wavedl 1.5.7__py3-none-any.whl → 1.6.0__py3-none-any.whl

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (29) hide show
  1. wavedl/__init__.py +1 -1
  2. wavedl/models/__init__.py +52 -4
  3. wavedl/models/_timm_utils.py +238 -0
  4. wavedl/models/caformer.py +270 -0
  5. wavedl/models/convnext.py +108 -33
  6. wavedl/models/convnext_v2.py +504 -0
  7. wavedl/models/densenet.py +5 -5
  8. wavedl/models/efficientnet.py +6 -6
  9. wavedl/models/efficientnetv2.py +3 -3
  10. wavedl/models/fastvit.py +285 -0
  11. wavedl/models/mamba.py +535 -0
  12. wavedl/models/maxvit.py +251 -0
  13. wavedl/models/mobilenetv3.py +6 -6
  14. wavedl/models/regnet.py +10 -10
  15. wavedl/models/resnet.py +5 -5
  16. wavedl/models/resnet3d.py +2 -2
  17. wavedl/models/swin.py +3 -3
  18. wavedl/models/tcn.py +3 -3
  19. wavedl/models/unet.py +1 -1
  20. wavedl/models/vit.py +6 -6
  21. wavedl/train.py +21 -16
  22. wavedl/utils/data.py +39 -6
  23. {wavedl-1.5.7.dist-info → wavedl-1.6.0.dist-info}/METADATA +90 -62
  24. wavedl-1.6.0.dist-info/RECORD +44 -0
  25. wavedl-1.5.7.dist-info/RECORD +0 -38
  26. {wavedl-1.5.7.dist-info → wavedl-1.6.0.dist-info}/LICENSE +0 -0
  27. {wavedl-1.5.7.dist-info → wavedl-1.6.0.dist-info}/WHEEL +0 -0
  28. {wavedl-1.5.7.dist-info → wavedl-1.6.0.dist-info}/entry_points.txt +0 -0
  29. {wavedl-1.5.7.dist-info → wavedl-1.6.0.dist-info}/top_level.txt +0 -0
{wavedl-1.5.7.dist-info → wavedl-1.6.0.dist-info}/METADATA RENAMED
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.2
2
2
  Name: wavedl
3
- Version: 1.5.7
3
+ Version: 1.6.0
4
4
  Summary: A Scalable Deep Learning Framework for Wave-Based Inverse Problems
5
5
  Author: Ductho Le
6
6
  License: MIT
@@ -23,6 +23,7 @@ Description-Content-Type: text/markdown
23
23
  License-File: LICENSE
24
24
  Requires-Dist: torch>=2.0.0
25
25
  Requires-Dist: torchvision>=0.15.0
26
+ Requires-Dist: timm>=0.9.0
26
27
  Requires-Dist: accelerate>=0.20.0
27
28
  Requires-Dist: numpy>=1.24.0
28
29
  Requires-Dist: scipy>=1.10.0
@@ -117,7 +118,7 @@ Train on datasets larger than RAM:
117
118
 
118
119
  **🧠 Models? We've Got Options**
119
120
 
120
- 38 architectures, ready to go:
121
+ 57 architectures, ready to go:
121
122
  - CNNs, ResNets, ViTs, EfficientNets...
122
123
  - All adapted for regression
123
124
  - [Add your own](#adding-custom-models) in one line
@@ -202,7 +203,7 @@ Deploy models anywhere:
202
203
  #### From PyPI (recommended for all users)
203
204
 
204
205
  ```bash
205
- pip install wavedl
206
+ pip install --upgrade wavedl
206
207
  ```
207
208
 
208
209
  This installs everything you need: training, inference, HPO, ONNX export.
