wavedl 1.6.0__py3-none-any.whl → 1.6.2__py3-none-any.whl

{wavedl-1.6.0.dist-info → wavedl-1.6.2.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: wavedl
-Version: 1.6.0
+Version: 1.6.2
 Summary: A Scalable Deep Learning Framework for Wave-Based Inverse Problems
 Author: Ductho Le
 License: MIT
@@ -38,6 +38,7 @@ Requires-Dist: wandb>=0.15.0
 Requires-Dist: optuna>=3.0.0
 Requires-Dist: onnx>=1.14.0
 Requires-Dist: onnxruntime>=1.15.0
+Requires-Dist: onnxscript>=0.1.0
 Requires-Dist: triton>=2.0.0; sys_platform == "linux"
 Provides-Extra: dev
 Requires-Dist: pytest>=7.0.0; extra == "dev"
@@ -118,7 +119,7 @@ Train on datasets larger than RAM:
 
 **🧠 Models? We've Got Options**
 
-57 architectures, ready to go:
+69 architectures, ready to go:
 - CNNs, ResNets, ViTs, EfficientNets...
 - All adapted for regression
 - [Add your own](#adding-custom-models) in one line
@@ -224,66 +225,74 @@ pip install -e .
 > [!TIP]
 > In all examples below, replace `<...>` placeholders with your values. See [Configuration](#️-configuration) for defaults and options.
 
-#### Option 1: Using wavedl-hpc (Recommended for HPC)
-
-The `wavedl-hpc` command automatically configures the environment for HPC systems:
+### Training
 
 ```bash
-# Basic training (auto-detects available GPUs)
-wavedl-hpc --model <model_name> --data_path <train_data> --batch_size <number> --output_dir <output_folder>
+# Basic training (auto-detects GPUs and environment)
+wavedl-train --model <model_name> --data_path <train_data> --output_dir <output_folder>
 
 # Detailed configuration
-wavedl-hpc --model <model_name> --data_path <train_data> --batch_size <number> \
+wavedl-train --model <model_name> --data_path <train_data> --batch_size <number> \
   --lr <number> --epochs <number> --patience <number> --compile --output_dir <output_folder>
 
-# Specify GPU count explicitly
-wavedl-hpc --num_gpus 4 --model cnn --data_path train.npz --output_dir results
-```
-
-#### Option 2: Direct Accelerate Launch
-
-```bash
-# Local - auto-detects GPUs
-accelerate launch -m wavedl.train --model <model_name> --data_path <train_data> --batch_size <number> --output_dir <output_folder>
+# Multi-GPU is automatic (uses all available GPUs)
+# Override with --num_gpus if needed
+wavedl-train --model cnn --data_path train.npz --num_gpus 4 --output_dir results
 
 # Resume training (automatic - just re-run with same output_dir)
-# Manual resume from specific checkpoint:
-accelerate launch -m wavedl.train --model <model_name> --data_path <train_data> --resume <checkpoint_folder> --output_dir <output_folder>
+wavedl-train --model <model_name> --data_path <train_data> --output_dir <output_folder>
 
 # Force fresh start (ignores existing checkpoints)
-accelerate launch -m wavedl.train --model <model_name> --data_path <train_data> --output_dir <output_folder> --fresh
+wavedl-train --model <model_name> --data_path <train_data> --output_dir <output_folder> --fresh
 
 # List available models
 wavedl-train --list_models
 ```
 
-> [!TIP]
-> **Auto-Resume**: If training crashes or is interrupted, simply re-run with the same `--output_dir`. The framework automatically detects incomplete training and resumes from the last checkpoint. Use `--fresh` to force a fresh start.
+> [!NOTE]
+> `wavedl-train` automatically detects your environment:
+> - **HPC clusters** (SLURM, PBS, etc.): Uses local caching, offline WandB
+> - **Local machines**: Uses standard cache locations (~/.cache)
 >
-> **GPU Auto-Detection**: `wavedl-hpc` automatically detects available GPUs using `nvidia-smi`. Use `--num_gpus` to override.
+> **Auto-Resume**: If training crashes or is interrupted, simply re-run with the same `--output_dir`. The framework automatically detects incomplete training and resumes from the last checkpoint.
+
+<details>
+<summary><b>Advanced: Direct Accelerate Launch</b></summary>
+
+For fine-grained control over distributed training, you can use `accelerate launch` directly:
+
+```bash
+# Custom accelerate configuration
+accelerate launch -m wavedl.train --model <model_name> --data_path <train_data> --output_dir <output_folder>
+
+# Multi-node training
+accelerate launch --num_machines 2 --main_process_ip <ip> -m wavedl.train --model cnn --data_path train.npz
+```
+
+</details>
 
