training no longer launches since update 1.4.1a2 (type-casting issue?)
Hi all, I need your help to understand and debug this error please
Bug description
I've just updated SLEAP (v1.3.3 to v1.4.1, via conda package) on my computer and since then, every time I restart the training of my model (I am using the GUI), I get an error that blocks everything. No other changes have been made to my data or training parameters.
Expected behaviour
start training
Actual behaviour
Doesn't run training "an error occured while training centered. Your command line terminal would have more information about the training" Error in terminal reported in section 'how to reproduce'
Your personal set up
Software versions: SLEAP: 1.4.1a2 TensorFlow: 2.7.0 Numpy: 1.21.6 Python: 3.7.12 OS: Windows-10-10.0.22621-SP0
For SLEAP update, I've used conda package from https://sleap.ai/installation.html#upgrading-and-uninstalling and instructions: conda env remove -n sleap conda create -y -n sleap -c conda-forge -c nvidia -c sleap/label/dev -c sleap -c anaconda sleap=1.4.1
How to reproduce
- Go to 'run training'. Please see copy of parameters:
{ "_pipeline": "multi-animal top-down", "_ensure_channels": "", "controller_port": 9000, "publish_port": 9001, "outputs.run_name_prefix": "", "outputs.runs_folder": "C:/Windows/System32\models", "outputs.tags": "", "outputs.checkpointing.best_model": true, "outputs.checkpointing.latest_model": false, "outputs.checkpointing.final_model": false, "outputs.tensorboard.write_logs": false, "_save_viz": true, "_predict_frames": "nothing", "max_instances": null, "model.heads.centroid.sigma": 2.5, "model.heads.centered_instance.anchor_part": "spine1", "model.heads.centered_instance.sigma": 2.5, "model.heads.centroid.anchor_part": "spine1", "model.heads.multi_class_topdown.confmaps.anchor_part": "spine1", "data.instance_cropping.center_on_part": "spine1" } { "data": { "labels": { "training_labels": "C:/Windows/System32/topdownapproachvideomodif.v006.slp", "validation_labels": null, "validation_fraction": 0.35, "test_labels": null, "split_by_inds": false, "training_inds": [ 836, 108, 267, 271, 419, 565, 460, 829, 296, 825, 19, 803, 608, 520, 637, 444, 331, 140, 138, 429, 103, 348, 28, 761, 476, 636, 36, 450, 686, 109, 746, 291, 321, 553, 157, 674, 226, 779, 253, 342, 604, 264, 851, 237, 743, 676, 611, 796, 552, 230, 766, 813, 389, 324, 139, 574, 751, 110, 114, 250, 748, 727, 469, 277, 555, 581, 628, 173, 692, 220, 217, 256, 653, 191, 716, 307, 207, 489, 56, 46, 294, 804, 789, 745, 362, 765, 501, 300, 159, 379, 212, 791, 783, 314, 398, 11, 706, 135, 504, 293, 839, 219, 83, 675, 216, 286, 662, 633, 32, 547, 279, 0, 164, 695, 39, 532, 284, 347, 184, 335, 234, 364, 648, 710, 698, 464, 25, 411, 756, 561, 753, 521, 685, 425, 228, 272, 62, 614, 189, 437, 455, 280, 436, 454, 376, 560, 591, 567, 566, 426, 564, 276, 269, 152, 79, 113, 52, 696, 778, 245, 786, 31, 251, 742, 443, 479, 484, 53, 141, 69, 283, 718, 66, 23, 353, 447, 328, 223, 830, 725, 817, 641, 126, 149, 281, 399, 439, 788, 837, 623, 622, 317, 615, 193, 194, 63, 29, 735, 438, 95, 345, 729, 225, 244, 470, 295, 835, 415, 646, 472, 43, 526, 241, 814, 694, 288, 418, 150, 203, 325, 403, 583, 434, 652, 408, 599, 326, 246, 525, 634, 365, 800, 147, 274, 7, 312, 679, 412, 625, 332, 486, 490, 499, 467, 240, 315, 744, 717, 642, 44, 534, 620, 769, 239, 666, 738, 810, 612, 182, 587, 171, 382, 93, 318, 601, 201, 131, 232, 248, 395, 100, 784, 224, 243, 156, 154, 705, 359, 26, 167, 349, 38, 166, 278, 84, 589, 262, 665, 827, 863, 704, 586, 136, 363, 297, 92, 795, 420, 158, 377, 647, 733, 519, 740, 433, 860, 500, 127, 10, 13, 831, 491, 181, 856, 631, 402, 658, 338, 86, 838, 195, 807, 730, 577, 682, 496, 388, 261, 736, 233, 687, 372, 360, 571, 650, 754, 651, 118, 544, 308, 497, 229, 495, 320, 826, 96, 818, 517, 120, 400, 590, 198, 155, 313, 254, 683, 205, 762, 559, 302, 196, 134, 709, 671, 572, 381, 606, 820, 471, 855, 350, 593, 257, 824, 655, 417, 50, 481, 285, 550, 80, 485, 85, 708, 857, 598, 597, 542, 654, 596, 673, 531, 340, 463, 197, 273, 815, 680, 797, 629, 221, 688, 579, 351, 619, 823, 627, 677, 558, 72, 741, 793, 664, 163, 462, 260, 446, 453, 792, 806, 570, 160, 1, 702, 459, 554, 355, 693, 145, 265, 422, 584, 518, 266, 128, 119, 617, 390, 144, 543, 71, 739, 767, 311, 6, 172, 828, 714, 672, 657, 77, 643, 380, 768, 101, 616, 255, 27, 310, 