@@ -358,22 +359,10 @@ WaveDL/
358
359
  │ ├── hpo.py # Hyperparameter optimization
359
360
  │ ├── hpc.py # HPC distributed training launcher
360
361
  │ │
361
- │ ├── models/ # Model architectures (38 variants)
362
+ │ ├── models/ # Model Zoo (57 architectures)
362
363
  │ │ ├── registry.py # Model factory (@register_model)
363
364
  │ │ ├── base.py # Abstract base class
364
- │ │ ├── cnn.py # Baseline CNN (1D/2D/3D)
365
- │ │ ├── resnet.py # ResNet-18/34/50 (1D/2D/3D)
366
- │ │ ├── resnet3d.py # ResNet3D-18, MC3-18 (3D only)
367
- │ │ ├── tcn.py # TCN (1D only)
368
- │ │ ├── efficientnet.py # EfficientNet-B0/B1/B2 (2D)
369
- │ │ ├── efficientnetv2.py # EfficientNetV2-S/M/L (2D)
370
- │ │ ├── mobilenetv3.py # MobileNetV3-Small/Large (2D)
371
- │ │ ├── regnet.py # RegNetY variants (2D)
372
- │ │ ├── swin.py # Swin Transformer (2D)
373
- │ │ ├── vit.py # Vision Transformer (1D/2D)
374
- │ │ ├── convnext.py # ConvNeXt (1D/2D/3D)
375
- │ │ ├── densenet.py # DenseNet-121/169 (1D/2D/3D)
376
- │ │ └── unet.py # U-Net Regression
365
+ │ │ └── ... # See "Available Models" section
377
366
  │ │
378
367
  │ └── utils/ # Utilities
379
368
  │ ├── data.py # Memory-mapped data pipeline
@@ -388,7 +377,7 @@ WaveDL/
388
377
  ├── configs/ # YAML config templates
389
378
  ├── examples/ # Ready-to-run examples
390
379
  ├── notebooks/ # Jupyter notebooks
391
- ├── unit_tests/ # Pytest test suite (903 tests)
380
+ ├── unit_tests/ # Pytest test suite
392
381
  │
393
382
  ├── pyproject.toml # Package config, dependencies
394
383
  ├── CHANGELOG.md # Version history
@@ -411,71 +400,96 @@ WaveDL/
411
400
  > ```
412
401
 
413
402
  <details>
414
- <summary><b>Available Models</b> — 38 architectures</summary>
403
+ <summary><b>Available Models</b> — 57 architectures</summary>
415
404
 
416
- | Model | Params | Dim |
417
- |-------|--------|-----|
405
+ | Model | Backbone Params | Dim |
406
+ |-------|-----------------|-----|
418
407
  | **CNN** — Convolutional Neural Network |||
419
- | `cnn` | 1.7M | 1D/2D/3D |
408
+ | `cnn` | 1.6M | 1D/2D/3D |
420
409
  | **ResNet** — Residual Network |||
421
- | `resnet18` | 11.4M | 1D/2D/3D |
422
- | `resnet34` | 21.5M | 1D/2D/3D |
423
- | `resnet50` | 24.6M | 1D/2D/3D |
424
- | `resnet18_pretrained` ⭐ | 11.4M | 2D |
425
- | `resnet50_pretrained` ⭐ | 24.6M | 2D |
410