 ### Testing & Inference
 
-After training, use `wavedl.test` to evaluate your model on test data:
+After training, use `wavedl-test` to evaluate your model on test data:
 
 ```bash
 # Basic inference
-python -m wavedl.test --checkpoint <checkpoint_folder> --data_path <test_data>
+wavedl-test --checkpoint <checkpoint_folder> --data_path <test_data>
 
 # With visualization, CSV export, and multiple file formats
-python -m wavedl.test --checkpoint <checkpoint_folder> --data_path <test_data> \
+wavedl-test --checkpoint <checkpoint_folder> --data_path <test_data> \
   --plot --plot_format png pdf --save_predictions --output_dir <output_folder>
 
 # With custom parameter names
-python -m wavedl.test --checkpoint <checkpoint_folder> --data_path <test_data> \
+wavedl-test --checkpoint <checkpoint_folder> --data_path <test_data> \
   --param_names '$p_1$' '$p_2$' '$p_3$' --plot
 
 # Export model to ONNX for deployment (LabVIEW, MATLAB, C++, etc.)
-python -m wavedl.test --checkpoint <checkpoint_folder> --data_path <test_data> \
+wavedl-test --checkpoint <checkpoint_folder> --data_path <test_data> \
   --export onnx --export_path <output_file.onnx>
 
 # For 3D volumes with small depth (e.g., 8×128×128), override auto-detection
-python -m wavedl.test --checkpoint <checkpoint_folder> --data_path <test_data> \
+wavedl-test --checkpoint <checkpoint_folder> --data_path <test_data> \
   --input_channels 1
 ```
 
@@ -294,7 +303,7 @@ python -m wavedl.test --checkpoint <checkpoint_folder> --data_path <test_data> \
 - **Format** (with `--plot_format`): Supported formats: `png` (default), `pdf` (vector), `svg` (vector), `eps` (LaTeX), `tiff`, `jpg`, `ps`
 
 > [!NOTE]
-> `wavedl.test` auto-detects the model architecture from checkpoint metadata. If unavailable, it falls back to folder name parsing. Use `--model` to override if needed.
+> `wavedl-test` auto-detects the model architecture from checkpoint metadata. If unavailable, it falls back to folder name parsing. Use `--model` to override if needed.
 
 ### Adding Custom Models
 
@@ -338,7 +347,7 @@ class MyModel(BaseModel):
 **Step 2: Train**
 
 ```bash
-wavedl-hpc --import my_model.py --model my_model --data_path train.npz
+wavedl-train --import my_model.py --model my_model --data_path train.npz
 ```
 
 WaveDL handles everything else: training loop, logging, checkpoints, multi-GPU, early stopping, etc.
@@ -354,12 +363,12 @@ WaveDL/
 ├── src/
 │   └── wavedl/                   # Main package (namespaced)
 │       ├── __init__.py           # Package init with __version__
-│       ├── train.py              # Training entry point
+│       ├── train.py              # Training script
 │       ├── test.py               # Testing & inference script
 │       ├── hpo.py                # Hyperparameter optimization
-│       ├── hpc.py                # HPC distributed training launcher
+│       ├── launcher.py           # Training launcher (wavedl-train)
 │       │
-│       ├── models/               # Model Zoo (57 architectures)
+│       ├── models/               # Model Zoo (69 architectures)
 │       │   ├── registry.py       # Model factory (@register_model)
 │       │   ├── base.py           # Abstract base class
 │       │   └── ...               # See "Available Models" section
@@ -388,22 +397,14 @@ WaveDL/
 ## ⚙️ Configuration
 
 > [!NOTE]
-> All configuration options below work with **both** `wavedl-hpc` and direct `accelerate launch`. The wrapper script passes all arguments directly to `train.py`.
->
-> **Examples:**
-> ```bash
-> # Using wavedl-hpc
-> wavedl-hpc --model cnn --batch_size 256 --lr 5e-4 --compile
->
-> # Using accelerate launch directly
-> accelerate launch -m wavedl.train --model cnn --batch_size 256 --lr 5e-4 --compile
-> ```
+> All configuration options below work with `wavedl-train`. The wrapper script passes all arguments directly to `train.py`.
 
 <details>
-<summary><b>Available Models</b> — 57 architectures</summary>
+<summary><b>Available Models</b> — 69 architectures</summary>
 
