diff --git a/.circleci/config.yml b/.circleci/config.yml index 4759b3fc6f..00583749bb 100644 --- a/.circleci/config.yml +++ b/.circleci/config.yml @@ -468,11 +468,11 @@ jobs: python3.8 -m pip install pytorch-quantization==2.1.2 --extra-index-url https://pypi.ngc.nvidia.com python3.8 tests/verify_min_samples_ddp.py - python3.8 -m super_gradients.train_from_recipe --config-name=coco2017_pose_dekr_w32_no_dc experiment_name=shortened_coco2017_pose_dekr_w32_ap_test batch_size=4 val_batch_size=8 epochs=1 training_hyperparams.lr_warmup_steps=0 training_hyperparams.average_best_models=False training_hyperparams.max_train_batches=1000 training_hyperparams.max_valid_batches=100 multi_gpu=DDP num_gpus=4 - python3.8 -m super_gradients.train_from_recipe --config-name=cifar10_resnet experiment_name=shortened_cifar10_resnet_accuracy_test epochs=100 training_hyperparams.average_best_models=False multi_gpu=DDP num_gpus=4 + python3.8 src/super_gradients/train_from_recipe.py --config-name=coco2017_pose_dekr_w32_no_dc experiment_name=shortened_coco2017_pose_dekr_w32_ap_test batch_size=4 val_batch_size=8 epochs=1 training_hyperparams.lr_warmup_steps=0 training_hyperparams.average_best_models=False training_hyperparams.max_train_batches=1000 training_hyperparams.max_valid_batches=100 multi_gpu=DDP num_gpus=4 + python3.8 src/super_gradients/train_from_recipe.py --config-name=cifar10_resnet experiment_name=shortened_cifar10_resnet_accuracy_test epochs=100 training_hyperparams.average_best_models=False multi_gpu=DDP num_gpus=4 python3.8 src/super_gradients/examples/convert_recipe_example/convert_recipe_example.py --config-name=cifar10_conversion_params experiment_name=shortened_cifar10_resnet_accuracy_test - python3.8 -m super_gradients.train_from_recipe --config-name=coco2017_yolox experiment_name=shortened_coco2017_yolox_n_map_test architecture=yolox_n training_hyperparams.loss=yolox_fast_loss epochs=10 training_hyperparams.average_best_models=False multi_gpu=DDP num_gpus=4 - python3.8 -m super_gradients.train_from_recipe --config-name=cityscapes_regseg48 experiment_name=shortened_cityscapes_regseg48_iou_test epochs=10 training_hyperparams.average_best_models=False multi_gpu=DDP num_gpus=4 + python3.8 src/super_gradients/train_from_recipe.py --config-name=coco2017_yolox experiment_name=shortened_coco2017_yolox_n_map_test architecture=yolox_n training_hyperparams.loss=yolox_fast_loss epochs=10 training_hyperparams.average_best_models=False multi_gpu=DDP num_gpus=4 + python3.8 src/super_gradients/train_from_recipe.py --config-name=cityscapes_regseg48 experiment_name=shortened_cityscapes_regseg48_iou_test epochs=10 training_hyperparams.average_best_models=False multi_gpu=DDP num_gpus=4 coverage run --source=super_gradients -m unittest tests/deci_core_recipe_test_suite_runner.py - run: @@ -511,12 +511,12 @@ jobs: python3.8 -m pip install -r requirements.txt python3.8 -m pip install . python3.8 -m pip install torch torchvision torchaudio - python3.8 src/super_gradients/examples/train_from_recipe_example/train_from_recipe.py --config-name=imagenet_regnetY architecture=regnetY600 batch_size=8 val_batch_size=16 epochs=1 training_hyperparams.average_best_models=False training_hyperparams.max_train_batches=100 training_hyperparams.max_valid_batches=100 multi_gpu=DDP num_gpus=4 dataset_params.train_dataset_params.root=/data/Imagenet/train dataset_params.val_dataset_params.root=/data/Imagenet/val - python3.8 src/super_gradients/examples/train_from_recipe_example/train_from_recipe.py --config-name=imagenet_regnetY