+ | `resnet18` | 11.2M | 1D/2D/3D |
411
+ | `resnet34` | 21.3M | 1D/2D/3D |
412
+ | `resnet50` | 23.5M | 1D/2D/3D |
413
+ | `resnet18_pretrained` ⭐ | 11.2M | 2D |
414
+ | `resnet50_pretrained` ⭐ | 23.5M | 2D |
426
415
  | **ResNet3D** — 3D Residual Network |||
427
- | `resnet3d_18` | 33.6M | 3D |
428
- | `mc3_18` — Mixed Convolution 3D | 11.9M | 3D |
416
+ | `resnet3d_18` | 33.2M | 3D |
417
+ | `mc3_18` — Mixed Convolution 3D | 11.5M | 3D |
429
418
  | **TCN** — Temporal Convolutional Network |||
430
- | `tcn_small` | 1.0M | 1D |
431
- | `tcn` | 7.0M | 1D |
432
- | `tcn_large` | 10.2M | 1D |
419
+ | `tcn_small` | 0.9M | 1D |
420
+ | `tcn` | 6.9M | 1D |
421
+ | `tcn_large` | 10.0M | 1D |
433
422
  | **EfficientNet** — Efficient Neural Network |||
434
- | `efficientnet_b0` ⭐ | 4.7M | 2D |
435
- | `efficientnet_b1` ⭐ | 7.2M | 2D |
436
- | `efficientnet_b2` ⭐ | 8.4M | 2D |
423
+ | `efficientnet_b0` ⭐ | 4.0M | 2D |
424
+ | `efficientnet_b1` ⭐ | 6.5M | 2D |
425
+ | `efficientnet_b2` ⭐ | 7.7M | 2D |
437
426
  | **EfficientNetV2** — Efficient Neural Network V2 |||
438
- | `efficientnet_v2_s` ⭐ | 21.0M | 2D |
439
- | `efficientnet_v2_m` ⭐ | 53.6M | 2D |
440
- | `efficientnet_v2_l` ⭐ | 118.0M | 2D |
427
+ | `efficientnet_v2_s` ⭐ | 20.2M | 2D |
428
+ | `efficientnet_v2_m` ⭐ | 52.9M | 2D |
429
+ | `efficientnet_v2_l` ⭐ | 117.2M | 2D |
441
430
  | **MobileNetV3** — Mobile Neural Network V3 |||
442
- | `mobilenet_v3_small` ⭐ | 1.1M | 2D |
443
- | `mobilenet_v3_large` ⭐ | 3.2M | 2D |
431
+ | `mobilenet_v3_small` ⭐ | 0.9M | 2D |
432
+ | `mobilenet_v3_large` ⭐ | 3.0M | 2D |
444
433
  | **RegNet** — Regularized Network |||
445
- | `regnet_y_400mf` ⭐ | 4.0M | 2D |
446
- | `regnet_y_800mf` ⭐ | 5.8M | 2D |
447
- | `regnet_y_1_6gf` ⭐ | 10.5M | 2D |
448
- | `regnet_y_3_2gf` ⭐ | 18.3M | 2D |
449
- | `regnet_y_8gf` ⭐ | 37.9M | 2D |
434
+ | `regnet_y_400mf` ⭐ | 3.9M | 2D |
435
+ | `regnet_y_800mf` ⭐ | 5.7M | 2D |
436
+ | `regnet_y_1_6gf` ⭐ | 10.3M | 2D |
437
+ | `regnet_y_3_2gf` ⭐ | 17.9M | 2D |
438
+ | `regnet_y_8gf` ⭐ | 37.4M | 2D |
450
439
  | **Swin** — Shifted Window Transformer |||
451
- | `swin_t` ⭐ | 28.0M | 2D |
452
- | `swin_s` ⭐ | 49.4M | 2D |
453
- | `swin_b` ⭐ | 87.4M | 2D |
440
+ | `swin_t` ⭐ | 27.5M | 2D |
441
+ | `swin_s` ⭐ | 48.8M | 2D |
442
+ | `swin_b` ⭐ | 86.7M | 2D |
454
443