 | Model | Backbone Params | Dim |
 |-------|-----------------|-----|
+| **── Classic CNNs ──** |||
 | **CNN** — Convolutional Neural Network |||
 | `cnn` | 1.6M | 1D/2D/3D |
 | **ResNet** — Residual Network |||
@@ -412,13 +413,14 @@ WaveDL/
 | `resnet50` | 23.5M | 1D/2D/3D |
 | `resnet18_pretrained` ⭐ | 11.2M | 2D |
 | `resnet50_pretrained` ⭐ | 23.5M | 2D |
-| **ResNet3D** — 3D Residual Network |||
-| `resnet3d_18` | 33.2M | 3D |
-| `mc3_18` — Mixed Convolution 3D | 11.5M | 3D |
-| **TCN** — Temporal Convolutional Network |||
-| `tcn_small` | 0.9M | 1D |
-| `tcn` | 6.9M | 1D |
-| `tcn_large` | 10.0M | 1D |
+| **DenseNet** — Densely Connected Network |||
+| `densenet121` | 7.0M | 1D/2D/3D |
+| `densenet169` | 12.5M | 1D/2D/3D |
+| `densenet121_pretrained` ⭐ | 7.0M | 2D |
+| **── Efficient/Mobile CNNs ──** |||
+| **MobileNetV3** — Mobile Neural Network V3 |||
+| `mobilenet_v3_small` ⭐ | 0.9M | 2D |
+| `mobilenet_v3_large` ⭐ | 3.0M | 2D |
 | **EfficientNet** — Efficient Neural Network |||
 | `efficientnet_b0` ⭐ | 4.0M | 2D |
 | `efficientnet_b1` ⭐ | 6.5M | 2D |
@@ -427,47 +429,41 @@ WaveDL/
 | `efficientnet_v2_s` ⭐ | 20.2M | 2D |
 | `efficientnet_v2_m` ⭐ | 52.9M | 2D |
 | `efficientnet_v2_l` ⭐ | 117.2M | 2D |
-| **MobileNetV3** — Mobile Neural Network V3 |||
-| `mobilenet_v3_small` ⭐ | 0.9M | 2D |
-| `mobilenet_v3_large` ⭐ | 3.0M | 2D |
 | **RegNet** — Regularized Network |||
 | `regnet_y_400mf` ⭐ | 3.9M | 2D |
 | `regnet_y_800mf` ⭐ | 5.7M | 2D |
 | `regnet_y_1_6gf` ⭐ | 10.3M | 2D |
 | `regnet_y_3_2gf` ⭐ | 17.9M | 2D |
 | `regnet_y_8gf` ⭐ | 37.4M | 2D |
-| **Swin** — Shifted Window Transformer |||
-| `swin_t` ⭐ | 27.5M | 2D |
-| `swin_s` ⭐ | 48.8M | 2D |
-| `swin_b` ⭐ | 86.7M | 2D |
+| **── Modern CNNs ──** |||
 | **ConvNeXt** — Convolutional Next |||
 | `convnext_tiny` | 27.8M | 1D/2D/3D |
 | `convnext_small` | 49.5M | 1D/2D/3D |
 | `convnext_base` | 87.6M | 1D/2D/3D |
 | `convnext_tiny_pretrained` ⭐ | 27.8M | 2D |
-| **DenseNet** — Densely Connected Network |||
-| `densenet121` | 7.0M | 1D/2D/3D |
-| `densenet169` | 12.5M | 1D/2D/3D |
-| `densenet121_pretrained` ⭐ | 7.0M | 2D |
-| **ViT** — Vision Transformer |||
-| `vit_tiny` | 5.4M | 1D/2D |
-| `vit_small` | 21.4M | 1D/2D |
-| `vit_base` | 85.3M | 1D/2D |
 | **ConvNeXt V2** — ConvNeXt with GRN |||
 | `convnext_v2_tiny` | 27.9M | 1D/2D/3D |
 | `convnext_v2_small` | 49.6M | 1D/2D/3D |
 | `convnext_v2_base` | 87.7M | 1D/2D/3D |
 | `convnext_v2_tiny_pretrained` ⭐ | 27.9M | 2D |
-| **Mamba** — State Space Model |||
-| `mamba_1d` | 3.4M | 1D |
-| **Vision Mamba (ViM)** — 2D Mamba |||
-| `vim_tiny` | 6.6M | 2D |
-| `vim_small` | 51.1M | 2D |
-| `vim_base` | 201.4M | 2D |
+| **UniRepLKNet** — Large-Kernel ConvNet |||
+| `unireplknet_tiny` | 30.8M | 1D/2D/3D |
+| `unireplknet_small` | 56.0M | 1D/2D/3D |
+| `unireplknet_base` | 97.6M | 1D/2D/3D |
+| **── Vision Transformers ──** |||
+| **ViT** — Vision Transformer |||
+| `vit_tiny` | 5.4M | 1D/2D |
+| `vit_small` | 21.4M | 1D/2D |
+| `vit_base` | 85.3M | 1D/2D |
+| **Swin** — Shifted Window Transformer |||
+| `swin_t` ⭐ | 27.5M | 2D |
+| `swin_s` ⭐ | 48.8M | 2D |
+| `swin_b` ⭐ | 86.7M | 2D |
 | **MaxViT** — Multi-Axis ViT |||
 | `maxvit_tiny` ⭐ | 30.1M | 2D |
 | `maxvit_small` ⭐ | 67.6M | 2D |
 | `maxvit_base` ⭐ | 119.1M | 2D |
+| **── Hybrid CNN-Transformer ──** |||
 | **FastViT** — Fast Hybrid CNN-ViT |||
 | `fastvit_t8` ⭐ | 4.0M | 2D |
 | `fastvit_t12` ⭐ | 6.8M | 2D |
@@ -478,6 +474,31 @@ WaveDL/
 | `caformer_s36` ⭐ | 39.2M | 2D |
 | `caformer_m36` ⭐ | 56.9M | 2D |
 | `poolformer_s12` ⭐ | 11.9M | 2D |
+| **EfficientViT** — Memory-Efficient ViT |||
+| `efficientvit_m0` ⭐ | 2.2M | 2D |
+| `efficientvit_m1` ⭐ | 2.6M | 2D |
+| `efficientvit_m2` ⭐ | 3.8M | 2D |
+| `efficientvit_b0` ⭐ | 2.1M | 2D |
+| `efficientvit_b1` ⭐ | 7.5M | 2D |
+| `efficientvit_b2` ⭐ | 21.8M | 2D |
+| `efficientvit_b3` ⭐ | 46.1M | 2D |
+| `efficientvit_l1` ⭐ | 49.5M | 2D |
+| `efficientvit_l2` ⭐ | 60.5M | 2D |
+| **── State Space Models ──** |||
+| **Mamba** — State Space Model |||
+| `mamba_1d` | 3.4M | 1D |
+| **Vision Mamba (ViM)** — 2D Mamba |||
+| `vim_tiny` | 6.6M | 2D |
+| `vim_small` | 51.1M | 2D |
+| `vim_base` | 201.4M | 2D |
+| **── Specialized Architectures ──** |||
+| **TCN** — Temporal Convolutional Network |||
+| `tcn_small` | 0.9M | 1D |
+| `tcn` | 6.9M | 1D |
+| `tcn_large` | 10.0M | 1D |
+| **ResNet3D** — 3D Residual Network |||
+| `resnet3d_18` | 33.2M | 3D |
+| `mc3_18` — Mixed Convolution 3D | 11.5M | 3D |
 | **U-Net** — U-shaped Network |||
 | `unet_regression` | 31.0M | 1D/2D/3D |
 