613, 722, 516, 707, 798, 728, 35, 343, 305, 737, 299, 190, 457, 757, 582, 177, 850, 54, 132, 523, 776, 5, 222, 461, 323, 9, 721, 329, 603, 834, 396, 70, 67, 391, 91, 213, 755, 507, 211, 162, 4, 371, 133, 607, 122, 759, 624, 242, 370, 40, 808, 151, 375, 621, 723, 231, 556, 540, 684, 847, 15, 106, 752, 645, 361, 512, 82, 777, 168, 845, 701, 148, 505, 451, 787, 569, 384, 282, 413, 819, 20, 117, 822, 252, 594, 319, 515, 852, 249, 861, 18, 247, 770, 337, 292, 60, 394, 179, 539, 699, 98, 859, 200 ], "validation_inds": [ 423, 369, 774, 358, 458, 330, 494, 715, 393, 538, 153, 568, 48, 289, 732, 33, 790, 580, 442, 270, 61, 218, 502, 258, 528, 498, 750, 635, 374, 805, 392, 711, 414, 649, 697, 410, 333, 37, 794, 47, 104, 129, 511, 832, 764, 94, 510, 660, 430, 811, 690, 180, 275, 161, 75, 24, 404, 432, 763, 681, 16, 115, 378, 97, 487, 592, 407, 334, 482, 42, 199, 480, 843, 816, 713, 368, 514, 3, 111, 640, 2, 846, 541, 802, 209, 799, 386, 548, 595, 609, 65, 290, 64, 691, 492, 670, 427, 73, 493, 204, 656, 421, 55, 210, 483, 537, 445, 585, 30, 726, 187, 700, 448, 573, 405, 530, 780, 401, 304, 545, 663, 506, 639, 45, 524, 842, 668, 397, 105, 678, 175, 116, 549, 782, 259, 137, 841, 57, 781, 644, 208, 49, 431, 74, 227, 734, 215, 747, 121, 68, 235, 186, 833, 107, 773, 303, 238, 58, 125, 758, 309, 513, 771, 533, 22, 202, 146, 78, 503, 263, 801, 712, 344, 488, 661, 848, 508, 165, 602, 853, 383, 775, 409, 336, 206, 456, 659, 475, 529, 8, 527, 406, 563, 183, 170, 618, 416, 578, 440, 87, 812, 367, 772, 90, 449, 435, 785, 188, 287, 130, 626, 477, 719, 17, 356, 474, 354, 21, 174, 81, 849, 638, 551, 509, 142, 102, 749, 466, 821, 840, 76, 298, 465, 341, 34, 99, 536, 720, 123, 557, 192, 88, 59, 605, 306, 185, 575, 169, 473, 703, 522, 600, 51, 301, 327, 428, 178, 667, 176, 562, 858, 112, 339, 373, 357, 12, 576, 441, 387, 535, 316, 478, 669, 632, 14, 689, 731, 468, 346, 854, 610, 760, 424, 809, 41, 352, 236, 214, 724, 385, 588, 452, 268, 124, 630, 143, 89, 322, 844, 862, 366, 546 ], "test_inds": null, "search_path_hints": [ "", "", "", "", "", "", "", "" ], "skeletons": [] }, "preprocessing": { "ensure_rgb": false, "ensure_grayscale": false, "imagenet_mode": null, "input_scaling": 0.5, "pad_to_stride": 16, "resize_and_pad_to_target": true, "target_height": 768, "target_width": 1024 }, "instance_cropping": { "center_on_part": "spine1", "crop_size": 0, "crop_size_detection_padding": 16 } }, "model": { "backbone": { "leap": null, "unet": { "stem_stride": null, "max_stride": 16, "output_stride": 2, "filters": 16, "filters_rate": 2.0, "middle_block": true, "up_interpolate": true, "stacks": 1 }, "hourglass": null, "resnet": null, "pretrained_encoder": null }, "heads": { "single_instance": null, "centroid": { "anchor_part": "spine1", "sigma": 2.5, "output_stride": 2, "loss_weight": 1.0, "offset_refinement": false }, "centered_instance": null, "multi_instance": null, "multi_class_bottomup": null, "multi_class_topdown": null }, "base_checkpoint": null }, "optimization": { "preload_data": true, "augmentation_config": { "rotate": true, "rotation_min_angle": -180.0, "rotation_max_angle": 180.0, "translate": false, "translate_min": -5, "translate_max": 5, "scale": true, "scale_min": 0.5, "scale_max": 2.0, "uniform_noise": true, "uniform_noise_min_val": 0.0, "uniform_noise_max_val": 10.0, "gaussian_noise": true, "gaussian_noise_mean": 5.0, "gaussian_noise_stddev": 1.0, "contrast": true, "contrast_min_gamma": 0.5, "contrast_max_gamma": 2.0, "brightness": true, "brightness_min_val": -20.0, "brightness_max_val": 20.0, "random_crop": false, "random_crop_height": 256, "random_crop_width": 256, "random_flip": false, "flip_horizontal": false }, "online_shuffling": true, "shuffle_buffer_size": 128, "prefetch": true, "batch_size": 8, "batches_per_epoch": 200, "min_batches_per_epoch": 200, "val_batches_per_epoch": 18, "min_val_batches_per_epoch": 10, "epochs": 200, "optimizer": "adam", "initial_learning_rate": 0.0001, "learning_rate_schedule": { "reduce_on_plateau": true, "reduction_factor": 0.5, "plateau_min_delta": 1e-06, "plateau_patience": 5, "plateau_cooldown": 3, "min_learning_rate": 1e-08 }, "hard_keypoint_mining": { "online_mining": false, "hard_to_easy_ratio": 2.0, "min_hard_keypoints": 2, "max_hard_keypoints": null, "loss_scale": 5.0 }, "early_stopping": { "stop_training_on_plateau": true, "plateau_min_delta": 