` ### EfficientNet-B3 with RandAugment - 81.5 top-1, 95.7 top-5 @@ -70,26 +70,26 @@ The training of this model started with the same command line as EfficientNet-B2 [Michael Klachko](https://github.com/michaelklachko) achieved these results with the command line for B2 adapted for larger batch size, with the recommended B0 dropout rate of 0.2. ```bash -./distributed_train.sh 2 /imagenet/ --model efficientnet_b0 -b 384 --sched step --epochs 450 --decay-epochs 2.4 --decay-rate .97 --opt rmsproptf --opt-eps .001 -j 8 --warmup-lr 1e-6 --weight-decay 1e-5 --drop 0.2 --drop-path 0.2 --model-ema --model-ema-decay 0.9999 --aa rand-m9-mstd0.5 --remode pixel --reprob 0.2 --amp --lr .048 +./distributed_train.sh 2 --data-dir /imagenet/ --model efficientnet_b0 -b 384 --sched step --epochs 450 --decay-epochs 2.4 --decay-rate .97 --opt rmsproptf --opt-eps .001 -j 8 --warmup-lr 1e-6 --weight-decay 1e-5 --drop 0.2 --drop-path 0.2 --model-ema --model-ema-decay 0.9999 --aa rand-m9-mstd0.5 --remode pixel --reprob 0.2 --amp --lr .048 ``` ### ResNet50 with JSD loss and RandAugment (clean + 2x RA augs) - 79.04 top-1, 94.39 top-5 Trained on two older 1080Ti cards, this took a while. Only slightly, non statistically better ImageNet validation result than my first good AugMix training of 78.99. However, these weights are more robust on tests with ImageNetV2, ImageNet-Sketch, etc. Unlike my first AugMix runs, I've enabled SplitBatchNorm, disabled random erasing on the clean split, and cranked up random erasing prob on the 2 augmented paths. ```bash -./distributed_train.sh 2 /imagenet -b 64 --model resnet50 --sched cosine --epochs 200 --lr 0.05 --amp --remode pixel --reprob 0.6 --aug-splits 3 --aa rand-m9-mstd0.5-inc1 --resplit --split-bn --jsd --dist-bn reduce +./distributed_train.sh 2 --data-dir /imagenet -b 64 --model resnet50 --sched cosine --epochs 200 --lr 0.05 --amp --remode pixel --reprob 0.6 --aug-splits 3 --aa rand-m9-mstd0.5-inc1 --resplit --split-bn --jsd --dist-bn reduce ``` ### EfficientNet-ES (EdgeTPU-Small) with RandAugment - 78.066 top-1, 93.926 top-5 Trained by [Andrew Lavin](https://github.com/andravin) with 8 V100 cards. Model EMA was not used, final checkpoint is the average of 8 best checkpoints during training. ```bash -./distributed_train.sh 8 /imagenet --model efficientnet_es -b 128 --sched step --epochs 450 --decay-epochs 2.4 --decay-rate .97 --opt rmsproptf --opt-eps .001 -j 8 --warmup-lr 1e-6 --weight-decay 1e-5 --drop 0.2 --drop-path 0.2 --aa rand-m9-mstd0.5 --remode pixel --reprob 0.2 --amp --lr .064 +./distributed_train.sh 8 --data-dir /imagenet --model efficientnet_es -b 128 --sched step --epochs 450 --decay-epochs 2.4 --decay-rate .97 --opt rmsproptf --opt-eps .001 -j 8 --warmup-lr 1e-6 --weight-decay 1e-5 --drop 0.2 --drop-path 0.2 --aa rand-m9-mstd0.5 --remode pixel --reprob 0.2 --amp --lr .064 ``` ### MobileNetV3-Large-100 - 75.766 top-1, 92,542 top-5 ```bash -./distributed_train.sh 2 /imagenet/ --model mobilenetv3_large_100 -b 512 --sched step --epochs 600 --decay-epochs 2.4 --decay-rate .973 --opt rmsproptf --opt-eps .001 -j 7 --warmup-lr 1e-6 --weight-decay 1e-5 --drop 0.2 --drop-path 0.2 --model-ema --model-ema-decay 0.9999 --aa rand-m9-mstd0.5 --remode pixel --reprob 0.2 --amp --lr .064 --lr-noise 0.42 0.9 +./distributed_train.sh 2 /--data-dir imagenet/ --model mobilenetv3_large_100 -b 512 --sched step --epochs 600 --decay-epochs 2.4 --decay-rate .973 --opt rmsproptf --opt-eps .001 -j 7 --warmup-lr 1e-6 --weight-decay 1e-5 --drop 0.2 --drop-path 0.2 --model-ema --model-ema-decay 0.9999 --aa rand-m9-mstd0.5 --remode pixel --reprob 0.2 --amp --lr .064 --lr-noise 0.42 0.9 ``` ### ResNeXt-50 32x4d w/ RandAugment - 79.762 top-1, 94.60 top-5 @@ -97,5 +97,5 @@ These params will also work well for SE-ResNeXt-50 and SK-ResNeXt-50 and likely ```bash -./distributed_train.sh 8 /imagenet --model resnext50_32x4d --lr 0.6 --warmup-epochs 5 --epochs 240 --weight-decay 1e-4 --sched cosine --reprob 0.4 --recount 3 --remode pixel --aa rand-m7-mstd0.5-inc1 -b 192 -j 6 --amp --dist-bn reduce +./distributed_train.sh 8 --data-dir /imagenet --model resnext50_32x4d --lr 0.6 --warmup-epochs 5 --epochs 240 --weight-decay 1e-4 --sched cosine --reprob 0.4 --recount 3 --remode pixel --aa rand-m7-mstd0.5-inc1 -b 192 -j 6 --amp --dist-bn reduce ```