architecture=regnetY800 batch_size=8 val_batch_size=16 epochs=1 training_hyperparams.average_best_models=False training_hyperparams.max_train_batches=100 training_hyperparams.max_valid_batches=100 multi_gpu=DDP num_gpus=4 dataset_params.train_dataset_params.root=/data/Imagenet/train dataset_params.val_dataset_params.root=/data/Imagenet/val - python3.8 src/super_gradients/examples/train_from_recipe_example/train_from_recipe.py --config-name=imagenet_repvgg batch_size=8 val_batch_size=16 epochs=1 training_hyperparams.average_best_models=False training_hyperparams.max_train_batches=100 training_hyperparams.max_valid_batches=100 multi_gpu=DDP num_gpus=4 dataset_params.train_dataset_params.root=/data/Imagenet/train dataset_params.val_dataset_params.root=/data/Imagenet/val - python3.8 src/super_gradients/examples/train_from_recipe_example/train_from_recipe.py --config-name=imagenet_resnet50 batch_size=8 val_batch_size=16 epochs=1 training_hyperparams.average_best_models=False training_hyperparams.max_train_batches=100 training_hyperparams.max_valid_batches=100 multi_gpu=DDP num_gpus=4 dataset_params.train_dataset_params.root=/data/Imagenet/train dataset_params.val_dataset_params.root=/data/Imagenet/val - python3.8 src/super_gradients/examples/train_from_recipe_example/train_from_recipe.py --config-name=imagenet_vit_base batch_size=8 val_batch_size=16 epochs=1 training_hyperparams.average_best_models=False training_hyperparams.max_train_batches=100 training_hyperparams.max_valid_batches=100 multi_gpu=DDP num_gpus=4 dataset_params.train_dataset_params.root=/data/Imagenet/train dataset_params.val_dataset_params.root=/data/Imagenet/val - python3.8 src/super_gradients/examples/train_from_kd_recipe_example/train_from_kd_recipe.py --config-name=imagenet_resnet50_kd batch_size=8 val_batch_size=8 epochs=1 training_hyperparams.average_best_models=False training_hyperparams.max_train_batches=100 training_hyperparams.max_valid_batches=100 multi_gpu=DDP num_gpus=4 dataset_params.train_dataset_params.root=/data/Imagenet/train dataset_params.val_dataset_params.root=/data/Imagenet/val + python3.8 src/super_gradients/train_from_recipe.py --config-name=imagenet_regnetY architecture=regnetY600 batch_size=8 val_batch_size=16 epochs=1 training_hyperparams.average_best_models=False training_hyperparams.max_train_batches=100 training_hyperparams.max_valid_batches=100 multi_gpu=DDP num_gpus=4 dataset_params.train_dataset_params.root=/data/Imagenet/train dataset_params.val_dataset_params.root=/data/Imagenet/val + python3.8 src/super_gradients/train_from_recipe.py --config-name=imagenet_regnetY architecture=regnetY800 batch_size=8 val_batch_size=16 epochs=1 training_hyperparams.average_best_models=False training_hyperparams.max_train_batches=100 training_hyperparams.max_valid_batches=100 multi_gpu=DDP num_gpus=4 dataset_params.train_dataset_params.root=/data/Imagenet/train dataset_params.val_dataset_params.root=/data/Imagenet/val + python3.8 src/super_gradients/train_from_recipe.py --config-name=imagenet_repvgg batch_size=8 val_batch_size=16 epochs=1 training_hyperparams.average_best_models=False training_hyperparams.max_train_batches=100 training_hyperparams.max_valid_batches=100 multi_gpu=DDP num_gpus=4 dataset_params.train_dataset_params.root=/data/Imagenet/train dataset_params.val_dataset_params.root=/data/Imagenet/val + python3.8 src/super_gradients/train_from_recipe.py --config-name=imagenet_resnet50 batch_size=8 val_batch_size=16 epochs=1 training_hyperparams.average_best_models=False training_hyperparams.max_train_batches=100 