Upload folder using huggingface_hub

.hydra/config.yaml

@@ -0,0 +1,320 @@
+training_hyperparams:
+  resume: null
+  run_id: null
+  resume_path: null
+  resume_from_remote_sg_logger: false
+  ckpt_name: ckpt_latest.pth
+  lr_mode: CosineLRScheduler
+  lr_schedule_function: null
+  lr_warmup_epochs: 3
+  lr_warmup_steps: 1000
+  lr_cooldown_epochs: 0
+  warmup_initial_lr: 1.0e-06
+  step_lr_update_freq: null
+  cosine_final_lr_ratio: 0.1
+  warmup_mode: LinearEpochLRWarmup
+  lr_updates:
+    _target_: super_gradients.training.utils.utils.empty_list
+  pre_prediction_callback: null
+  optimizer: AdamW
+  optimizer_params:
+    weight_decay: 0.0001
+  load_opt_params: true
+  zero_weight_decay_on_bias_and_bn: true
+  loss: PPYoloELoss
+  criterion_params:
+    use_static_assigner: false
+    num_classes: ${num_classes}
+    reg_max: 16
+  ema: true
+  ema_params:
+    decay: 0.9
+    decay_type: threshold
+    beta: 15
+  train_metrics_list: []
+  valid_metrics_list:
+  - DetectionMetrics_050:
+      score_thres: 0.1
+      top_k_predictions: 300
+      num_cls: ${num_classes}
+      normalize_targets: true
+      post_prediction_callback:
+        _target_: super_gradients.training.models.detection_models.pp_yolo_e.PPYoloEPostPredictionCallback
+        score_threshold: 0.01
+        nms_top_k: 1000
+        max_predictions: 300
+        nms_threshold: 0.7
+  metric_to_watch: mAP@0.50
+  greater_metric_to_watch_is_better: true
+  launch_tensorboard: false
+  tensorboard_port: null
+  tb_files_user_prompt: false
+  save_tensorboard_to_s3: false
+  precise_bn: false
+  precise_bn_batch_size: null
+  sync_bn: true
+  silent_mode: false
+  mixed_precision: true
+  save_ckpt_epoch_list:
+  - 100
+  - 200
+  - 250
+  average_best_models: true
+  dataset_statistics: false
+  batch_accumulate: 1
+  run_validation_freq: 1
+  run_test_freq: 1
+  save_model: true
+  seed: 42
+  phase_callbacks: []
+  log_installed_packages: true
+  clip_grad_norm: null
+  ckpt_best_name: ckpt_best.pth
+  max_train_batches: null
+  max_valid_batches: null
+  sg_logger: base_sg_logger
+  sg_logger_params:
+    tb_files_user_prompt: false
+    launch_tensorboard: false
+    tensorboard_port: null
+    save_checkpoints_remote: false
+    save_tensorboard_remote: false
+    save_logs_remote: false
+    monitor_system: true
+  torch_compile: false
+  torch_compile_loss: false
+  torch_compile_options:
+    mode: reduce-overhead
+    fullgraph: false
+    dynamic: false
+    backend: inductor
+    options: null
+    disable: false
+  finetune: false
+  _convert_: all
+  max_epochs: 100
+  initial_lr: 0.0004
+dataset_params:
+  data_dir: /workspace/final-final-3
+  dataset_name: ${dataset_name}
+  train_dataset_params:
+    data_dir: ${..data_dir}
+    dataset_name: ${..dataset_name}
+    split: train
+    input_dim:
+    - 640
+    - 640
+    cache_annotations: true
+    ignore_empty_annotations: false
+    transforms:
+    - DetectionMosaic:
+        input_dim: ${dataset_params.train_dataset_params.input_dim}
+        prob: 1.0
+    - DetectionRandomAffine:
+        degrees: 0.0
+        translate: 0.1
+        scales:
+        - 0.5
+        - 1.5
+        shear: 0.0
+        target_size: ${dataset_params.train_dataset_params.input_dim}
+        filter_box_candidates: false
+        wh_thr: 2
+        area_thr: 0.1
+        ar_thr: 20
+        border_value: 128
+    - DetectionHSV:
+        prob: 1.0
+        hgain: 5
+        sgain: 30
+        vgain: 30
+    - DetectionHorizontalFlip:
+        prob: 0.5
+    - DetectionPaddedRescale:
+        input_dim: ${dataset_params.train_dataset_params.input_dim}
+    - DetectionStandardize:
+        max_value: 255.0
+    - DetectionTargetsFormatTransform:
+        input_dim: ${dataset_params.train_dataset_params.input_dim}
+        output_format: LABEL_CXCYWH
+    class_inclusion_list: null
+    max_num_samples: null
+    with_crowd: false
+    verbose: 0
+  train_dataloader_params:
+    shuffle: true
+    batch_size: 12
+    min_samples: 512
+    num_workers: 4
+    drop_last: false
+    pin_memory: true
+    worker_init_fn:
+      _target_: super_gradients.training.utils.utils.load_func
+      dotpath: super_gradients.training.datasets.datasets_utils.worker_init_reset_seed
+    collate_fn: DetectionCollateFN