1e-08, "plateau_patience": 20 } }, "outputs": { "save_outputs": true, "run_name": null, "run_name_prefix": "", "run_name_suffix": null, "runs_folder": "C:/Windows/System32\models", "tags": [ "" ], "save_visualizations": true, "delete_viz_images": true, "zip_outputs": false, "log_to_csv": true, "checkpointing": { "initial_model": false, "best_model": true, "every_epoch": false, "latest_model": false, "final_model": false }, "tensorboard": { "write_logs": false, "loss_frequency": "epoch", "architecture_graph": false, "profile_graph": false, "visualizations": true }, "zmq": { "subscribe_to_controller": true, "controller_address": "tcp://127.0.0.1:9000", "controller_polling_timeout": 10, "publish_updates": true, "publish_address": "tcp://127.0.0.1:9001" } }, "name": "", "description": "", "sleap_version": "1.3.3", "filename": "C:/Windows/System32\models\250120_200358.centroid.n=864\training_config.json" } { "data": { "labels": { "training_labels": "C:/Windows/System32/topdownapproachvideomodif.v006.slp", "validation_labels": null, "validation_fraction": 0.35, "test_labels": null, "split_by_inds": false, "training_inds": [ 32, 430, 465, 99, 174, 45, 252, 401, 169, 450, 191, 200, 539, 532, 198, 74, 396, 166, 142, 263, 280, 7, 540, 120, 246, 492, 353, 326, 347, 315, 289, 69, 491, 560, 400, 80, 57, 167, 195, 508, 29, 368, 168, 346, 413, 499, 374, 402, 516, 5, 212, 304, 13, 448, 393, 349, 314, 115, 409, 517, 173, 476, 305, 535, 126, 154, 60, 367, 481, 84, 376, 328, 220, 119, 555, 211, 434, 435, 161, 544, 410, 193, 245, 541, 379, 332, 217, 175, 244, 148, 552, 184, 352, 218, 117, 106, 163, 265, 43, 66, 453, 49, 459, 251, 242, 129, 223, 197, 426, 398, 140, 546, 172, 519, 21, 399, 12, 523, 359, 135, 500, 25, 145, 502, 170, 185, 180, 458, 266, 188, 455, 423, 36, 162, 468, 417, 530, 512, 151, 533, 103, 464, 362, 443, 320, 271, 310, 343, 397, 318, 243, 156, 404, 474, 277, 147, 415, 323, 303, 336, 364, 494, 378, 282, 324, 357, 522, 296, 213, 365, 205, 411, 425, 92, 48, 138, 424, 518, 283, 86, 391, 360, 1, 116, 478, 83, 275, 164, 104, 548, 286, 471, 98, 385, 366, 128, 377, 456, 493, 134, 247, 259, 144, 429, 210, 449, 371, 439, 155, 510, 545, 338, 511, 190, 97, 182, 268, 79, 262, 177, 390, 549, 28, 421, 354, 526, 41, 75, 165, 344, 225, 301, 267, 319, 6, 427, 14, 8, 256, 356, 270, 127, 102, 461, 67, 231, 329, 137, 333, 447, 408, 108, 559, 437, 39, 309, 386, 467, 284, 72, 369, 171, 520, 419, 207, 2, 76, 477, 42, 316, 394, 64, 483, 537, 230, 470, 238, 90, 527, 228, 422, 528, 59, 317, 94, 109, 442, 279, 30, 260, 27, 73, 33, 22, 291, 416, 105, 216, 232, 70, 489, 221, 340, 78, 50, 531, 118, 311, 525, 53, 547, 63, 406, 46, 186, 58, 255, 249, 521, 47, 294, 9, 542, 554, 107, 157, 509, 176, 507, 181, 350, 479, 132, 431, 203, 558, 114, 278, 543, 387, 222, 321, 308, 529, 375, 538, 17, 463, 77, 65, 15, 31, 10, 131, 488, 469, 438, 100, 96, 363, 227, 312, 452, 553, 325 ], "validation_inds": [ 348, 130, 226, 550, 208, 298, 101, 123, 240, 202, 248, 204, 0, 372, 440, 250, 187, 3, 158, 24, 405, 146, 124, 159, 345, 482, 224, 139, 55, 487, 179, 4, 122, 160, 496, 91, 335, 234, 35, 460, 237, 214, 327, 451, 498, 342, 239, 56, 189, 473, 441, 418, 287, 480, 274, 143, 201, 215, 414, 229, 20, 16, 254, 551, 307, 515, 433, 281, 269, 355, 504, 253, 407, 194, 192, 276, 299, 490, 339, 330, 113, 432, 206, 428, 121, 112, 54, 52, 141, 38, 153, 125, 501, 62, 88, 258, 514, 196, 388, 395, 199, 40, 341, 26, 236, 497, 484, 87, 337, 306, 293, 111, 462, 290, 273, 322, 361, 11, 19, 373, 412, 233, 392, 82, 380, 136, 297, 257, 209, 436, 261, 300, 536, 557, 485, 381, 183, 444, 534, 23, 457, 34, 389, 513, 313, 506, 503, 71, 219, 81, 495, 133, 466, 556, 334, 454, 403, 351, 178, 382, 370, 95, 475, 524, 505, 486, 68, 44, 61, 420, 51, 37, 384, 272, 446, 331, 110, 241, 89, 18, 472, 292, 152, 235, 358, 85, 93, 445, 288, 264, 302, 285, 383, 295, 149, 150 ], "test_inds": null, "search_path_hints": [ "", "", "", "" ], "skeletons": [] }, "preprocessing": { "ensure_rgb": false, "ensure_grayscale": false, "imagenet_mode": null, "input_scaling": 1.0, "pad_to_stride": 1, "resize_and_pad_to_target": true, "target_height": 768, "target_width": 1024 }, "instance_cropping": { "center_on_part": "spine1", "crop_size": 128, "crop_size_detection_padding": 16 } }, "model": { "backbone": { "leap": null, "unet": { "stem_stride": null, "max_stride": 32, "output_stride": 