@@ -497,34 +518,52 @@ os.environ['TORCH_HOME'] = '.torch_cache'  # Match WaveDL's HPC cache location
 from torchvision import models as m
 from torchvision.models import video as v
 
-# === TorchVision Models ===
-weights = {
-    'resnet18': m.ResNet18_Weights, 'resnet50': m.ResNet50_Weights,
-    'efficientnet_b0': m.EfficientNet_B0_Weights, 'efficientnet_b1': m.EfficientNet_B1_Weights,
-    'efficientnet_b2': m.EfficientNet_B2_Weights, 'efficientnet_v2_s': m.EfficientNet_V2_S_Weights,
-    'efficientnet_v2_m': m.EfficientNet_V2_M_Weights, 'efficientnet_v2_l': m.EfficientNet_V2_L_Weights,
-    'mobilenet_v3_small': m.MobileNet_V3_Small_Weights, 'mobilenet_v3_large': m.MobileNet_V3_Large_Weights,
-    'regnet_y_400mf': m.RegNet_Y_400MF_Weights, 'regnet_y_800mf': m.RegNet_Y_800MF_Weights,
-    'regnet_y_1_6gf': m.RegNet_Y_1_6GF_Weights, 'regnet_y_3_2gf': m.RegNet_Y_3_2GF_Weights,
-    'regnet_y_8gf': m.RegNet_Y_8GF_Weights, 'swin_t': m.Swin_T_Weights, 'swin_s': m.Swin_S_Weights,
-    'swin_b': m.Swin_B_Weights, 'convnext_tiny': m.ConvNeXt_Tiny_Weights, 'densenet121': m.DenseNet121_Weights,
-}
-for name, w in weights.items():
-    getattr(m, name)(weights=w.DEFAULT); print(f'✓ {name}')
+# === TorchVision Models (use IMAGENET1K_V1 to match WaveDL) ===
+models = [
+    ('resnet18', m.ResNet18_Weights.IMAGENET1K_V1),
+    ('resnet50', m.ResNet50_Weights.IMAGENET1K_V1),
+    ('efficientnet_b0', m.EfficientNet_B0_Weights.IMAGENET1K_V1),
+    ('efficientnet_b1', m.EfficientNet_B1_Weights.IMAGENET1K_V1),
+    ('efficientnet_b2', m.EfficientNet_B2_Weights.IMAGENET1K_V1),
+    ('efficientnet_v2_s', m.EfficientNet_V2_S_Weights.IMAGENET1K_V1),
+    ('efficientnet_v2_m', m.EfficientNet_V2_M_Weights.IMAGENET1K_V1),
+    ('efficientnet_v2_l', m.EfficientNet_V2_L_Weights.IMAGENET1K_V1),
+    ('mobilenet_v3_small', m.MobileNet_V3_Small_Weights.IMAGENET1K_V1),
+    ('mobilenet_v3_large', m.MobileNet_V3_Large_Weights.IMAGENET1K_V1),
+    ('regnet_y_400mf', m.RegNet_Y_400MF_Weights.IMAGENET1K_V1),
+    ('regnet_y_800mf', m.RegNet_Y_800MF_Weights.IMAGENET1K_V1),
+    ('regnet_y_1_6gf', m.RegNet_Y_1_6GF_Weights.IMAGENET1K_V1),
+    ('regnet_y_3_2gf', m.RegNet_Y_3_2GF_Weights.IMAGENET1K_V1),
+    ('regnet_y_8gf', m.RegNet_Y_8GF_Weights.IMAGENET1K_V1),
+    ('swin_t', m.Swin_T_Weights.IMAGENET1K_V1),
+    ('swin_s', m.Swin_S_Weights.IMAGENET1K_V1),
+    ('swin_b', m.Swin_B_Weights.IMAGENET1K_V1),
+    ('convnext_tiny', m.ConvNeXt_Tiny_Weights.IMAGENET1K_V1),
+    ('densenet121', m.DenseNet121_Weights.IMAGENET1K_V1),
+]
+for name, w in models:
+    getattr(m, name)(weights=w); print(f'✓ {name}')
 
 # 3D video models
-v.r3d_18(weights=v.R3D_18_Weights.DEFAULT); print('✓ r3d_18')
-v.mc3_18(weights=v.MC3_18_Weights.DEFAULT); print('✓ mc3_18')
+v.r3d_18(weights=v.R3D_18_Weights.KINETICS400_V1); print('✓ r3d_18')
+v.mc3_18(weights=v.MC3_18_Weights.KINETICS400_V1); print('✓ mc3_18')
 