training_hyperparams.max_valid_batches=100 multi_gpu=DDP num_gpus=4 dataset_params.train_dataset_params.root=/data/Imagenet/train dataset_params.val_dataset_params.root=/data/Imagenet/val + python3.8 src/super_gradients/train_from_recipe.py --config-name=imagenet_vit_base batch_size=8 val_batch_size=16 epochs=1 training_hyperparams.average_best_models=False training_hyperparams.max_train_batches=100 training_hyperparams.max_valid_batches=100 multi_gpu=DDP num_gpus=4 dataset_params.train_dataset_params.root=/data/Imagenet/train dataset_params.val_dataset_params.root=/data/Imagenet/val + python3.8 src/super_gradients/train_from_kd_recipe.py --config-name=imagenet_resnet50_kd batch_size=8 val_batch_size=8 epochs=1 training_hyperparams.average_best_models=False training_hyperparams.max_train_batches=100 training_hyperparams.max_valid_batches=100 multi_gpu=DDP num_gpus=4 dataset_params.train_dataset_params.root=/data/Imagenet/train dataset_params.val_dataset_params.root=/data/Imagenet/val - run: name: Remove new environment when failed @@ -554,12 +554,12 @@ jobs: python3.8 -m pip install -r requirements.txt python3.8 -m pip install . python3.8 -m pip install torch torchvision torchaudio - python3.8 src/super_gradients/examples/train_from_recipe_example/train_from_recipe.py --config-name=imagenet_efficientnet batch_size=8 val_batch_size=16 epochs=1 training_hyperparams.average_best_models=False training_hyperparams.max_train_batches=100 training_hyperparams.max_valid_batches=100 multi_gpu=DDP num_gpus=4 dataset_params.train_dataset_params.root=/data/Imagenet/train dataset_params.val_dataset_params.root=/data/Imagenet/val - python3.8 src/super_gradients/examples/train_from_recipe_example/train_from_recipe.py --config-name=imagenet_mobilenetv2 batch_size=8 val_batch_size=16 epochs=1 training_hyperparams.average_best_models=False training_hyperparams.max_train_batches=100 training_hyperparams.max_valid_batches=100 multi_gpu=DDP num_gpus=4 dataset_params.train_dataset_params.root=/data/Imagenet/train dataset_params.val_dataset_params.root=/data/Imagenet/val - python3.8 src/super_gradients/examples/train_from_recipe_example/train_from_recipe.py --config-name=imagenet_mobilenetv3_large batch_size=8 val_batch_size=16 epochs=1 training_hyperparams.average_best_models=False training_hyperparams.max_train_batches=100 training_hyperparams.max_valid_batches=100 multi_gpu=DDP num_gpus=4 dataset_params.train_dataset_params.root=/data/Imagenet/train dataset_params.val_dataset_params.root=/data/Imagenet/val - python3.8 src/super_gradients/examples/train_from_recipe_example/train_from_recipe.py --config-name=imagenet_mobilenetv3_small batch_size=8 val_batch_size=16 epochs=1 training_hyperparams.average_best_models=False training_hyperparams.max_train_batches=100 training_hyperparams.max_valid_batches=100 multi_gpu=DDP num_gpus=4 dataset_params.train_dataset_params.root=/data/Imagenet/train dataset_params.val_dataset_params.root=/data/Imagenet/val - python3.8 src/super_gradients/examples/train_from_recipe_example/train_from_recipe.py --config-name=imagenet_regnetY architecture=regnetY200 batch_size=8 val_batch_size=16 epochs=1 training_hyperparams.average_best_models=False training_hyperparams.max_train_batches=100 training_hyperparams.max_valid_batches=100 multi_gpu=DDP num_gpus=4 dataset_params.train_dataset_params.root=/data/Imagenet/train dataset_params.val_dataset_params.root=/data/Imagenet/val - python3.8 src/super_gradients/examples/train_from_recipe_example/train_from_recipe.py --config-name=imagenet_regnetY