4, "filters": 24, "filters_rate": 1.5, "middle_block": true, "up_interpolate": true, "stacks": 1 }, "hourglass": null, "resnet": null, "pretrained_encoder": null }, "heads": { "single_instance": null, "centroid": null, "centered_instance": { "anchor_part": "spine1", "part_names": [ "nose", "left_ear", "right_ear", "left_shoulder", "right_shoulder", "left_hand", "right_hand", "left_back", "right_back", "tail", "head", "left_paw", "right_paw", "spine1", "spine2", "spine3" ], "sigma": 2.5, "output_stride": 4, "loss_weight": 1.0, "offset_refinement": false }, "multi_instance": null, "multi_class_bottomup": null, "multi_class_topdown": null }, "base_checkpoint": null }, "optimization": { "preload_data": true, "augmentation_config": { "rotate": true, "rotation_min_angle": -180.0, "rotation_max_angle": 180.0, "translate": false, "translate_min": -5, "translate_max": 5, "scale": true, "scale_min": 0.6, "scale_max": 1.4, "uniform_noise": true, "uniform_noise_min_val": 0.0, "uniform_noise_max_val": 10.0, "gaussian_noise": true, "gaussian_noise_mean": 5.0, "gaussian_noise_stddev": 1.0, "contrast": true, "contrast_min_gamma": 0.5, "contrast_max_gamma": 2.0, "brightness": true, "brightness_min_val": -20.0, "brightness_max_val": 20.0, "random_crop": false, "random_crop_height": 256, "random_crop_width": 256, "random_flip": false, "flip_horizontal": false }, "online_shuffling": true, "shuffle_buffer_size": 128, "prefetch": true, "batch_size": 8, "batches_per_epoch": 311, "min_batches_per_epoch": 200, "val_batches_per_epoch": 34, "min_val_batches_per_epoch": 10, "epochs": 200, "optimizer": "adam", "initial_learning_rate": 0.0001, "learning_rate_schedule": { "reduce_on_plateau": true, "reduction_factor": 0.5, "plateau_min_delta": 1e-06, "plateau_patience": 5, "plateau_cooldown": 3, "min_learning_rate": 1e-08 }, "hard_keypoint_mining": { "online_mining": true, "hard_to_easy_ratio": 2.0, "min_hard_keypoints": 2, "max_hard_keypoints": null, "loss_scale": 5.0 }, "early_stopping": { "stop_training_on_plateau": true, "plateau_min_delta": 1e-08, "plateau_patience": 20 } }, "outputs": { "save_outputs": true, "run_name": null, "run_name_prefix": "", "run_name_suffix": null, "runs_folder": "C:/Windows/System32\models", "tags": [ "" ], "save_visualizations": true, "delete_viz_images": true, "zip_outputs": false, "log_to_csv": true, "checkpointing": { "initial_model": false, "best_model": true, "every_epoch": false, "latest_model": false, "final_model": false }, "tensorboard": { "write_logs": false, "loss_frequency": "epoch", "architecture_graph": false, "profile_graph": false, "visualizations": true }, "zmq": { "subscribe_to_controller": true, "controller_address": "tcp://127.0.0.1:9000", "controller_polling_timeout": 10, "publish_updates": true, "publish_address": "tcp://127.0.0.1:9001" } }, "name": "", "description": "", "sleap_version": "1.3.3", "filename": "C:/Windows/System32\models\250106_184019.centered_instance.n=561\training_config.json" }
- Please see error Resetting monitor window. Polling: C:/Windows/System32\models\250121_134227.centroid.n=864\viz\validation.*.png Start training centroid... ['sleap-train', 'C:\Users\cviel\AppData\Local\Temp\tmpasrp01rk\250121_134227_training_job.json', 'C:/Windows/System32/topdownapproachvideomodif.v006.slp', '--zmq', '--controller_port', '9000', '--publish_port', '9001', '--save_viz'] INFO:sleap.nn.training:Versions: SLEAP: 1.4.1a2 TensorFlow: 2.7.0 Numpy: 1.21.6 Python: 3.7.12 OS: Windows-10-10.0.22621-SP0 INFO:sleap.nn.training:Training labels file: C:/Windows/System32/topdownapproachvideomodif.v006.slp INFO:sleap.nn.training:Training profile: C:\Users\cviel\AppData\Local\Temp\tmpasrp01rk\250121_134227_training_job.json INFO:sleap.nn.training: INFO:sleap.nn.training:Arguments: INFO:sleap.nn.training:{ "training_job_path": "C:\Users\cviel\AppData\Local\Temp\tmpasrp01rk\250121_134227_training_job.json", "labels_path": "C:/Windows/System32/topdownapproachvideomodif.v006.slp", "video_paths": [ "" ], "val_labels": null, "test_labels": null, "base_checkpoint": null, "tensorboard": false, "save_viz": true, "zmq": true, "publish_port": 9001, "controller_port": 9000, "run_name": "", "prefix": "", "suffix": "", "cpu": false, "first_gpu": false, "last_gpu": false, "gpu": "auto" } INFO:sleap.nn.training: INFO:sleap.nn.training:Training job: INFO:sleap.nn.training:{ "data": { "labels": { "training_labels": "C:/Windows/System32/topdownapproachvideomodif.v006.slp", "validation_labels": null, "validation_fraction": 0.35, "test_labels": null, "split_by_inds": false, "training_inds": [ 836, 108, 267, 271, 419, 565, 460, 829, 296, 825, 19, 803, 608, 520, 637, 444, 331, 140, 138, 429, 103, 348, 28, 761, 476, 636, 36, 450, 686, 109, 746, 291, 321, 553, 157, 674, 226, 779, 253, 342, 604, 264, 851, 237, 743, 676, 611, 796, 552, 230, 766, 813, 389, 324, 139, 574, 751, 110, 114, 250, 748, 727, 469, 277, 555, 581, 628, 173, 692, 220, 217, 256, 653, 191, 716, 307, 207, 489, 56, 46, 294, 804, 789, 745, 362, 765, 501, 300, 159, 379, 212, 791, 783, 314, 398, 11, 706, 135, 504, 293, 839, 219, 83, 675, 216, 286, 662, 633, 32, 547, 279, 0, 164, 695, 39, 532, 284, 347, 184, 335, 234, 364, 648, 710, 698, 464, 25, 411, 756, 561, 753, 521, 685, 425, 228, 272, 62, 614, 189, 437, 455, 280, 436, 454, 376, 560, 591, 567, 566, 426, 564, 276, 269, 152, 79, 113, 52, 696, 778, 245, 786, 31, 251, 742, 443, 479, 484, 53, 141, 69, 283, 718, 66, 23, 353, 447, 328, 223, 830, 725, 817, 641, 126, 149, 281, 399, 439, 788, 837, 623, 622, 317, 615, 193, 194, 63, 29, 735, 438, 95, 345, 729, 225, 244, 470, 295, 835, 415, 646, 472, 43, 526, 241, 814, 694, 288, 418, 150, 203, 325, 403, 583, 434, 652, 408, 599, 326, 246, 525, 634, 365, 800, 147, 274, 7, 312, 679, 412, 625, 332, 486, 490, 499, 467, 240, 315, 744, 717, 642, 44, 534, 620, 769, 239, 666, 738, 810, 612, 182, 587, 171, 382, 93, 318, 601, 201, 131, 232, 248, 395, 100, 784, 224, 243, 156, 154, 705, 359, 26, 167, 349, 38, 166, 278, 84, 589, 262, 665, 827, 863, 704, 586, 136, 363, 297, 92, 795, 420, 158, 377, 647, 733, 519, 740, 433, 860, 500, 127, 10, 13, 831, 491, 181, 856, 631, 402, 658, 338, 86, 838, 195, 807, 730, 577, 682, 496, 388, 261, 736, 233, 687, 372, 360, 571, 650, 754, 651, 118, 544, 308, 497, 229, 495, 320, 826, 96, 818, 517, 120, 400, 590, 198, 155, 313, 254, 683, 205, 762, 559, 302, 196, 134, 709, 671, 572, 381, 606, 820, 471, 855, 350, 593, 257, 824, 655, 417, 50, 481, 285, 550, 80, 485, 85, 708, 857, 598, 597, 542, 654, 596, 673, 531, 340, 463, 197, 273, 815, 680, 797, 629, 221, 688, 579, 351, 619, 823, 627, 677, 558, 72, 741, 793, 664, 163, 462, 260, 446, 453, 792, 806, 570, 160, 1, 702, 459, 554, 355, 693, 145, 265, 422, 584, 518, 266, 128, 119, 617, 390, 144, 543, 71, 739, 767, 311, 6, 172, 828, 714, 672, 657, 77, 643, 380, 768, 101, 616, 255, 27, 310, 613, 722, 516, 707, 798, 728, 35, 343, 305, 737, 299, 190, 457, 757, 582, 177, 850, 54, 132, 523, 776, 5, 222, 461, 323, 9, 721, 329, 603, 834, 396, 70, 67, 391, 91, 213, 755, 507, 211, 162, 4, 371, 133, 607, 122, 759, 624, 242, 370, 40, 808, 151, 375, 621, 723, 231, 556, 540, 684, 847, 15, 106, 752, 645, 361, 512, 82, 777, 168, 845, 701, 148, 505, 451, 787, 569, 384, 282, 413, 819, 20, 117, 822, 252, 594, 319, 515, 852, 249, 861, 18, 247, 770, 337, 292, 60, 394, 179, 539, 699, 98, 859, 200 ], "validation_inds": [ 423, 369, 774, 358, 458, 330, 494, 715, 393, 538, 153, 568, 48, 289, 732, 33, 790, 580, 442, 270, 61, 218, 502, 258, 528, 498, 750, 635, 374, 805, 392, 711, 414, 649, 697, 410, 333, 37, 794, 47, 104, 129, 511, 832, 764, 94, 510, 660, 430, 811, 690, 180, 275, 161, 75, 24, 404, 432, 763, 681, 16, 115, 378, 97, 487, 592, 407, 334, 482, 42, 199, 480, 843, 816, 713, 368, 514, 3, 111, 640, 2, 846, 541, 802, 209, 799, 386, 548, 595, 609, 65, 290, 64, 691, 492, 670, 427, 73, 493, 204, 656, 421, 55, 210, 483, 537, 445, 585, 30, 726, 187, 700, 448, 573, 405, 530, 780, 401, 304, 545, 663, 506, 639, 45, 524, 842, 668, 397, 105, 678, 175, 116, 549, 782, 259, 137, 841, 57, 781, 644, 208, 49, 431, 74, 227, 734, 215, 747, 121, 68, 235, 186, 833, 107, 773, 303, 238, 58, 125, 758, 309, 513, 771, 533, 22, 202, 146, 78, 503, 263, 801, 712, 344, 488, 661, 848, 508, 165, 602, 853, 383, 775, 409, 336, 206, 456, 659, 475, 529, 8, 527, 406, 563, 183, 170, 618, 416, 578, 440, 87, 812, 367, 772, 90, 449, 435, 785, 188, 287, 130, 626, 477, 719, 17, 356, 474, 354, 21, 174, 81, 849, 638, 551, 509, 142, 102, 749, 466, 821, 840, 76, 298, 465, 341, 34, 99, 536, 720, 123, 557, 192, 88, 59, 605, 306, 185, 575, 169, 473, 703, 522, 600, 51, 301, 327, 428, 178, 667, 176, 562, 858, 112, 339, 373, 357, 12, 576, 441, 387, 535, 316, 478, 669, 632, 14, 689, 731, 468, 346, 