+  val_dataset_params:
+    data_dir: ${..data_dir}
+    dataset_name: ${..dataset_name}
+    split: valid
+    input_dim:
+    - 640
+    - 640
+    cache_annotations: true
+    ignore_empty_annotations: false
+    transforms:
+    - DetectionPaddedRescale:
+        input_dim: ${dataset_params.val_dataset_params.input_dim}
+        pad_value: 114
+    - DetectionStandardize:
+        max_value: 255.0
+    - DetectionTargetsFormatTransform:
+        input_dim: ${dataset_params.val_dataset_params.input_dim}
+        output_format: LABEL_CXCYWH
+    class_inclusion_list: null
+    max_num_samples: null
+    with_crowd: true
+    verbose: 0
+  val_dataloader_params:
+    batch_size: 16
+    num_workers: 4
+    drop_last: false
+    shuffle: false
+    pin_memory: true
+    collate_fn: CrowdDetectionCollateFN
+  _convert_: all
+checkpoint_params:
+  load_checkpoint: false
+  load_backbone: false
+  checkpoint_path: null
+  external_checkpoint_path: null
+  source_ckpt_folder_name: null
+  strict_load:
+    _target_: super_gradients.training.sg_trainer.StrictLoad
+    value: no_key_matching
+  pretrained_weights: coco
+  checkpoint_num_classes: null
+arch_params:
+  in_channels: 3
+  backbone:
+    NStageBackbone:
+      stem:
+        YoloNASStem:
+          out_channels: 48
+      stages:
+      - YoloNASStage:
+          out_channels: 96
+          num_blocks: 2
+          activation_type: relu
+          hidden_channels: 64
+          concat_intermediates: true
+      - YoloNASStage:
+          out_channels: 192
+          num_blocks: 3
+          activation_type: relu
+          hidden_channels: 128
+          concat_intermediates: true
+      - YoloNASStage:
+          out_channels: 384
+          num_blocks: 5
+          activation_type: relu
+          hidden_channels: 256
+          concat_intermediates: true
+      - YoloNASStage:
+          out_channels: 768
+          num_blocks: 2
+          activation_type: relu
+          hidden_channels: 384
+          concat_intermediates: false
+      context_module:
+        SPP:
+          output_channels: 768
+          activation_type: relu
+          k:
+          - 5
+          - 9
+          - 13
+      out_layers:
+      - stage1
+      - stage2
+      - stage3
+      - context_module
+  neck:
+    YoloNASPANNeckWithC2:
+      neck1:
+        YoloNASUpStage:
+          out_channels: 192
+          num_blocks: 2
+          hidden_channels: 192
+          width_mult: 1
+          depth_mult: 1
+          activation_type: relu
+          reduce_channels: true
+      neck2:
+        YoloNASUpStage:
+          out_channels: 96
+          num_blocks: 3
+          hidden_channels: 64
+          width_mult: 1
+          depth_mult: 1
+          activation_type: relu
+          reduce_channels: true
+      neck3:
+        YoloNASDownStage:
+          out_channels: 192
+          num_blocks: 2
+          hidden_channels: 192
+          activation_type: relu
+          width_mult: 1
+          depth_mult: 1
+      neck4:
+        YoloNASDownStage:
+          out_channels: 384
+          num_blocks: 3
+          hidden_channels: 256
+          activation_type: relu
+          width_mult: 1
+          depth_mult: 1
+  heads:
+    NDFLHeads:
+      num_classes: 80
+      reg_max: 16
+      heads_list:
+      - YoloNASDFLHead:
+          inter_channels: 128
+          width_mult: 0.75
+          first_conv_group_size: 0
+          stride: 8
+      - YoloNASDFLHead:
+          inter_channels: 256
+          width_mult: 0.75
+          first_conv_group_size: 0
+          stride: 16
+      - YoloNASDFLHead:
+          inter_channels: 512
+          width_mult: 0.75
+          first_conv_group_size: 0
+          stride: 32
+  bn_eps: 0.001
+  bn_momentum: 0.03
+  inplace_act: true
+  _convert_: all
+  num_classes: ${num_classes}
+train_dataloader: roboflow_train_yolox
+val_dataloader: roboflow_val_yolox
+dataset_name: final-final-c2j0n-mdjfm/3
+num_classes: 7
+architecture: yolo_nas_m
+load_checkpoint: false
+result_path: null
+resume: null
+multi_gpu: false
+num_gpus: 1
+experiment_suffix: ''
+experiment_name: ${architecture}_roboflow_${dataset_name}${experiment_suffix}
+lr: 0.0004
+batch_size: 12
+val_batch_size: 16
+ema: true
+epochs: 100
+num_workers: 4
+ckpt_root_dir: null