  | **ConvNeXt** — Convolutional Next |||
455
- | `convnext_tiny` | 28.2M | 1D/2D/3D |
456
- | `convnext_small` | 49.8M | 1D/2D/3D |
457
- | `convnext_base` | 88.1M | 1D/2D/3D |
458
- | `convnext_tiny_pretrained` ⭐ | 28.2M | 2D |
444
+ | `convnext_tiny` | 27.8M | 1D/2D/3D |
445
+ | `convnext_small` | 49.5M | 1D/2D/3D |
446
+ | `convnext_base` | 87.6M | 1D/2D/3D |
447
+ | `convnext_tiny_pretrained` ⭐ | 27.8M | 2D |
459
448
  | **DenseNet** — Densely Connected Network |||
460
- | `densenet121` | 7.5M | 1D/2D/3D |
461
- | `densenet169` | 13.3M | 1D/2D/3D |
462
- | `densenet121_pretrained` ⭐ | 7.5M | 2D |
449
+ | `densenet121` | 7.0M | 1D/2D/3D |
450
+ | `densenet169` | 12.5M | 1D/2D/3D |
451
+ | `densenet121_pretrained` ⭐ | 7.0M | 2D |
463
452
  | **ViT** — Vision Transformer |||
464
- | `vit_tiny` | 5.5M | 1D/2D |
465
- | `vit_small` | 21.6M | 1D/2D |
466
- | `vit_base` | 85.6M | 1D/2D |
453
+ | `vit_tiny` | 5.4M | 1D/2D |
454
+ | `vit_small` | 21.4M | 1D/2D |
455
+ | `vit_base` | 85.3M | 1D/2D |
456
+ | **ConvNeXt V2** — ConvNeXt with GRN |||
457
+ | `convnext_v2_tiny` | 27.9M | 1D/2D/3D |
458
+ | `convnext_v2_small` | 49.6M | 1D/2D/3D |
459
+ | `convnext_v2_base` | 87.7M | 1D/2D/3D |
460
+ | `convnext_v2_tiny_pretrained` ⭐ | 27.9M | 2D |
461
+ | **Mamba** — State Space Model |||
462
+ | `mamba_1d` | 3.4M | 1D |
463
+ | **Vision Mamba (ViM)** — 2D Mamba |||
464
+ | `vim_tiny` | 6.6M | 2D |
465
+ | `vim_small` | 51.1M | 2D |
466
+ | `vim_base` | 201.4M | 2D |
467
+ | **MaxViT** — Multi-Axis ViT |||
468
+ | `maxvit_tiny` ⭐ | 30.1M | 2D |
469
+ | `maxvit_small` ⭐ | 67.6M | 2D |
470
+ | `maxvit_base` ⭐ | 119.1M | 2D |
471
+ | **FastViT** — Fast Hybrid CNN-ViT |||
472
+ | `fastvit_t8` ⭐ | 4.0M | 2D |
473
+ | `fastvit_t12` ⭐ | 6.8M | 2D |
474
+ | `fastvit_s12` ⭐ | 8.8M | 2D |
475
+ | `fastvit_sa12` ⭐ | 10.9M | 2D |
476
+ | **CAFormer** — MetaFormer with Attention |||
477
+ | `caformer_s18` ⭐ | 26.3M | 2D |
478
+ | `caformer_s36` ⭐ | 39.2M | 2D |
479
+ | `caformer_m36` ⭐ | 56.9M | 2D |
480
+ | `poolformer_s12` ⭐ | 11.9M | 2D |
467
481
  | **U-Net** — U-shaped Network |||
468
- | `unet_regression` | 31.1M | 1D/2D/3D |
482
+ | `unet_regression` | 31.0M | 1D/2D/3D |
483
+
469
484
 
470
485
  ⭐ = **Pretrained on ImageNet** (recommended for smaller datasets). Weights are downloaded automatically on first use.