 # === Timm Models (MaxViT, FastViT, CAFormer, ConvNeXt V2) ===
 import timm
 
 timm_models = [
-    'maxvit_tiny_tf_224.in1k', 'maxvit_small_tf_224.in1k', 'maxvit_base_tf_224.in1k',
-    'fastvit_t8.apple_in1k', 'fastvit_t12.apple_in1k', 'fastvit_s12.apple_in1k', 'fastvit_sa12.apple_in1k',
-    'caformer_s18.sail_in1k', 'caformer_s36.sail_in22k_ft_in1k', 'caformer_m36.sail_in22k_ft_in1k',
-    'poolformer_s12.sail_in1k',
-    'convnextv2_tiny.fcmae_ft_in1k',
+    # MaxViT (no suffix - timm resolves to default)
+    'maxvit_tiny_tf_224', 'maxvit_small_tf_224', 'maxvit_base_tf_224',
+    # FastViT (no suffix)
+    'fastvit_t8', 'fastvit_t12', 'fastvit_s12', 'fastvit_sa12',
+    # CAFormer/PoolFormer (no suffix)
+    'caformer_s18', 'caformer_s36', 'caformer_m36', 'poolformer_s12',
+    # ConvNeXt V2 (no suffix)
+    'convnextv2_tiny',
+    # EfficientViT (no suffix)
+    'efficientvit_m0', 'efficientvit_m1', 'efficientvit_m2',
+    'efficientvit_b0', 'efficientvit_b1', 'efficientvit_b2', 'efficientvit_b3',
+    'efficientvit_l1', 'efficientvit_l2',
 ]
 for name in timm_models:
     timm.create_model(name, pretrained=True); print(f'✓ {name}')
@@ -602,7 +641,7 @@ WaveDL automatically enables performance optimizations for modern GPUs:
 </details>
 
 <details>
-<summary><b>HPC CLI Arguments (wavedl-hpc)</b></summary>
+<summary><b>Distributed Training Arguments</b></summary>
 
 | Argument | Default | Description |
 |----------|---------|-------------|
@@ -634,10 +673,10 @@ WaveDL automatically enables performance optimizations for modern GPUs:
 **Example:**
 ```bash
 # Use Huber loss for noisy NDE data
-accelerate launch -m wavedl.train --model cnn --loss huber --huber_delta 0.5
+wavedl-train --model cnn --loss huber --huber_delta 0.5
 
 # Weighted MSE: prioritize thickness (first target)
-accelerate launch -m wavedl.train --model cnn --loss weighted_mse --loss_weights "2.0,1.0,1.0"
+wavedl-train --model cnn --loss weighted_mse --loss_weights "2.0,1.0,1.0"
 ```
 
 </details>
@@ -657,10 +696,10 @@ accelerate launch -m wavedl.train --model cnn --loss weighted_mse --loss_weights
 **Example:**
 ```bash
 # SGD with Nesterov momentum (often better generalization)
-accelerate launch -m wavedl.train --model cnn --optimizer sgd --lr 0.01 --momentum 0.9 --nesterov
+wavedl-train --model cnn --optimizer sgd --lr 0.01 --momentum 0.9 --nesterov
 
 # RAdam for more stable training
-accelerate launch -m wavedl.train --model cnn --optimizer radam --lr 1e-3
+wavedl-train --model cnn --optimizer radam --lr 1e-3
 ```
 
 </details>
@@ -682,13 +721,13 @@ accelerate launch -m wavedl.train --model cnn --optimizer radam --lr 1e-3
 **Example:**
 ```bash
 # Cosine annealing for 1000 epochs
-accelerate launch -m wavedl.train --model cnn --scheduler cosine --epochs 1000 --min_lr 1e-7
+wavedl-train --model cnn --scheduler cosine --epochs 1000 --min_lr 1e-7
 
 # OneCycleLR for super-convergence
-accelerate launch -m wavedl.train --model cnn --scheduler onecycle --lr 1e-2 --epochs 50
+wavedl-train --model cnn --scheduler onecycle --lr 1e-2 --epochs 50
 
 # MultiStep with custom milestones
-accelerate launch -m wavedl.train --model cnn --scheduler multistep --milestones "100,200,300"
+wavedl-train --model cnn --scheduler multistep --milestones "100,200,300"
 ```
 
 </details>
@@ -699,16 +738,14 @@ accelerate launch -m wavedl.train --model cnn --scheduler multistep --milestones
 For robust model evaluation, simply add the `--cv` flag:
 
 ```bash
-# 5-fold cross-validation (works with both methods!)
-wavedl-hpc --model cnn --cv 5 --data_path train_data.npz
-# OR
-accelerate launch -m wavedl.train --model cnn --cv 5 --data_path train_data.npz
+# 5-fold cross-validation
+wavedl-train --model cnn --cv 5 --data_path train_data.npz
 
 # Stratified CV (recommended for unbalanced data)
-wavedl-hpc --model cnn --cv 5 --cv_stratify --loss huber --epochs 100
+wavedl-train --model cnn --cv 5 --cv_stratify --loss huber --epochs 100
 
 # Full configuration
-wavedl-hpc --model cnn --cv 5 --cv_stratify \
+wavedl-train --model cnn --cv 5 --cv_stratify \
     --loss huber --optimizer adamw --scheduler cosine \
     --output_dir ./cv_results
 ```
@@ -733,10 +770,10 @@ Use YAML files for reproducible experiments. CLI arguments can override any conf
 
 ```bash
 # Use a config file
-accelerate launch -m wavedl.train --config configs/config.yaml --data_path train.npz
+wavedl-train --config configs/config.yaml --data_path train.npz
 
 # Override specific values from config
-accelerate launch -m wavedl.train --config configs/config.yaml --lr 5e-4 --epochs 500
+wavedl-train --config configs/config.yaml --lr 5e-4 --epochs 500
 ```
 
 **Example config (`configs/config.yaml`):**
@@ -889,7 +926,7 @@ wavedl-hpo --data_path train.npz --models cnn --n_trials 50 --quick
 