.hydra/hydra.yaml

@@ -0,0 +1,160 @@
+hydra:
+  run:
+    dir: ${hydra_output_dir:${ckpt_root_dir}, ${experiment_name}}
+  sweep:
+    dir: multirun/${now:%Y-%m-%d}/${now:%H-%M-%S}
+    subdir: ${hydra.job.num}
+  launcher:
+    _target_: hydra._internal.core_plugins.basic_launcher.BasicLauncher
+  sweeper:
+    _target_: hydra._internal.core_plugins.basic_sweeper.BasicSweeper
+    max_batch_size: null
+    params: null
+  help:
+    app_name: ${hydra.job.name}
+    header: '${hydra.help.app_name} is powered by Hydra.
+
+      '
+    footer: 'Powered by Hydra (https://hydra.cc)
+
+      Use --hydra-help to view Hydra specific help
+
+      '
+    template: '${hydra.help.header}
+
+      == Configuration groups ==
+
+      Compose your configuration from those groups (group=option)
+
+
+      $APP_CONFIG_GROUPS
+
+
+      == Config ==
+
+      Override anything in the config (foo.bar=value)
+
+
+      $CONFIG
+
+
+      ${hydra.help.footer}
+
+      '
+  hydra_help:
+    template: 'Hydra (${hydra.runtime.version})
+
+      See https://hydra.cc for more info.
+
+
+      == Flags ==
+
+      $FLAGS_HELP
+
+
+      == Configuration groups ==
+
+      Compose your configuration from those groups (For example, append hydra/job_logging=disabled
+      to command line)
+
+
+      $HYDRA_CONFIG_GROUPS
+
+
+      Use ''--cfg hydra'' to Show the Hydra config.
+
+      '
+    hydra_help: ???
+  hydra_logging:
+    version: 1
+    formatters:
+      simple:
+        format: '[%(asctime)s][HYDRA] %(message)s'
+    handlers:
+      console:
+        class: logging.StreamHandler
+        formatter: simple
+        stream: ext://sys.stdout
+    root:
+      level: INFO
+      handlers:
+      - console
+    loggers:
+      logging_example:
+        level: DEBUG
+    disable_existing_loggers: false
+  job_logging:
+    version: 1
+    formatters:
+      simple:
+        format: '[%(asctime)s][%(name)s][%(levelname)s] - %(message)s'
+    handlers:
+      console:
+        class: logging.StreamHandler
+        formatter: simple
+        stream: ext://sys.stdout
+      file:
+        class: logging.FileHandler
+        formatter: simple
+        filename: ${hydra.runtime.output_dir}/${hydra.job.name}.log
+    root:
+      level: INFO
+      handlers:
+      - console
+      - file
+    disable_existing_loggers: false
+  env: {}
+  mode: RUN
+  searchpath: []
+  callbacks:
+    shortcuts_cb:
+      _target_: super_gradients.common.environment.omegaconf_utils.RecipeShortcutsCallback
+  output_subdir: .hydra
+  overrides:
+    hydra:
+    - hydra.mode=RUN
+    task: []
+  job:
+    name: train_from_recipe
+    chdir: null
+    override_dirname: ''
+    id: ???
+    num: ???
+    config_name: roboflow_yolo_nas_m
+    env_set: {}
+    env_copy: []
+    config:
+      override_dirname:
+        kv_sep: '='
+        item_sep: ','
+        exclude_keys: []
+  runtime:
+    version: 1.3.2
+    version_base: '1.2'
+    cwd: /opt/conda/envs/app/lib/python3.10/site-packages/super_gradients/recipes
+    config_sources:
+    - path: hydra.conf
+      schema: pkg
+      provider: hydra
+    - path: /opt/conda/envs/app/lib/python3.10/site-packages/super_gradients/recipes
+      schema: file
+      provider: main
+    - path: ''
+      schema: structured
+      provider: schema
+    output_dir: /opt/conda/envs/app/lib/python3.10/checkpoints/yolo_nas_m_roboflow_final-final-c2j0n-mdjfm/3
+    choices:
+      arch_params: yolo_nas_m_arch_params
+      checkpoint_params: default_checkpoint_params
+      dataset_params: roboflow_detection_dataset_params
+      training_hyperparams: coco2017_yolo_nas_train_params
+      hydra/env: default
+      hydra/callbacks: null
+      hydra/job_logging: default
+      hydra/hydra_logging: default
+      hydra/hydra_help: default
+      hydra/help: default
+      hydra/sweeper: basic
+      hydra/launcher: basic
+      hydra/output: default
+  verbose: false