471
486
  - **Cache location**: `~/.cache/torch/hub/checkpoints/` (or `./.torch_cache/` on HPC if home is not writable)
472
- - **Size**: ~20–350 MB per model depending on architecture
473
487
  - **Train from scratch**: Use `--no_pretrained` to disable pretrained weights
474
488
 
475
489
  **💡 HPC Users**: If compute nodes block internet, pre-download weights on the login node:
476
490
 
477
491
  ```bash
478
- # Run once on login node (with internet) — downloads ALL pretrained weights (~1.5 GB total)
492
+ # Run once on login node (with internet) — downloads ALL pretrained weights
479
493
  python -c "
480
494
  import os
481
495
  os.environ['TORCH_HOME'] = '.torch_cache' # Match WaveDL's HPC cache location
@@ -483,7 +497,7 @@ os.environ['TORCH_HOME'] = '.torch_cache' # Match WaveDL's HPC cache location
483
497
  from torchvision import models as m
484
498
  from torchvision.models import video as v
485
499
 
486
- # Model name -> Weights class mapping
500
+ # === TorchVision Models ===
487
501
  weights = {
488
502
  'resnet18': m.ResNet18_Weights, 'resnet50': m.ResNet50_Weights,
489
503
  'efficientnet_b0': m.EfficientNet_B0_Weights, 'efficientnet_b1': m.EfficientNet_B1_Weights,
@@ -501,6 +515,20 @@ for name, w in weights.items():
501
515
  # 3D video models
502
516
  v.r3d_18(weights=v.R3D_18_Weights.DEFAULT); print('✓ r3d_18')
503
517
  v.mc3_18(weights=v.MC3_18_Weights.DEFAULT); print('✓ mc3_18')
518
+
519
+ # === Timm Models (MaxViT, FastViT, CAFormer, ConvNeXt V2) ===
520
+ import timm
521
+
522
+ timm_models = [
523
+ 'maxvit_tiny_tf_224.in1k', 'maxvit_small_tf_224.in1k', 'maxvit_base_tf_224.in1k',
524
+ 'fastvit_t8.apple_in1k', 'fastvit_t12.apple_in1k', 'fastvit_s12.apple_in1k', 'fastvit_sa12.apple_in1k',
525
+ 'caformer_s18.sail_in1k', 'caformer_s36.sail_in22k_ft_in1k', 'caformer_m36.sail_in22k_ft_in1k',
526
+ 'poolformer_s12.sail_in1k',
527
+ 'convnextv2_tiny.fcmae_ft_in1k',
528
+ ]
529
+ for name in timm_models:
530
+ timm.create_model(name, pretrained=True); print(f'✓ {name}')
531
+
504
532
  print('\\n✓ All pretrained weights cached!')
505
533
  "
506
534
  ```
wavedl-1.6.0.dist-info/RECORD ADDED
@@ -0,0 +1,44 @@
1
+ wavedl/__init__.py,sha256=aVEVBCcciyAZkpkVZjaY2BrgP5Pbx96x38_RRvv4H2Q,1177
2
+ wavedl/hpc.py,sha256=6rV38nozzMt0-jKZbVJNwvQZXK0wUsIZmr9lgWN_XUw,9212