854, 610, 760, 424, 809, 41, 352, 236, 214, 724, 385, 588, 452, 268, 124, 630, 143, 89, 322, 844, 862, 366, 546 ], "test_inds": null, "search_path_hints": [ "", "", "", "", "", "", "", "" ], "skeletons": [] }, "preprocessing": { "ensure_rgb": false, "ensure_grayscale": false, "imagenet_mode": null, "input_scaling": 0.5, "pad_to_stride": 16, "resize_and_pad_to_target": true, "target_height": 768, "target_width": 1024 }, "instance_cropping": { "center_on_part": "spine1", "crop_size": 0, "crop_size_detection_padding": 16 } }, "model": { "backbone": { "leap": null, "unet": { "stem_stride": null, "max_stride": 16, "output_stride": 2, "filters": 16, "filters_rate": 2.0, "middle_block": true, "up_interpolate": true, "stacks": 1 }, "hourglass": null, "resnet": null, "pretrained_encoder": null }, "heads": { "single_instance": null, "centroid": { "anchor_part": "spine1", "sigma": 2.5, "output_stride": 2, "loss_weight": 1.0, "offset_refinement": false }, "centered_instance": null, "multi_instance": null, "multi_class_bottomup": null, "multi_class_topdown": null }, "base_checkpoint": null }, "optimization": { "preload_data": true, "augmentation_config": { "rotate": true, "rotation_min_angle": -180.0, "rotation_max_angle": 180.0, "translate": false, "translate_min": -5, "translate_max": 5, "scale": true, "scale_min": 0.5, "scale_max": 2.0, "uniform_noise": true, "uniform_noise_min_val": 0.0, "uniform_noise_max_val": 10.0, "gaussian_noise": true, "gaussian_noise_mean": 5.0, "gaussian_noise_stddev": 1.0, "contrast": true, "contrast_min_gamma": 0.5, "contrast_max_gamma": 2.0, "brightness": true, "brightness_min_val": -20.0, "brightness_max_val": 20.0, "random_crop": false, "random_crop_height": 256, "random_crop_width": 256, "random_flip": false, "flip_horizontal": false }, "online_shuffling": true, "shuffle_buffer_size": 128, "prefetch": true, "batch_size": 8, "batches_per_epoch": 200, "min_batches_per_epoch": 200, "val_batches_per_epoch": 18, "min_val_batches_per_epoch": 10, "epochs": 200, "optimizer": "adam", "initial_learning_rate": 0.0001, "learning_rate_schedule": { "reduce_on_plateau": true, "reduction_factor": 0.5, "plateau_min_delta": 1e-06, "plateau_patience": 5, "plateau_cooldown": 3, "min_learning_rate": 1e-08 }, "hard_keypoint_mining": { "online_mining": false, "hard_to_easy_ratio": 2.0, "min_hard_keypoints": 2, "max_hard_keypoints": null, "loss_scale": 5.0 }, "early_stopping": { "stop_training_on_plateau": true, "plateau_min_delta": 1e-08, "plateau_patience": 20 } }, "outputs": { "save_outputs": true, "run_name": "250121_134227.centroid.n=864", "run_name_prefix": "", "run_name_suffix": "", "runs_folder": "C:/Windows/System32\models", "tags": [ "" ], "save_visualizations": true, "delete_viz_images": true, "zip_outputs": false, "log_to_csv": true, "checkpointing": { "initial_model": false, "best_model": true, "every_epoch": false, "latest_model": false, "final_model": false }, "tensorboard": { "write_logs": false, "loss_frequency": "epoch", "architecture_graph": false, "profile_graph": false, "visualizations": true }, "zmq": { "subscribe_to_controller": true, "controller_address": "tcp://127.0.0.1:9000", "controller_polling_timeout": 10, "publish_updates": true, "publish_address": "tcp://127.0.0.1:9001" } }, "name": "", "description": "", "sleap_version": "1.3.3", "filename": "C:\Users\cviel\AppData\Local\Temp\tmpasrp01rk\250121_134227_training_job.json" } INFO:sleap.nn.training: INFO:sleap.nn.training:Auto-selected GPU 0 with 16050 MiB of free memory. INFO:sleap.nn.training:Using GPU 0 for acceleration. INFO:sleap.nn.training:Disabled GPU memory pre-allocation. INFO:sleap.nn.training:System: GPUs: 1/1 available Device: /physical_device:GPU:0 Available: True Initialized: False Memory growth: True INFO:sleap.nn.training: INFO:sleap.nn.training:Initializing trainer... INFO:sleap.nn.training:Loading training labels from: C:/Windows/System32/topdownapproachvideomodif.v006.slp INFO:sleap.nn.training:Creating training and validation splits from validation fraction: 0.35 INFO:sleap.nn.training: Splits: Training = 562 / Validation = 302. INFO:sleap.nn.training:Setting up for training... INFO:sleap.nn.training:Setting up pipeline builders... INFO:sleap.nn.training:Setting up model... INFO:sleap.nn.training:Building test pipeline... 