 After HPO completes, it prints the optimal command:
 ```bash
-accelerate launch -m wavedl.train --data_path train.npz --model cnn --lr 3.2e-4 --batch_size 128 ...
+wavedl-train --data_path train.npz --model cnn --lr 3.2e-4 --batch_size 128 ...
 ```
 
 ---
@@ -1082,12 +1119,12 @@ The `examples/` folder contains a **complete, ready-to-run example** for **mater
 
 ```bash
 # Run inference on the example data
-python -m wavedl.test --checkpoint ./examples/elasticity_prediction/best_checkpoint \
+wavedl-test --checkpoint ./examples/elasticity_prediction/best_checkpoint \
   --data_path ./examples/elasticity_prediction/Test_data_100.mat \
   --plot --save_predictions --output_dir ./examples/elasticity_prediction/test_results
 
 # Export to ONNX (already included as model.onnx)
-python -m wavedl.test --checkpoint ./examples/elasticity_prediction/best_checkpoint \
+wavedl-test --checkpoint ./examples/elasticity_prediction/best_checkpoint \
   --data_path ./examples/elasticity_prediction/Test_data_100.mat \
   --export onnx --export_path ./examples/elasticity_prediction/model.onnx
 ```

wavedl-1.6.2.dist-info/RECORD

@@ -0,0 +1,46 @@
+wavedl/__init__.py,sha256=hFGU_j86Beexkcrn_V3fotGQ4ncwLGvz2lCOejEJ-f0,1177
+wavedl/hpo.py,sha256=nEiy-2O_5EhxF5hU8X5TviSAiXfVrTQx0-VE6baW7JQ,14633
+wavedl/launcher.py,sha256=_CFlgpKgHrtZebl1yQbJZJEcob06Y9-fqnRYzwW7UJQ,11776
+wavedl/test.py,sha256=1UUy9phCqrr3h_lN6mGJ7Sj73skDg4KyLk2Yuq9DiKU,38797
+wavedl/train.py,sha256=vBufy6gHShawgj8O6dvVER9TPhORa1s7L6pQtTe-N5M,57824
+wavedl/models/__init__.py,sha256=8OiT2seq1qBiUzKaSkmh_VOLJlLTT9Cn-mjhMHKGFpI,5203
+wavedl/models/_pretrained_utils.py,sha256=VPdU1DwJB93ZBf_GFIgb8-6BbAt18Phs4yorwlhLw70,12404
+wavedl/models/_template.py,sha256=J_D8taSPmV8lBaucN_vU-WiG98iFr7CJrZVNNX_Tdts,4600
+wavedl/models/base.py,sha256=bDoHYFli-aR8amcFYXbF98QYaKSCEwZWpvOhN21ODro,9075
+wavedl/models/caformer.py,sha256=ufPM-HzQ-qUZcXgnOulurY6jBUlMUzokC01whtPeVMg,7922
+wavedl/models/cnn.py,sha256=1-sNBDZHc5DySbduf5tkV1Ha25R6irksjVqfOiFbI3M,7465
+wavedl/models/convnext.py,sha256=fdXieXUuHyULjicw9Nno2SK2Tm5bDabUtdiGuEpuAF4,15711
+wavedl/models/convnext_v2.py,sha256=1ELKBPWIlUm3uybLX1KN5cgwjBPEUzZDoXL8qUzF9YY,14920
+wavedl/models/densenet.py,sha256=V_caGd0wsG_Q3Q38I4MEgYmU0v4j8mDyvv7Rn3Bk7Ac,12667
+wavedl/models/efficientnet.py,sha256=HWfhqSX57lC5Xug5TrQ3r-uFqkksoIKjmQ5Zr5njkEA,8264
+wavedl/models/efficientnetv2.py,sha256=hVSnVId8T1rjqaKlckLqWFwvo2J-qASX7o9lMbXbP-s,10947