architecture=regnetY400 batch_size=8 val_batch_size=16 epochs=1 training_hyperparams.average_best_models=False training_hyperparams.max_train_batches=100 training_hyperparams.max_valid_batches=100 multi_gpu=DDP num_gpus=4 dataset_params.train_dataset_params.root=/data/Imagenet/train dataset_params.val_dataset_params.root=/data/Imagenet/val + python3.8 src/super_gradients/train_from_recipe.py --config-name=imagenet_efficientnet batch_size=8 val_batch_size=16 epochs=1 training_hyperparams.average_best_models=False training_hyperparams.max_train_batches=100 training_hyperparams.max_valid_batches=100 multi_gpu=DDP num_gpus=4 dataset_params.train_dataset_params.root=/data/Imagenet/train dataset_params.val_dataset_params.root=/data/Imagenet/val + python3.8 src/super_gradients/train_from_recipe.py --config-name=imagenet_mobilenetv2 batch_size=8 val_batch_size=16 epochs=1 training_hyperparams.average_best_models=False training_hyperparams.max_train_batches=100 training_hyperparams.max_valid_batches=100 multi_gpu=DDP num_gpus=4 dataset_params.train_dataset_params.root=/data/Imagenet/train dataset_params.val_dataset_params.root=/data/Imagenet/val + python3.8 src/super_gradients/train_from_recipe.py --config-name=imagenet_mobilenetv3_large batch_size=8 val_batch_size=16 epochs=1 training_hyperparams.average_best_models=False training_hyperparams.max_train_batches=100 training_hyperparams.max_valid_batches=100 multi_gpu=DDP num_gpus=4 dataset_params.train_dataset_params.root=/data/Imagenet/train dataset_params.val_dataset_params.root=/data/Imagenet/val + python3.8 src/super_gradients/train_from_recipe.py --config-name=imagenet_mobilenetv3_small batch_size=8 val_batch_size=16 epochs=1 training_hyperparams.average_best_models=False training_hyperparams.max_train_batches=100 training_hyperparams.max_valid_batches=100 multi_gpu=DDP num_gpus=4 dataset_params.train_dataset_params.root=/data/Imagenet/train dataset_params.val_dataset_params.root=/data/Imagenet/val + python3.8 src/super_gradients/train_from_recipe.py --config-name=imagenet_regnetY architecture=regnetY200 batch_size=8 val_batch_size=16 epochs=1 training_hyperparams.average_best_models=False training_hyperparams.max_train_batches=100 training_hyperparams.max_valid_batches=100 multi_gpu=DDP num_gpus=4 dataset_params.train_dataset_params.root=/data/Imagenet/train dataset_params.val_dataset_params.root=/data/Imagenet/val + python3.8 src/super_gradients/train_from_recipe.py --config-name=imagenet_regnetY architecture=regnetY400 batch_size=8 val_batch_size=16 epochs=1 training_hyperparams.average_best_models=False training_hyperparams.max_train_batches=100 training_hyperparams.max_valid_batches=100 multi_gpu=DDP num_gpus=4 dataset_params.train_dataset_params.root=/data/Imagenet/train dataset_params.val_dataset_params.root=/data/Imagenet/val - run: name: Remove new environment when failed command: "rm -r << parameters.sg_new_env_name >>" @@ -597,19 +597,19 @@ jobs: wget -O $(pwd)/checkpoints/ddrnet23_slim_bb_imagenet.pth https://deci-pretrained-models.s3.amazonaws.com/ddrnet/imagenet_pt_backbones/ddrnet23_slim_bb_imagenet.pth wget -O $(pwd)/checkpoints/ddrnet23_bb_imagenet.pth https://deci-pretrained-models.s3.amazonaws.com/ddrnet/imagenet_pt_backbones/ddrnet23_bb_imagenet.pth wget -O $(pwd)/checkpoints/ddrnet39_imagenet_pretrained.pth https://deci-pretrained-models.s3.amazonaws.com/ddrnet/imagenet_pt_backbones/ddrnet39_bb_imagenet.pth - python3.8 src/super_gradients/examples/train_from_recipe_example/train_from_recipe.py --config-name=cityscapes_ddrnet