2025-01-21 13:42:36.419356: I tensorflow/core/platform/cpu_feature_guard.cc:151] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations: AVX AVX2 To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags. 2025-01-21 13:42:37.025550: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1525] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 13394 MB memory: -> device: 0, name: NVIDIA GeForce RTX 4090 Laptop GPU, pci bus id: 0000:01:00.0, compute capability: 8.9 INFO:sleap.nn.training:Loaded test example. [2.440s] INFO:sleap.nn.training: Input shape: (384, 512, 3) INFO:sleap.nn.training:Created Keras model. INFO:sleap.nn.training: Backbone: UNet(stacks=1, filters=16, filters_rate=2.0, kernel_size=3, stem_kernel_size=7, convs_per_block=2, stem_blocks=0, down_blocks=4, middle_block=True, up_blocks=3, up_interpolate=True, block_contraction=False) INFO:sleap.nn.training: Max stride: 16 INFO:sleap.nn.training: Parameters: 1,953,393 INFO:sleap.nn.training: Heads: INFO:sleap.nn.training: [0] = CentroidConfmapsHead(anchor_part='spine1', sigma=2.5, output_stride=2, loss_weight=1.0) INFO:sleap.nn.training: Outputs: INFO:sleap.nn.training: [0] = KerasTensor(type_spec=TensorSpec(shape=(None, 192, 256, 1), dtype=tf.float32, name=None), name='CentroidConfmapsHead/BiasAdd:0', description="created by layer 'CentroidConfmapsHead'") INFO:sleap.nn.training:Training from scratch INFO:sleap.nn.training:Setting up data pipelines... C:\Users\cviel\anaconda3\envs\sleap\lib\site-packages\albumentations\augmentations\transforms.py:1260: FutureWarning: This class has been deprecated. Please use RandomBrightnessContrast FutureWarning, INFO:sleap.nn.training:Training set: n = 562 INFO:sleap.nn.training:Validation set: n = 302 INFO:sleap.nn.training:Setting up optimization... INFO:sleap.nn.training: Learning rate schedule: LearningRateScheduleConfig(reduce_on_plateau=True, reduction_factor=0.5, plateau_min_delta=1e-06, plateau_patience=5, plateau_cooldown=3, min_learning_rate=1e-08) INFO:sleap.nn.training: Early stopping: EarlyStoppingConfig(stop_training_on_plateau=True, plateau_min_delta=1e-08, plateau_patience=20) INFO:sleap.nn.training:Setting up outputs... INFO:sleap.nn.callbacks:Training controller subscribed to: tcp://127.0.0.1:9000 (topic: ) INFO:sleap.nn.training: ZMQ controller subcribed to: tcp://127.0.0.1:9000 INFO:sleap.nn.callbacks:Progress reporter publishing on: tcp://127.0.0.1:9001 for: not_set INFO:sleap.nn.training: ZMQ progress reporter publish on: tcp://127.0.0.1:9001 INFO:sleap.nn.training:Created run path: C:/Windows/System32\models\250121_134227.centroid.n=864 INFO:sleap.nn.training:Setting up visualization... INFO:sleap.nn.training:Finished trainer set up. [5.9s] INFO:sleap.nn.training:Creating tf.data.Datasets for training data generation... 2025-01-21 13:43:41.008955: W tensorflow/core/framework/op_kernel.cc:1733] UNKNOWN: KeyError: dtype('float64') Traceback (most recent call last):
File "C:\Users\cviel\anaconda3\envs\sleap\lib\site-packages\tensorflow\python\ops\script_ops.py", line 273, in call return func(device, token, args)
File "C:\Users\cviel\anaconda3\envs\sleap\lib\site-packages\tensorflow\python\ops\script_ops.py", line 151, in call outputs = self._call(device, args)
File "C:\Users\cviel\anaconda3\envs\sleap\lib\site-packages\tensorflow\python\ops\script_ops.py", line 158, in _call ret = self._func(*args)
File "C:\Users\cviel\anaconda3\envs\sleap\lib\site-packages\tensorflow\python\autograph\impl\api.py", line 649, in wrapper return func(*args, **kwargs)
File "C:\Users\cviel\anaconda3\envs\sleap\lib\site-packages\sleap\nn\data\augmentation.py", line 240, in py_augment augmented = self.augmenter(image=img, keypoints=kps)
File "C:\Users\cviel\anaconda3\envs\sleap\lib\site-packages\albumentations\core\composition.py", line 210, in call data = t(**data)
File "C:\Users\cviel\anaconda3\envs\sleap\lib\site-packages\albumentations\core\transforms_interface.py", line 118, in call return self.apply_with_params(params, **kwargs)
File "C:\Users\cviel\anaconda3\envs\sleap\lib\site-packages\albumentations\core\transforms_interface.py", line 131, in apply_with_params res[key] = target_function(arg, **dict(params, **target_dependencies))
File "C:\Users\cviel\anaconda3\envs\sleap\lib\site-packages\albumentations\augmentations\transforms.py", line 1229, in apply return F.brightness_contrast_adjust(img, alpha, beta, self.brightness_by_max)