+wavedl/models/efficientvit.py,sha256=KqFoZq9YHBMnTue6aMdPKgBOMczeBPryY_F6ip0hoEI,11630
+wavedl/models/fastvit.py,sha256=S0SF0iC-9ZJrP-9YUTLPhMJMV-W9r2--V3hVAmSSVKI,7083
+wavedl/models/mamba.py,sha256=ENmOQjtoX8btS1tDvOYEG_M3GFn1P2vWsDWcsQPSPJ0,17189
+wavedl/models/maxvit.py,sha256=I6TFGrLRcyMU-nU7u5VhOaXZWWdwmNJwHsMqbJh_g_o,7548
+wavedl/models/mobilenetv3.py,sha256=LZxCg599kGP6-XI_l3PpT8jzh4oTAdWH3Y7GH097o28,10242
+wavedl/models/registry.py,sha256=InYAXX2xbRvsFDFnYUPCptJh0F9lHlFPN77A9kqHRT0,2980
+wavedl/models/regnet.py,sha256=6Yjo2wZzdjK8VpOMagbCrHqmsfRmGkuiURmc-MesYvA,13777
+wavedl/models/resnet.py,sha256=3i4zfE15qF4cd0qbTKX-Wdy2Kd0f4mLcdd316FAcVCo,16720
+wavedl/models/resnet3d.py,sha256=edxLW4P4OBpZ5z9kMnWYV6qJ1GTkiqpwnW3-IqrPyqE,8510
+wavedl/models/swin.py,sha256=39Gwn5hNEw3-tndc8qFFzV-VZ7pJMMKey2oZONAZ8MU,14980
+wavedl/models/tcn.py,sha256=XzojpuMFG4lu_0oQHbQnkLAb7AnW-D7_6KoBlQDPLnQ,12367
+wavedl/models/unet.py,sha256=oi7eBONSe0ALpJKsYda3jRGwu-LuSiFgNdURebnGGt0,7712
+wavedl/models/unireplknet.py,sha256=jCy22m6mkApkLf3EzimMIqXy4xFs5WPUkaoz_KVWpqc,15205
+wavedl/models/vit.py,sha256=5DXshtBdN2jYlH8MxWGTlIxP5lgbmfsdLSNchOvTaYk,14911
+wavedl/utils/__init__.py,sha256=s5R9bRmJ8GNcJrD3OSAOXzwZJIXZbdYrAkZnus11sVQ,3300
+wavedl/utils/config.py,sha256=MXkaVc1_zo8sDro8mjtK1MV65t2z8b1Z6fviwSorNiY,10534
+wavedl/utils/constraints.py,sha256=V9Gyi8-uIMbLUWb2cOaHZD0SliWLxVrHZHFyo4HWK7g,18031
+wavedl/utils/cross_validation.py,sha256=HfInyZ8gUROc_AyihYKzzUE0vnoPt_mFvAI2OPK4P54,17945
+wavedl/utils/data.py,sha256=5ph2Pi8PKvuaSoJaXbFIL9WsX8pTN0A6P8FdmxvXdv4,63469
+wavedl/utils/distributed.py,sha256=7wQ3mRjkp_xjPSxDWMnBf5dSkAGUaTzntxbz0BhC5v0,4145
+wavedl/utils/losses.py,sha256=KWpU5S5noFzp3bLbcH9RNpkFPajy6fyTIh5cNjI-BYA,7038
+wavedl/utils/metrics.py,sha256=YoqiXWOsUB9Y4_alj8CmHcTgnV4MFcH5PH4XlIC13HY,40304
+wavedl/utils/optimizers.py,sha256=ZoETDSOK1fWUT2dx69PyYebeM8Vcqf9zOIKUERWk5HY,6107
+wavedl/utils/schedulers.py,sha256=K6YCiyiMM9rb0cCRXTp89noXeXcAyUEiePr27O5Cozs,7408
+wavedl-1.6.2.dist-info/LICENSE,sha256=cEUCvcvH-9BT9Y-CNGY__PwWONCKu9zsoIqWA-NeHJ4,1066
+wavedl-1.6.2.dist-info/METADATA,sha256=2mTyuip32AneUURV3K8oAjZQ2rA_13AB16R-VyRN5s8,47659
+wavedl-1.6.2.dist-info/WHEEL,sha256=beeZ86-EfXScwlR_HKu4SllMC9wUEj_8Z_4FJ3egI2w,91
+wavedl-1.6.2.dist-info/entry_points.txt,sha256=NuAvdiG93EYYpqv-_1wf6PN0WqBfABanDKalNKe2GOs,148
+wavedl-1.6.2.dist-info/top_level.txt,sha256=ccneUt3D5Qzbh3bsBSSrq9bqrhGiogcWKY24ZC4Q6Xw,7
+wavedl-1.6.2.dist-info/RECORD,,