3
+ wavedl/hpo.py,sha256=CZF0MZwTGMOrPGDveUXZFbGHwLHj1FcJTCBKVVEtLWg,15105
4
+ wavedl/test.py,sha256=1UUy9phCqrr3h_lN6mGJ7Sj73skDg4KyLk2Yuq9DiKU,38797
5
+ wavedl/train.py,sha256=xfA5fuug0bk-20o2MHpAXoWpGFmciSpWsE9C5RERpf8,59433
6
+ wavedl/models/__init__.py,sha256=uBoH7JRZIYF2TxiZbdTw8x_I9fz_ZRaSnQPRG7HDyug,4462
7
+ wavedl/models/_template.py,sha256=J_D8taSPmV8lBaucN_vU-WiG98iFr7CJrZVNNX_Tdts,4600
8
+ wavedl/models/_timm_utils.py,sha256=yb_6ZiklFmNG3ETw3kw8BzGfo6DCdgizb_B7duLQEFs,8051
9
+ wavedl/models/base.py,sha256=T9iDF9IQM2MYucG_ggQd31rieUkB2fob-nkHyNIl2ak,7337
10
+ wavedl/models/caformer.py,sha256=H8T_UbO1gq0PZFMgWYaWq5qg_5sFf42coQ829ab7n3o,7916
11
+ wavedl/models/cnn.py,sha256=rn2Xmup0w_ll6wuAnYclSeIVazoSUrUGPY-9XnhA1gE,8341
12
+ wavedl/models/convnext.py,sha256=R72w6Vep-SIvzIYlAdQz38Gk8Zmg4wU1WyQ_ZFNdOk0,16116
13
+ wavedl/models/convnext_v2.py,sha256=qj8SewFxOJ-JZiUJjzBDGmSw1wxEX7XnMBwf_yckhvI,15434
14
+ wavedl/models/densenet.py,sha256=oVNKJPzoET43KJxJBhDnLkbJOjFBDWe_f_TqpgBetlY,13050
15
+ wavedl/models/efficientnet.py,sha256=HWfhqSX57lC5Xug5TrQ3r-uFqkksoIKjmQ5Zr5njkEA,8264
16
+ wavedl/models/efficientnetv2.py,sha256=mSJaHJwtQbtfsOFEuOCoQwUY2vh4CXgISqnobbABD_U,11262
17
+ wavedl/models/fastvit.py,sha256=PrrNEN_q5uFHRcbY4LrzM2MwU3Y_C1cOqdv_oErRlm8,8539
18
+ wavedl/models/mamba.py,sha256=ZavdpOLYZOIuCgyy2tFPCk0jiAtW7_mRKu8O9kqH3nY,15819
19
+ wavedl/models/maxvit.py,sha256=yHPbFyEppEweSg4TwMbcrZQmJYHrpKtciTslfa_KhwY,7459
20
+ wavedl/models/mobilenetv3.py,sha256=nj-OYXSfxLp_HkoMF2qzvaa8wwhmpNslWlpyknN-VKk,10537
21
+ wavedl/models/registry.py,sha256=InYAXX2xbRvsFDFnYUPCptJh0F9lHlFPN77A9kqHRT0,2980
22
+ wavedl/models/regnet.py,sha256=kZz9IVxPW_q0ZIFsMbD7H2DuW60h4pfdZmOTypvAkbg,14183
23
+ wavedl/models/resnet.py,sha256=W27hx_g8_Jt6kmzRILZ4uYuhL4_c0Jro_yOLJ2ijm6g,18082
24
+ wavedl/models/resnet3d.py,sha256=I2_4k2kEXfgSxpkocD2J0cLN2RRoPezrDzDyd_o5bDs,8768
25
+ wavedl/models/swin.py,sha256=G_C7xQM2RIuEzrOrD2m_4VINUhmJNsntcu1WnKwHK68,15423
26
+ wavedl/models/tcn.py,sha256=VZOzTnGbDyXZeULPU9VnGcN-4WcRbgAff7fKbGUVqrA,13214
27
+ wavedl/models/unet.py,sha256=L5qPmSKRrybwSldXIuUCPdpY1KSkokbWsQIl1ZHABhg,7799
28
+ wavedl/models/vit.py,sha256=nE2IWtSeMVxyKJreI7jyfS-ZqNG5g2AB7KBHKjLHKyc,14878
29
+ wavedl/utils/__init__.py,sha256=s5R9bRmJ8GNcJrD3OSAOXzwZJIXZbdYrAkZnus11sVQ,3300
30