File "C:\Users\cviel\anaconda3\envs\sleap\lib\site-packages\albumentations\augmentations\functional.py", line 877, in brightness_contrast_adjust return _brightness_contrast_adjust_non_uint(img, alpha, beta, beta_by_max)
File "C:\Users\cviel\anaconda3\envs\sleap\lib\site-packages\albumentations\augmentations\utils.py", line 68, in wrapped_function return clip(func(img, *args, **kwargs), dtype, maxval)
File "C:\Users\cviel\anaconda3\envs\sleap\lib\site-packages\albumentations\augmentations\functional.py", line 845, in _brightness_contrast_adjust_non_uint max_value = MAX_VALUES_BY_DTYPE[dtype]
KeyError: dtype('float64')
Traceback (most recent call last):
File "C:\Users\cviel\anaconda3\envs\sleap\Scripts\sleap-train-script.py", line 33, in
File "C:\Users\cviel\anaconda3\envs\sleap\lib\site-packages\tensorflow\python\ops\script_ops.py", line 273, in call return func(device, token, args)
File "C:\Users\cviel\anaconda3\envs\sleap\lib\site-packages\tensorflow\python\ops\script_ops.py", line 151, in call outputs = self._call(device, args)
File "C:\Users\cviel\anaconda3\envs\sleap\lib\site-packages\tensorflow\python\ops\script_ops.py", line 158, in _call ret = self._func(*args)
File "C:\Users\cviel\anaconda3\envs\sleap\lib\site-packages\tensorflow\python\autograph\impl\api.py", line 649, in wrapper return func(*args, **kwargs)
File "C:\Users\cviel\anaconda3\envs\sleap\lib\site-packages\sleap\nn\data\augmentation.py", line 240, in py_augment augmented = self.augmenter(image=img, keypoints=kps)
File "C:\Users\cviel\anaconda3\envs\sleap\lib\site-packages\albumentations\core\composition.py", line 210, in call data = t(**data)
File "C:\Users\cviel\anaconda3\envs\sleap\lib\site-packages\albumentations\core\transforms_interface.py", line 118, in call return self.apply_with_params(params, **kwargs)
File "C:\Users\cviel\anaconda3\envs\sleap\lib\site-packages\albumentations\core\transforms_interface.py", line 131, in apply_with_params res[key] = target_function(arg, **dict(params, **target_dependencies))
File "C:\Users\cviel\anaconda3\envs\sleap\lib\site-packages\albumentations\augmentations\transforms.py", line 1229, in apply return F.brightness_contrast_adjust(img, alpha, beta, self.brightness_by_max)
File "C:\Users\cviel\anaconda3\envs\sleap\lib\site-packages\albumentations\augmentations\functional.py", line 877, in brightness_contrast_adjust return _brightness_contrast_adjust_non_uint(img, alpha, beta, beta_by_max)
File "C:\Users\cviel\anaconda3\envs\sleap\lib\site-packages\albumentations\augmentations\utils.py", line 68, in wrapped_function return clip(func(img, *args, **kwargs), dtype, maxval)
File "C:\Users\cviel\anaconda3\envs\sleap\lib\site-packages\albumentations\augmentations\functional.py", line 845, in _brightness_contrast_adjust_non_uint max_value = MAX_VALUES_BY_DTYPE[dtype]
KeyError: dtype('float64')
[[{{node EagerPyFunc}}]] [Op:IteratorGetNext]
INFO:sleap.nn.callbacks:Closing the reporter controller/context. INFO:sleap.nn.callbacks:Closing the training controller socket/context. Run Path: C:/Windows/System32\models\250121_134227.centroid.n=864
UPDATE: I was able to run my code again without encountering any bugs, by removing the 'brightness' augmentation. I guess it's because of the switch from imgaug to albumentations. Nevertheless, if anyone knows how I can put back this augmentation (very useful for the model), if possible via the GUI, I'm interested!
Thanks for the update @Elleiv! We'll look into what's going on with this bug, but I suspect it's a simple type casting issue.
Update 2: Apparently I'm having other problems with the update: I've run a short training session again with a model I'd already trained (no changes in the data, nor training parameters, apart from removing the brightness augmentation). Metrics are similar but the predictions are very poor (all the annotations are grouped and tightened around my anchor); this is a clear degradation compared with my model's performance before the update. I can't figure out why. As I'm only using the GUI at the moment, I doubt it's a typo error. So I'm going back to version 1.3.3 until I figure out what's going on.
We have released again since the pre-release: https://github.com/talmolab/sleap/releases/tag/v1.4.1.
If you upload your sleap package here, we can try to replicate your error.
Thanks,
Elizabeth