{wavedl-1.6.0.dist-info → wavedl-1.6.2.dist-info}/entry_points.txt

@@ -1,5 +1,5 @@
 [console_scripts]
-wavedl-hpc = wavedl.hpc:main
+wavedl-hpc = wavedl.launcher:main
 wavedl-hpo = wavedl.hpo:main
 wavedl-test = wavedl.test:main
-wavedl-train = wavedl.train:main
+wavedl-train = wavedl.launcher:main

wavedl-1.6.0.dist-info/RECORD

@@ -1,44 +0,0 @@
-wavedl/__init__.py,sha256=aVEVBCcciyAZkpkVZjaY2BrgP5Pbx96x38_RRvv4H2Q,1177
-wavedl/hpc.py,sha256=6rV38nozzMt0-jKZbVJNwvQZXK0wUsIZmr9lgWN_XUw,9212
-wavedl/hpo.py,sha256=CZF0MZwTGMOrPGDveUXZFbGHwLHj1FcJTCBKVVEtLWg,15105
-wavedl/test.py,sha256=1UUy9phCqrr3h_lN6mGJ7Sj73skDg4KyLk2Yuq9DiKU,38797
-wavedl/train.py,sha256=xfA5fuug0bk-20o2MHpAXoWpGFmciSpWsE9C5RERpf8,59433
-wavedl/models/__init__.py,sha256=uBoH7JRZIYF2TxiZbdTw8x_I9fz_ZRaSnQPRG7HDyug,4462
-wavedl/models/_template.py,sha256=J_D8taSPmV8lBaucN_vU-WiG98iFr7CJrZVNNX_Tdts,4600
-wavedl/models/_timm_utils.py,sha256=yb_6ZiklFmNG3ETw3kw8BzGfo6DCdgizb_B7duLQEFs,8051
-wavedl/models/base.py,sha256=T9iDF9IQM2MYucG_ggQd31rieUkB2fob-nkHyNIl2ak,7337
-wavedl/models/caformer.py,sha256=H8T_UbO1gq0PZFMgWYaWq5qg_5sFf42coQ829ab7n3o,7916
-wavedl/models/cnn.py,sha256=rn2Xmup0w_ll6wuAnYclSeIVazoSUrUGPY-9XnhA1gE,8341
-wavedl/models/convnext.py,sha256=R72w6Vep-SIvzIYlAdQz38Gk8Zmg4wU1WyQ_ZFNdOk0,16116
-wavedl/models/convnext_v2.py,sha256=qj8SewFxOJ-JZiUJjzBDGmSw1wxEX7XnMBwf_yckhvI,15434
-wavedl/models/densenet.py,sha256=oVNKJPzoET43KJxJBhDnLkbJOjFBDWe_f_TqpgBetlY,13050
-wavedl/models/efficientnet.py,sha256=HWfhqSX57lC5Xug5TrQ3r-uFqkksoIKjmQ5Zr5njkEA,8264
-wavedl/models/efficientnetv2.py,sha256=mSJaHJwtQbtfsOFEuOCoQwUY2vh4CXgISqnobbABD_U,11262
-wavedl/models/fastvit.py,sha256=PrrNEN_q5uFHRcbY4LrzM2MwU3Y_C1cOqdv_oErRlm8,8539
-wavedl/models/mamba.py,sha256=ZavdpOLYZOIuCgyy2tFPCk0jiAtW7_mRKu8O9kqH3nY,15819
-wavedl/models/maxvit.py,sha256=yHPbFyEppEweSg4TwMbcrZQmJYHrpKtciTslfa_KhwY,7459
-wavedl/models/mobilenetv3.py,sha256=nj-OYXSfxLp_HkoMF2qzvaa8wwhmpNslWlpyknN-VKk,10537
-wavedl/models/registry.py,sha256=InYAXX2xbRvsFDFnYUPCptJh0F9lHlFPN77A9kqHRT0,2980
-wavedl/models/regnet.py,sha256=kZz9IVxPW_q0ZIFsMbD7H2DuW60h4pfdZmOTypvAkbg,14183
-wavedl/models/resnet.py,sha256=W27hx_g8_Jt6kmzRILZ4uYuhL4_c0Jro_yOLJ2ijm6g,18082
-wavedl/models/resnet3d.py,sha256=I2_4k2kEXfgSxpkocD2J0cLN2RRoPezrDzDyd_o5bDs,8768
-wavedl/models/swin.py,sha256=G_C7xQM2RIuEzrOrD2m_4VINUhmJNsntcu1WnKwHK68,15423
-wavedl/models/tcn.py,sha256=VZOzTnGbDyXZeULPU9VnGcN-4WcRbgAff7fKbGUVqrA,13214
-wavedl/models/unet.py,sha256=L5qPmSKRrybwSldXIuUCPdpY1KSkokbWsQIl1ZHABhg,7799
-wavedl/models/vit.py,sha256=nE2IWtSeMVxyKJreI7jyfS-ZqNG5g2AB7KBHKjLHKyc,14878
-wavedl/utils/__init__.py,sha256=s5R9bRmJ8GNcJrD3OSAOXzwZJIXZbdYrAkZnus11sVQ,3300
-wavedl/utils/config.py,sha256=AsGwb3XtxmbTLb59BLl5AA4wzMNgVTpl7urOJ6IGqfM,10901
-wavedl/utils/constraints.py,sha256=V9Gyi8-uIMbLUWb2cOaHZD0SliWLxVrHZHFyo4HWK7g,18031
-wavedl/utils/cross_validation.py,sha256=gwXSFTx5oxWndPjWLJAJzB6nnq2f1t9f86SbjbF-jNI,18475
-wavedl/utils/data.py,sha256=5ph2Pi8PKvuaSoJaXbFIL9WsX8pTN0A6P8FdmxvXdv4,63469
-wavedl/utils/distributed.py,sha256=7wQ3mRjkp_xjPSxDWMnBf5dSkAGUaTzntxbz0BhC5v0,4145
-wavedl/utils/losses.py,sha256=5762M-TBC_hz6uyj1NPbU1vZeFOJQq7fR3-j7OygJRo,7254
-wavedl/utils/metrics.py,sha256=YoqiXWOsUB9Y4_alj8CmHcTgnV4MFcH5PH4XlIC13HY,40304
-wavedl/utils/optimizers.py,sha256=PyIkJ_hRhFi_Fio81Gy5YQNhcME0JUUEl8OTSyu-0RA,6323
-wavedl/utils/schedulers.py,sha256=e6Sf0yj8VOqkdwkUHLMyUfGfHKTX4NMr-zfgxWqCTYI,7659
-wavedl-1.6.0.dist-info/LICENSE,sha256=cEUCvcvH-9BT9Y-CNGY__PwWONCKu9zsoIqWA-NeHJ4,1066
-wavedl-1.6.0.dist-info/METADATA,sha256=rYu2eVqVaFndhEngDzM0yr-U1MAlcH2zBjELaMY9xmU,46707
-wavedl-1.6.0.dist-info/WHEEL,sha256=beeZ86-EfXScwlR_HKu4SllMC9wUEj_8Z_4FJ3egI2w,91
-wavedl-1.6.0.dist-info/entry_points.txt,sha256=f1RNDkXFZwBzrBzTMFocJ6xhfTvTmaEDTi5YyDEUaF8,140
-wavedl-1.6.0.dist-info/top_level.txt,sha256=ccneUt3D5Qzbh3bsBSSrq9bqrhGiogcWKY24ZC4Q6Xw,7
-wavedl-1.6.0.dist-info/RECORD,,