+ wavedl/utils/config.py,sha256=AsGwb3XtxmbTLb59BLl5AA4wzMNgVTpl7urOJ6IGqfM,10901
31
+ wavedl/utils/constraints.py,sha256=V9Gyi8-uIMbLUWb2cOaHZD0SliWLxVrHZHFyo4HWK7g,18031
32
+ wavedl/utils/cross_validation.py,sha256=gwXSFTx5oxWndPjWLJAJzB6nnq2f1t9f86SbjbF-jNI,18475
33
+ wavedl/utils/data.py,sha256=5ph2Pi8PKvuaSoJaXbFIL9WsX8pTN0A6P8FdmxvXdv4,63469
34
+ wavedl/utils/distributed.py,sha256=7wQ3mRjkp_xjPSxDWMnBf5dSkAGUaTzntxbz0BhC5v0,4145
35
+ wavedl/utils/losses.py,sha256=5762M-TBC_hz6uyj1NPbU1vZeFOJQq7fR3-j7OygJRo,7254
36
+ wavedl/utils/metrics.py,sha256=YoqiXWOsUB9Y4_alj8CmHcTgnV4MFcH5PH4XlIC13HY,40304
37
+ wavedl/utils/optimizers.py,sha256=PyIkJ_hRhFi_Fio81Gy5YQNhcME0JUUEl8OTSyu-0RA,6323
38
+ wavedl/utils/schedulers.py,sha256=e6Sf0yj8VOqkdwkUHLMyUfGfHKTX4NMr-zfgxWqCTYI,7659
39
+ wavedl-1.6.0.dist-info/LICENSE,sha256=cEUCvcvH-9BT9Y-CNGY__PwWONCKu9zsoIqWA-NeHJ4,1066
40
+ wavedl-1.6.0.dist-info/METADATA,sha256=rYu2eVqVaFndhEngDzM0yr-U1MAlcH2zBjELaMY9xmU,46707
41
+ wavedl-1.6.0.dist-info/WHEEL,sha256=beeZ86-EfXScwlR_HKu4SllMC9wUEj_8Z_4FJ3egI2w,91
42
+ wavedl-1.6.0.dist-info/entry_points.txt,sha256=f1RNDkXFZwBzrBzTMFocJ6xhfTvTmaEDTi5YyDEUaF8,140
43
+ wavedl-1.6.0.dist-info/top_level.txt,sha256=ccneUt3D5Qzbh3bsBSSrq9bqrhGiogcWKY24ZC4Q6Xw,7
44
+ wavedl-1.6.0.dist-info/RECORD,,
wavedl-1.5.7.dist-info/RECORD DELETED
@@ -1,38 +0,0 @@
1
- wavedl/__init__.py,sha256=Sp5fnCumQ3_S2X9LMYJsS9p7vSbjdOiQf15wBIE1RcE,1177
2
- wavedl/hpc.py,sha256=6rV38nozzMt0-jKZbVJNwvQZXK0wUsIZmr9lgWN_XUw,9212
3
- wavedl/hpo.py,sha256=CZF0MZwTGMOrPGDveUXZFbGHwLHj1FcJTCBKVVEtLWg,15105
4
- wavedl/test.py,sha256=1UUy9phCqrr3h_lN6mGJ7Sj73skDg4KyLk2Yuq9DiKU,38797
5
- wavedl/train.py,sha256=JL1ZHsqBRGTqRjoAY--vVj47kq9LdDTqen8ABkLnwEw,59090
6
- wavedl/models/__init__.py,sha256=lfSohEnAUztO14nuwayMJhPjpgySzRN3jGiyAUuBmAU,3206
7
- wavedl/models/_template.py,sha256=J_D8taSPmV8lBaucN_vU-WiG98iFr7CJrZVNNX_Tdts,4600
8
- wavedl/models/base.py,sha256=T9iDF9IQM2MYucG_ggQd31rieUkB2fob-nkHyNIl2ak,7337
9
- wavedl/models/cnn.py,sha256=rn2Xmup0w_ll6wuAnYclSeIVazoSUrUGPY-9XnhA1gE,8341
10
- wavedl/models/convnext.py,sha256=5zELY0ztMB6FxJB9uBurloT7JBdxLXezmrNRzLQjrI0,12846
11
- wavedl/models/densenet.py,sha256=LzNbQOvtcJJ4SVf-XvIlXGNUgVS2SXl-MMPbr8lcYrA,12995
12
- wavedl/models/efficientnet.py,sha256=nBgtc6EBUuDjzxg5xwW3Ftb3LFcpK2sgmyGuZL19fGA,8210
13