.hydra/overrides.yaml

@@ -0,0 +1 @@
+[]

average_model.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33bcf5ed7d2f930a4ccc3971bd1693f4e5a4333fe8b56df0b674bbd56bde513c
+size 205085470

ckpt_best.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91ce4e01af7d79d8ca938c5bdf526bbd3fa1a7425155eed177f9492f0ef86008
+size 681092674

ckpt_epoch_100.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a1089aa072ef28c8db6c0c954a136ce88fe71224ba6b44164194df49b7eb209
+size 681109574

ckpt_latest.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f76a6064a2733599db3f571ae5d2074d882111d35cbe72882de58e27a0752a7
+size 681099434

events.out.tfevents.1732165266.1213f0dc8cb8.11180.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:263ea174f666df5d2cde6f0d610ae36fc8d1f4ef08dce4310fde871fda1d5e28
+size 302121

logs_Nov21_05_01_06.txt

@@ -0,0 +1,46 @@
+[2024-11-21 05:01:02] INFO - super_gradients.common.crash_handler.crash_tips_setup - Crash tips is enabled. You can set your environment variable to CRASH_HANDLER=FALSE to disable it
+[2024-11-21 05:01:03] DEBUG - matplotlib - matplotlib data path: /opt/conda/envs/app/lib/python3.10/site-packages/matplotlib/mpl-data
+[2024-11-21 05:01:03] DEBUG - matplotlib - CONFIGDIR=/root/.config/matplotlib
+[2024-11-21 05:01:03] DEBUG - matplotlib - interactive is False
+[2024-11-21 05:01:03] DEBUG - matplotlib - platform is linux
+[2024-11-21 05:01:03] DEBUG - matplotlib - CACHEDIR=/root/.cache/matplotlib
+[2024-11-21 05:01:03] DEBUG - matplotlib.font_manager - Using fontManager instance from /root/.cache/matplotlib/fontlist-v390.json
+[2024-11-21 05:01:03] DEBUG - super_gradients.common.sg_loggers.clearml_sg_logger - Failed to import clearml
+[2024-11-21 05:01:04] DEBUG - hydra.core.utils - Setting JobRuntime:name=UNKNOWN_NAME
+[2024-11-21 05:01:04] DEBUG - hydra.core.utils - Setting JobRuntime:name=app
+[2024-11-21 05:01:04] DEBUG - hydra.core.utils - Setting JobRuntime:name=app
+[2024-11-21 05:01:04] INFO - super_gradients.sanity_check.env_sanity_check - Library check is not supported when super_gradients installed through "git+https://github.com/..." command
+[2024-11-21 05:01:04] DEBUG - hydra.core.utils - Setting JobRuntime:name=train_from_recipe
+[2024-11-21 05:01:06] INFO - super_gradients.training.sg_trainer.sg_trainer - Using EMA with params {'decay': 0.9, 'decay_type': 'threshold', 'beta': 15}
+[2024-11-21 05:01:08] INFO - super_gradients.training.utils.sg_trainer_utils - TRAINING PARAMETERS:
+    - Mode:                         OFF
+    - Number of GPUs:               1          (1 available on the machine)
+    - Full dataset size:            2399       (len(train_set))
+    - Batch size per GPU:           12         (batch_size)
+    - Batch Accumulate:             1          (batch_accumulate)
+    - Total batch size:             12         (num_gpus * batch_size)
+    - Effective Batch size:         12         (num_gpus * batch_size * batch_accumulate)
+    - Iterations per epoch:         200        (len(train_loader))
+    - Gradient updates per epoch:   200        (len(train_loader) / batch_accumulate)
+    - Model: YoloNAS_M  (51.13M parameters, 51.13M optimized)
+    - Learning Rates and Weight Decays:
+      - default: (51.13M parameters). LR: 0.0004 (51.13M parameters) WD: 0.0, (72.22K parameters), WD: 0.0001, (51.06M parameters)
+
+[2024-11-21 05:01:08] INFO - super_gradients.training.sg_trainer.sg_trainer - Started training for 100 epochs (0/99)
+
+[2024-11-21 05:01:47] INFO - super_gradients.common.sg_loggers.base_sg_logger - Checkpoint saved in /opt/conda/envs/app/lib/python3.10/checkpoints/yolo_nas_m_roboflow_final-final-c2j0n-mdjfm/3/RUN_20241121_050106_668266/ckpt_best.pth
+[2024-11-21 05:01:47] INFO - super_gradients.training.sg_trainer.sg_trainer - Best checkpoint overriden: validation mAP@0.50: 0.0021471609361469746
+[2024-11-21 05:02:25] INFO - super_gradients.common.sg_loggers.base_sg_logger - Checkpoint saved in /opt/conda/envs/app/lib/python3.10/checkpoints/yolo_nas_m_roboflow_final-final-c2j0n-mdjfm/3/RUN_20241121_050106_668266/ckpt_best.pth
+[2024-11-21 05:02:25] INFO - super_gradients.training.sg_trainer.sg_trainer - Best checkpoint overriden: validation mAP@0.50: 0.820346474647522
+[2024-11-21 05:03:04] INFO - super_gradients.common.sg_loggers.base_sg_logger - Checkpoint saved in /opt/conda/envs/app/lib/python3.10/checkpoints/yolo_nas_m_roboflow_final-final-c2j0n-mdjfm/3/RUN_20241121_050106_668266/ckpt_best.pth
+[2024-11-21 05:03:04] INFO - super_gradients.training.sg_trainer.sg_trainer - Best checkpoint overriden: validation mAP@0.50: 0.8461349606513977
+[2024-11-21 05:05:43] INFO - super_gradients.common.sg_loggers.base_sg_logger - Checkpoint saved in /opt/conda/envs/app/lib/python3.10/checkpoints/yolo_nas_m_roboflow_final-final-c2j0n-mdjfm/3/RUN_20241121_050106_668266/ckpt_best.pth
+[2024-11-21 05:05:43] INFO - super_gradients.training.sg_trainer.sg_trainer - Best checkpoint overriden: validation mAP@0.50: 0.8567641973495483
+[2024-11-21 05:08:28] INFO - super_gradients.common.sg_loggers.base_sg_logger - Checkpoint saved in /opt/conda/envs/app/lib/python3.10/checkpoints/yolo_nas_m_roboflow_final-final-c2j0n-mdjfm/3/RUN_20241121_050106_668266/ckpt_best.pth
+[2024-11-21 05:08:28] INFO - super_gradients.training.sg_trainer.sg_trainer - Best checkpoint overriden: validation mAP@0.50: 0.8589617013931274
+[2024-11-21 05:15:26] INFO - super_gradients.common.sg_loggers.base_sg_logger - Checkpoint saved in /opt/conda/envs/app/lib/python3.10/checkpoints/yolo_nas_m_roboflow_final-final-c2j0n-mdjfm/3/RUN_20241121_050106_668266/ckpt_best.pth
+[2024-11-21 05:15:26] INFO - super_gradients.training.sg_trainer.sg_trainer - Best checkpoint overriden: validation mAP@0.50: 0.8630316257476807
+[2024-11-21 05:39:03] INFO - super_gradients.common.sg_loggers.base_sg_logger - Checkpoint saved in /opt/conda/envs/app/lib/python3.10/checkpoints/yolo_nas_m_roboflow_final-final-c2j0n-mdjfm/3/RUN_20241121_050106_668266/ckpt_best.pth
+[2024-11-21 05:39:03] INFO - super_gradients.training.sg_trainer.sg_trainer - Best checkpoint overriden: validation mAP@0.50: 0.8690835237503052
+[2024-11-21 06:10:22] INFO - super_gradients.training.sg_trainer.sg_trainer - RUNNING ADDITIONAL TEST ON THE AVERAGED MODEL...
+[2024-11-21 06:10:27] INFO - super_gradients.common.sg_loggers.base_sg_logger - [CLEANUP] - Successfully stopped system monitoring process