checkpoint_params.checkpoint_path=$(pwd)/checkpoints/ddrnet23_bb_imagenet.pth batch_size=3 val_batch_size=3 epochs=1 training_hyperparams.average_best_models=False training_hyperparams.max_train_batches=100 training_hyperparams.max_valid_batches=100 multi_gpu=DDP num_gpus=4 - python3.8 src/super_gradients/examples/train_from_recipe_example/train_from_recipe.py --config-name=cityscapes_ddrnet architecture=ddrnet_23_slim checkpoint_params.checkpoint_path=$(pwd)/checkpoints/ddrnet23_slim_bb_imagenet.pth batch_size=3 val_batch_size=3 epochs=1 training_hyperparams.average_best_models=False training_hyperparams.max_train_batches=100 training_hyperparams.max_valid_batches=100 multi_gpu=DDP num_gpus=4 - python3.8 src/super_gradients/examples/train_from_recipe_example/train_from_recipe.py --config-name=cityscapes_ddrnet checkpoint_params.checkpoint_path=$(pwd)/checkpoints/ddrnet39_imagenet_pretrained.pth architecture=ddrnet_39 batch_size=3 val_batch_size=3 epochs=1 training_hyperparams.average_best_models=False training_hyperparams.max_train_batches=100 training_hyperparams.max_valid_batches=100 multi_gpu=DDP num_gpus=4 + python3.8 src/super_gradients/train_from_recipe.py --config-name=cityscapes_ddrnet checkpoint_params.checkpoint_path=$(pwd)/checkpoints/ddrnet23_bb_imagenet.pth batch_size=3 val_batch_size=3 epochs=1 training_hyperparams.average_best_models=False training_hyperparams.max_train_batches=100 training_hyperparams.max_valid_batches=100 multi_gpu=DDP num_gpus=4 + python3.8 src/super_gradients/train_from_recipe.py --config-name=cityscapes_ddrnet architecture=ddrnet_23_slim checkpoint_params.checkpoint_path=$(pwd)/checkpoints/ddrnet23_slim_bb_imagenet.pth batch_size=3 val_batch_size=3 epochs=1 training_hyperparams.average_best_models=False training_hyperparams.max_train_batches=100 training_hyperparams.max_valid_batches=100 multi_gpu=DDP num_gpus=4 + python3.8 src/super_gradients/train_from_recipe.py --config-name=cityscapes_ddrnet checkpoint_params.checkpoint_path=$(pwd)/checkpoints/ddrnet39_imagenet_pretrained.pth architecture=ddrnet_39 batch_size=3 val_batch_size=3 epochs=1 training_hyperparams.average_best_models=False training_hyperparams.max_train_batches=100 training_hyperparams.max_valid_batches=100 multi_gpu=DDP num_gpus=4 wget -O $(pwd)/checkpoints/stdc1_imagenet_pretrained.pth https://deci-pretrained-models.s3.amazonaws.com/stdc_backbones/stdc1_imagenet_pretrained.pth wget -O $(pwd)/checkpoints/stdc2_imagenet_pretrained.pth https://deci-pretrained-models.s3.amazonaws.com/stdc_backbones/stdc2_imagenet_pretrained.pth - python3.8 src/super_gradients/examples/train_from_recipe_example/train_from_recipe.py --config-name=cityscapes_pplite_seg50 checkpoint_params.checkpoint_path=$(pwd)/checkpoints/stdc1_imagenet_pretrained.pth architecture=pp_lite_t_seg batch_size=3 val_batch_size=3 epochs=1 training_hyperparams.average_best_models=False training_hyperparams.max_train_batches=100 training_hyperparams.max_valid_batches=100 multi_gpu=DDP num_gpus=4 - python3.8 src/super_gradients/examples/train_from_recipe_example/train_from_recipe.py --config-name=cityscapes_pplite_seg50 checkpoint_params.checkpoint_path=$(pwd)/checkpoints/stdc2_imagenet_pretrained.pth architecture=pp_lite_b_seg batch_size=3 val_batch_size=3 epochs=1 training_hyperparams.average_best_models=False training_hyperparams.max_train_batches=100 training_hyperparams.max_valid_batches=100 multi_gpu=DDP num_gpus=4 - python3.8 src/super_gradients/examples/train_from_recipe_example/train_from_recipe.py --config-name=cityscapes_pplite_seg75 checkpoint_params.checkpoint_path=$(pwd)/checkpoints/stdc1_imagenet_pretrained.pth architecture=pp_lite_t_seg batch_size=3 val_batch_size=3 epochs=1 training_hyperparams.average_best_models=False training_hyperparams.max_train_batches=100 training_hyperparams.max_valid_batches=100 multi_gpu=DDP num_gpus=4 - python3.8 src/super_gradients/examples/train_from_recipe_example/train_from_recipe.py --config-name=cityscapes_pplite_seg75 checkpoint_params.checkpoint_path=$(pwd)/checkpoints/stdc2_imagenet_pretrained.pth architecture=pp_lite_b_seg batch_size=3 val_batch_size=3 epochs=1 training_hyperparams.average_best_models=False training_hyperparams.max_train_batches=100 training_hyperparams.max_valid_batches=100 multi_gpu=DDP num_gpus=4 - python3.8 src/super_gradients/examples/train_from_recipe_example/train_from_recipe.py --config-name=cityscapes_stdc_seg50 checkpoint_params.checkpoint_path=$(pwd)/checkpoints/stdc1_imagenet_pretrained.pth batch_size=3 val_batch_size=3 epochs=1 training_hyperparams.average_best_models=False training_hyperparams.max_train_batches=100 training_hyperparams.max_valid_batches=100 multi_gpu=DDP num_gpus=4 - python3.8 src/super_gradients/examples/train_from_recipe_example/train_from_recipe.py --config-name=cityscapes_stdc_seg50 checkpoint_params.checkpoint_path=$(pwd)/checkpoints/stdc2_imagenet_pretrained.pth architecture=stdc2_seg batch_size=3 val_batch_size=3 epochs=1 training_hyperparams.average_best_models=False training_hyperparams.max_train_batches=100 training_hyperparams.max_valid_batches=100 multi_gpu=DDP num_gpus=4 - python3.8 src/super_gradients/examples/train_from_recipe_example/train_from_recipe.py --config-name=cityscapes_stdc_seg75 checkpoint_params.checkpoint_path=$(pwd)/checkpoints/stdc1_imagenet_pretrained.pth batch_size=3 val_batch_size=3 epochs=1 training_hyperparams.average_best_models=False training_hyperparams.max_train_batches=100 training_hyperparams.max_valid_batches=100 multi_gpu=DDP num_gpus=4 - python3.8 src/super_gradients/examples/train_from_recipe_example/train_from_recipe.py --config-name=cityscapes_stdc_seg75 checkpoint_params.checkpoint_path=$(pwd)/checkpoints/stdc2_imagenet_pretrained.pth architecture=stdc2_seg batch_size=3 val_batch_size=3 epochs=1 training_hyperparams.average_best_models=False training_hyperparams.max_train_batches=100 training_hyperparams.max_valid_batches=100 multi_gpu=DDP num_gpus=4 + python3.8 src/super_gradients/train_from_recipe.py --config-name=cityscapes_pplite_seg50 checkpoint_params.checkpoint_path=$(pwd)/checkpoints/stdc1_imagenet_pretrained.pth architecture=pp_lite_t_seg batch_size=3 val_batch_size=3 epochs=1 training_hyperparams.average_best_models=False training_hyperparams.max_train_batches=100 training_hyperparams.max_valid_batches=100 multi_gpu=DDP num_gpus=4 + python3.8 src/super_gradients/train_from_recipe.py --config-name=cityscapes_pplite_seg50 checkpoint_params.checkpoint_path=$(pwd)/checkpoints/stdc2_imagenet_pretrained.pth architecture=pp_lite_b_seg batch_size=3 val_batch_size=3 epochs=1 training_hyperparams.average_best_models=False training_hyperparams.max_train_batches=100 training_hyperparams.max_valid_batches=100 multi_gpu=DDP num_gpus=4 + python3.8 src/super_gradients/train_from_recipe.py --config-name=cityscapes_pplite_seg75 checkpoint_params.checkpoint_path=$(pwd)/checkpoints/stdc1_imagenet_pretrained.pth architecture=pp_lite_t_seg batch_size=3 val_batch_size=3 epochs=1 training_hyperparams.average_best_models=False training_hyperparams.max_train_batches=100 