- wavedl/models/efficientnetv2.py,sha256=zmnCJVa3J6jOXs5xQLvaTwUllno46ieAco1zKCoEzVU,11235
14
- wavedl/models/mobilenetv3.py,sha256=61iNPtRA8sfvWfedVZ5G1bpzaUOoGLWX5W66j_ymRyo,10483
15
- wavedl/models/registry.py,sha256=InYAXX2xbRvsFDFnYUPCptJh0F9lHlFPN77A9kqHRT0,2980
16
- wavedl/models/regnet.py,sha256=aYZ0ygtLGCHgPoxnFAx5TajGfBmvOetzyQHP7MhHaLI,14093
17
- wavedl/models/resnet.py,sha256=laePTbIgINijh-Xkcp4iui8-1F17NJAjyAuA4T11eG4,18027
18
- wavedl/models/resnet3d.py,sha256=C7CL4XeSnRlIBuwf5Ei-z183uzIBObrXfkM9Iwuc5e0,8746
19
- wavedl/models/swin.py,sha256=7bHBZokjBuo3GGGG6rclYq8uoqCHCsd70-ExL12dW-4,15390
20
- wavedl/models/tcn.py,sha256=u2R61Kr6D90c6eszmzJHMuMo3pQU7oj82masPlw4Ajg,13187
21
- wavedl/models/unet.py,sha256=LqIXhasdBygwP7SZNNmiW1bHMPaJTVBpaeHtPgEHkdU,7790
22
- wavedl/models/vit.py,sha256=D4jlYAlvegb3O19jCPpUHYmt5q0SZ7EGVBIWiYbq0GA,14816
23
- wavedl/utils/__init__.py,sha256=s5R9bRmJ8GNcJrD3OSAOXzwZJIXZbdYrAkZnus11sVQ,3300
24
- wavedl/utils/config.py,sha256=AsGwb3XtxmbTLb59BLl5AA4wzMNgVTpl7urOJ6IGqfM,10901
25
- wavedl/utils/constraints.py,sha256=V9Gyi8-uIMbLUWb2cOaHZD0SliWLxVrHZHFyo4HWK7g,18031
26
- wavedl/utils/cross_validation.py,sha256=gwXSFTx5oxWndPjWLJAJzB6nnq2f1t9f86SbjbF-jNI,18475
27
- wavedl/utils/data.py,sha256=UaHYWUhtASHWBkMjM4HkUXjsgQdFbAQPnC9btcMihxg,61985
28
- wavedl/utils/distributed.py,sha256=7wQ3mRjkp_xjPSxDWMnBf5dSkAGUaTzntxbz0BhC5v0,4145
29
- wavedl/utils/losses.py,sha256=5762M-TBC_hz6uyj1NPbU1vZeFOJQq7fR3-j7OygJRo,7254
30
- wavedl/utils/metrics.py,sha256=YoqiXWOsUB9Y4_alj8CmHcTgnV4MFcH5PH4XlIC13HY,40304
31
- wavedl/utils/optimizers.py,sha256=PyIkJ_hRhFi_Fio81Gy5YQNhcME0JUUEl8OTSyu-0RA,6323
32
- wavedl/utils/schedulers.py,sha256=e6Sf0yj8VOqkdwkUHLMyUfGfHKTX4NMr-zfgxWqCTYI,7659
33
- wavedl-1.5.7.dist-info/LICENSE,sha256=cEUCvcvH-9BT9Y-CNGY__PwWONCKu9zsoIqWA-NeHJ4,1066
34
- wavedl-1.5.7.dist-info/METADATA,sha256=kqRSEFWMTzR6pewC8pCp2oj7HtD_HrxH4RFOvBvHk2Y,46106
35
- wavedl-1.5.7.dist-info/WHEEL,sha256=beeZ86-EfXScwlR_HKu4SllMC9wUEj_8Z_4FJ3egI2w,91
36
- wavedl-1.5.7.dist-info/entry_points.txt,sha256=f1RNDkXFZwBzrBzTMFocJ6xhfTvTmaEDTi5YyDEUaF8,140
37
- wavedl-1.5.7.dist-info/top_level.txt,sha256=ccneUt3D5Qzbh3bsBSSrq9bqrhGiogcWKY24ZC4Q6Xw,7
38
- wavedl-1.5.7.dist-info/RECORD,,
{wavedl-1.5.7.dist-info → wavedl-1.6.0.dist-info}/WHEEL RENAMED
File without changes