File size: 4,550 Bytes
ddedd58 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 | {
"architectures": ["Visual_Cortex_Amygdala"],
"model_type": "visual-valence-model",
"task": "image-valence-regression",
"source_repo": "https://github.com/lab-smile/FearConditioningAI",
"source_module": "models.VGG_Model",
"paper": "https://arxiv.org/abs/2607.19327",
"backbone": {
"name": "vgg16",
"pretrained_on": "imagenet-1k",
"batch_norm": false,
"frozen": true
},
"shortcut_pathway": {
"name": "middleroad",
"source_vgg_layer_index": 10,
"pooling": {
"middleroad_maxpool": {"kernel_size": 29, "stride": 14},
"global_maxpool_output_size": 2,
"maxpool1": {"kernel_size": 5, "stride": 3},
"maxpool2": {"kernel_size": 9, "stride": 5},
"maxpool3": {"kernel_size": 13, "stride": 7},
"adaptive_avgpool_output_sizes": [1, 2]
},
"attention": {
"type": "efficient_channel_attention",
"reference": "https://doi.org/10.1109/CVPR42600.2020.01155",
"conv1d_kernel_size": 3
},
"fc_layers": {
"input_size": 1024,
"hidden_sizes": [1024, 512],
"dropout": 0.5
}
},
"valence_module": {
"name": "VCA_FC",
"input_size": 4608,
"input_composition": {"highroad_features": 4096, "middleroad_features": 512},
"hidden_sizes": [1024, 1024],
"dropout": 0.5,
"output_size": 1,
"output_activation": "sigmoid",
"output_rescale_range": [1, 9],
"output_semantics": "valence rating (1 = extreme displeasure, 9 = extreme pleasure)"
},
"input": {
"image_size": 224,
"channels": 3,
"normalize_mean": [0.485, 0.456, 0.406],
"normalize_std": [0.229, 0.224, 0.225]
},
"checkpoints": {
"stage0_videoframe_pretrain": {
"filename": "vca_ckvideo_batch128_lr2e-5_epoch20.pth",
"stage": "Stage 0 (trained from scratch on Videoframe)",
"trained_on": ["Cowen & Keltner (2017) Videoframe"],
"input_layout": "full-frame (no quadrant cropping)",
"val_pearson_r": 0.386,
"val_mse": 0.043
},
"stage1_iaps_finetune": {
"filename": "vca_IAPS_batch10_lr2e-4_epoch23.pth",
"stage": "Stage 1 (fine-tuned on full-size IAPS)",
"trained_on": ["Cowen & Keltner (2017) Videoframe", "IAPS full-size"],
"input_layout": "full-frame (no quadrant cropping)",
"val_pearson_r": 0.538,
"val_mse": 0.192
},
"pre_conditioning": {
"filename": "base_model_vca_IAPS_quadrant.pth",
"stage": "Stage 2 (quadrant fine-tuning), before Pavlovian conditioning",
"trained_on": ["Cowen & Keltner (2017) Videoframe", "IAPS full-size", "IAPS quadrant-cropped"],
"input_layout": "quadrant-cropped (US in quadrant 4)",
"val_pearson_r": null,
"val_mse": null,
"note": "See paper for definitive evaluation numbers."
},
"post_conditioning_epoch1": {
"filename": "base_model_conditioned_orientation_epoch1.pth",
"stage": "Stage 3 (Pavlovian conditioning), epoch 1 of 100",
"trained_on": ["Cowen & Keltner (2017) Videoframe", "IAPS full-size", "IAPS quadrant-cropped", "IAPS Conditioning (US) x Gabor patch (CS)"],
"input_layout": "quadrant-cropped (CS in quadrant 2, US in quadrant 4)",
"val_pearson_r": 0.660,
"val_mse": 0.466,
"note": "Early/under-trained snapshot, kept for provenance; not representative of the final model."
},
"post_conditioning": {
"filename": "base_model_conditioned_orientation_epoch100.pth",
"stage": "Stage 3 (Pavlovian conditioning), epoch 100 (final, used in the paper)",
"trained_on": ["Cowen & Keltner (2017) Videoframe", "IAPS full-size", "IAPS quadrant-cropped", "IAPS Conditioning (US) x Gabor patch (CS)"],
"input_layout": "quadrant-cropped (CS in quadrant 2, US in quadrant 4)",
"val_pearson_r": null,
"val_mse": null,
"note": "See paper for definitive evaluation numbers.",
"conditioning_paradigm": {
"cs_stimulus": "Gabor patch (45 deg or 135 deg orientation)",
"us_stimulus": "IAPS image (unpleasant paired with 45 deg CS, pleasant paired with 135 deg CS)",
"cs_quadrant": 2,
"us_quadrant": 4
}
}
},
"checkpoint_format": {
"type": "torch.save dict",
"keys": ["model", "epoch", "best_per", "best_loss", "state_dict", "optimizer"],
"state_dict_key": "state_dict",
"note": "Load with model.load_state_dict(checkpoint['state_dict'], strict=False); the 'model' key is a pickled model object retained for reproducibility but should not be trusted/unpickled directly."
},
"license": "mit"
}
|