training_hyperparams.max_valid_batches=100 multi_gpu=DDP num_gpus=4 + python3.8 src/super_gradients/train_from_recipe.py --config-name=cityscapes_pplite_seg75 checkpoint_params.checkpoint_path=$(pwd)/checkpoints/stdc2_imagenet_pretrained.pth architecture=pp_lite_b_seg batch_size=3 val_batch_size=3 epochs=1 training_hyperparams.average_best_models=False training_hyperparams.max_train_batches=100 training_hyperparams.max_valid_batches=100 multi_gpu=DDP num_gpus=4 + python3.8 src/super_gradients/train_from_recipe.py --config-name=cityscapes_stdc_seg50 checkpoint_params.checkpoint_path=$(pwd)/checkpoints/stdc1_imagenet_pretrained.pth batch_size=3 val_batch_size=3 epochs=1 training_hyperparams.average_best_models=False training_hyperparams.max_train_batches=100 training_hyperparams.max_valid_batches=100 multi_gpu=DDP num_gpus=4 + python3.8 src/super_gradients/train_from_recipe.py --config-name=cityscapes_stdc_seg50 checkpoint_params.checkpoint_path=$(pwd)/checkpoints/stdc2_imagenet_pretrained.pth architecture=stdc2_seg batch_size=3 val_batch_size=3 epochs=1 training_hyperparams.average_best_models=False training_hyperparams.max_train_batches=100 training_hyperparams.max_valid_batches=100 multi_gpu=DDP num_gpus=4 + python3.8 src/super_gradients/train_from_recipe.py --config-name=cityscapes_stdc_seg75 checkpoint_params.checkpoint_path=$(pwd)/checkpoints/stdc1_imagenet_pretrained.pth batch_size=3 val_batch_size=3 epochs=1 training_hyperparams.average_best_models=False training_hyperparams.max_train_batches=100 training_hyperparams.max_valid_batches=100 multi_gpu=DDP num_gpus=4 + python3.8 src/super_gradients/train_from_recipe.py --config-name=cityscapes_stdc_seg75 checkpoint_params.checkpoint_path=$(pwd)/checkpoints/stdc2_imagenet_pretrained.pth architecture=stdc2_seg batch_size=3 val_batch_size=3 epochs=1 training_hyperparams.average_best_models=False training_hyperparams.max_train_batches=100 training_hyperparams.max_valid_batches=100 multi_gpu=DDP num_gpus=4 - run: name: Remove new environment when failed command: "rm -r << parameters.sg_new_env_name >>" @@ -645,12 +645,12 @@ jobs: python3.8 -m pip install -r requirements.txt python3.8 -m pip install . python3.8 -m pip install torch torchvision torchaudio - python3.8 src/super_gradients/examples/train_from_recipe_example/train_from_recipe.py --config-name=coco2017_ssd_lite_mobilenet_v2 batch_size=8 val_batch_size=16 epochs=1 training_hyperparams.average_best_models=False training_hyperparams.max_train_batches=100 training_hyperparams.max_valid_batches=100 multi_gpu=DDP num_gpus=4 - python3.8 src/super_gradients/examples/train_from_recipe_example/train_from_recipe.py --config-name=coco2017_yolox architecture=yolox_n batch_size=8 val_batch_size=16 epochs=1 training_hyperparams.average_best_models=False training_hyperparams.max_train_batches=100 training_hyperparams.max_valid_batches=100 multi_gpu=DDP num_gpus=4 - python3.8 src/super_gradients/examples/train_from_recipe_example/train_from_recipe.py --config-name=coco2017_yolox architecture=yolox_t batch_size=8 val_batch_size=16 epochs=1 training_hyperparams.average_best_models=False training_hyperparams.max_train_batches=100 training_hyperparams.max_valid_batches=100 multi_gpu=DDP num_gpus=4 - python3.8 src/super_gradients/examples/train_from_recipe_example/train_from_recipe.py --config-name=coco2017_yolox architecture=yolox_s batch_size=8 val_batch_size=16 epochs=1 training_hyperparams.average_best_models=False training_hyperparams.max_train_batches=100 training_hyperparams.max_valid_batches=100 multi_gpu=DDP num_gpus=4 - python3.8 src/super_gradients/examples/train_from_recipe_example/train_from_recipe.py --config-name=coco2017_yolox architecture=yolox_m batch_size=8 val_batch_size=8 epochs=1 training_hyperparams.average_best_models=False training_hyperparams.max_train_batches=100 training_hyperparams.max_valid_batches=100 multi_gpu=DDP num_gpus=4 - python3.8 src/super_gradients/examples/train_from_recipe_example/train_from_recipe.py --config-name=coco2017_yolox architecture=yolox_l batch_size=4 val_batch_size=8 epochs=1 training_hyperparams.average_best_models=False training_hyperparams.max_train_batches=100 training_hyperparams.max_valid_batches=100 multi_gpu=DDP num_gpus=4 + python3.8 src/super_gradients/train_from_recipe.py --config-name=coco2017_ssd_lite_mobilenet_v2 batch_size=8 val_batch_size=16 epochs=1 training_hyperparams.average_best_models=False training_hyperparams.max_train_batches=100 training_hyperparams.max_valid_batches=100 multi_gpu=DDP num_gpus=4 + python3.8 src/super_gradients/train_from_recipe.py --config-name=coco2017_yolox architecture=yolox_n batch_size=8 val_batch_size=16 epochs=1 training_hyperparams.average_best_models=False training_hyperparams.max_train_batches=100 training_hyperparams.max_valid_batches=100 multi_gpu=DDP num_gpus=4 + python3.8 src/super_gradients/train_from_recipe.py --config-name=coco2017_yolox architecture=yolox_t batch_size=8 val_batch_size=16 epochs=1 training_hyperparams.average_best_models=False training_hyperparams.max_train_batches=100 training_hyperparams.max_valid_batches=100 multi_gpu=DDP num_gpus=4 + python3.8 src/super_gradients/train_from_recipe.py --config-name=coco2017_yolox architecture=yolox_s batch_size=8 val_batch_size=16 epochs=1 training_hyperparams.average_best_models=False training_hyperparams.max_train_batches=100 training_hyperparams.max_valid_batches=100 multi_gpu=DDP num_gpus=4 + python3.8 src/super_gradients/train_from_recipe.py --config-name=coco2017_yolox architecture=yolox_m batch_size=8 val_batch_size=8 epochs=1 training_hyperparams.average_best_models=False training_hyperparams.max_train_batches=100 training_hyperparams.max_valid_batches=100 multi_gpu=DDP num_gpus=4 + python3.8 src/super_gradients/train_from_recipe.py --config-name=coco2017_yolox architecture=yolox_l batch_size=4 val_batch_size=8 epochs=1 training_hyperparams.average_best_models=False training_hyperparams.max_train_batches=100 training_hyperparams.max_valid_batches=100 multi_gpu=DDP num_gpus=4 - run: name: Remove new environment when failed @@ -686,7 +686,7 @@ jobs: python3.8 -m pip install -r requirements.txt python3.8 -m pip install . python3.8 -m pip install torch torchvision torchaudio - python3.8 src/super_gradients/examples/train_from_recipe_example/train_from_recipe.py --config-name=coco2017_pose_dekr_w32_no_dc experiment_name=shortened_coco2017_pose_dekr_w32_ap_test batch_size=4 val_batch_size=8 epochs=1 training_hyperparams.lr_warmup_steps=0 training_hyperparams.average_best_models=False training_hyperparams.max_train_batches=1000 training_hyperparams.max_valid_batches=100 multi_gpu=DDP num_gpus=4 + python3.8 src/super_gradients/train_from_recipe.py --config-name=coco2017_pose_dekr_w32_no_dc experiment_name=shortened_coco2017_pose_dekr_w32_ap_test batch_size=4 val_batch_size=8 epochs=1 training_hyperparams.lr_warmup_steps=0 training_hyperparams.average_best_models=False training_hyperparams.max_train_batches=1000 training_hyperparams.max_valid_batches=100 multi_gpu=DDP num_gpus=4 - run: name: Remove new environment when failed