pose_mlp_v2 / pose_mlp_v2.json
ljchang's picture
Initial v2 release: 512-256-128 LayerNorm+GELU MLP distilled from img2pose on CelebV-HQ
2fa5435 verified
{
"architecture": {
"type": "PoseMLP",
"hidden": [
512,
256,
128
],
"dropout": 0.15,
"input_dim": 136,
"output_dim": 6,
"input_description": "68 (x, y) face landmarks normalized to face bbox [0,1]^2",
"output_description": "Pitch, Roll, Yaw (rad), X, Y, Z (units of img2pose template)",
"output_normalization": {
"mean": [
0.047110091894865036,
1.6245392531200054e-10,
-1.0606995282103071e-09,
-4.56669946302668e-09,
0.17980565130710602,
7.046011924743652
],
"std": [
0.19027948379516602,
0.3928057849407196,
0.17927488684654236,
0.5255976915359497,
0.40686145424842834,
2.5513007640838623
]
}
},
"training": {
"data": "/Storage/Projects/mp_blendshapes/data/bbox_pose/*_img2pose.csv (CelebV-HQ extraction)",
"n_clips": 35445,
"n_train_frames": 2783134,
"n_val_frames": 154619,
"face_score_threshold": 0.8,
"pose_clip_deg": 75.0,
"epochs": 40,
"batch_size": 1024,
"lr": 0.001,
"seed": 42
},
"best_val_loss": 0.0777415705746726,
"history": [
{
"epoch": 1,
"train": 0.11315019997803054,
"val": 0.104828848552547,
"pitch_mae_deg": 3.152665853500366,
"roll_mae_deg": 2.792881488800049,
"yaw_mae_deg": 2.13679838180542
},
{
"epoch": 2,
"train": 0.1065590488611336,
"val": 0.09961274236832794,
"pitch_mae_deg": 2.9992449283599854,
"roll_mae_deg": 2.6430251598358154,
"yaw_mae_deg": 1.9946171045303345
},
{
"epoch": 3,
"train": 0.10402416926071958,
"val": 0.09787551097963985,
"pitch_mae_deg": 2.9984378814697266,
"roll_mae_deg": 2.6911206245422363,
"yaw_mae_deg": 1.8750346899032593
},
{
"epoch": 4,
"train": 0.10253555926057764,
"val": 0.09612164048379973,
"pitch_mae_deg": 3.0127367973327637,
"roll_mae_deg": 2.6305713653564453,
"yaw_mae_deg": 1.8552767038345337
},
{
"epoch": 5,
"train": 0.10148297401859183,
"val": 0.09552087193649066,
"pitch_mae_deg": 2.9490880966186523,
"roll_mae_deg": 2.6785519123077393,
"yaw_mae_deg": 1.8824330568313599
},
{
"epoch": 6,
"train": 0.10051884218458308,
"val": 0.09247205514264734,
"pitch_mae_deg": 2.8985040187835693,
"roll_mae_deg": 2.477334976196289,
"yaw_mae_deg": 1.7141964435577393
},
{
"epoch": 7,
"train": 0.0995787868469493,
"val": 0.09395237100359641,
"pitch_mae_deg": 2.931995391845703,
"roll_mae_deg": 2.6331541538238525,
"yaw_mae_deg": 1.7413336038589478
},
{
"epoch": 8,
"train": 0.09886222485949048,
"val": 0.09294345720033896,
"pitch_mae_deg": 2.970853567123413,
"roll_mae_deg": 2.5920379161834717,
"yaw_mae_deg": 1.7464535236358643
},
{
"epoch": 9,
"train": 0.09830612088659829,
"val": 0.09182092106263888,
"pitch_mae_deg": 2.8500523567199707,
"roll_mae_deg": 2.511044502258301,
"yaw_mae_deg": 1.784227728843689
},
{
"epoch": 10,
"train": 0.09737222732988414,
"val": 0.09004505537450314,
"pitch_mae_deg": 2.873867988586426,
"roll_mae_deg": 2.472165107727051,
"yaw_mae_deg": 1.7860360145568848
},
{
"epoch": 11,
"train": 0.09690498495700607,
"val": 0.08976648708707408,
"pitch_mae_deg": 2.879437208175659,
"roll_mae_deg": 2.561363697052002,
"yaw_mae_deg": 1.6688872575759888
},
{
"epoch": 12,
"train": 0.09630656271153201,
"val": 0.08980230604739566,
"pitch_mae_deg": 2.838160514831543,
"roll_mae_deg": 2.4794445037841797,
"yaw_mae_deg": 1.7088587284088135
},
{
"epoch": 13,
"train": 0.09569354373427154,
"val": 0.08851547088277967,
"pitch_mae_deg": 2.856058120727539,
"roll_mae_deg": 2.5598247051239014,
"yaw_mae_deg": 1.7351120710372925
},
{
"epoch": 14,
"train": 0.09516716494366823,
"val": 0.08757703378796577,
"pitch_mae_deg": 2.800903558731079,
"roll_mae_deg": 2.4999215602874756,
"yaw_mae_deg": 1.7200062274932861
},
{
"epoch": 15,
"train": 0.09462323989595799,
"val": 0.08703844112000968,
"pitch_mae_deg": 2.810861110687256,
"roll_mae_deg": 2.425896167755127,
"yaw_mae_deg": 1.7037086486816406
},
{
"epoch": 16,
"train": 0.09410698983524984,
"val": 0.08680682148980468,
"pitch_mae_deg": 2.833448648452759,
"roll_mae_deg": 2.535163402557373,
"yaw_mae_deg": 1.7124162912368774
},
{
"epoch": 17,
"train": 0.09365605068138805,
"val": 0.08569933728952157,
"pitch_mae_deg": 2.8009047508239746,
"roll_mae_deg": 2.5543301105499268,
"yaw_mae_deg": 1.6394764184951782
},
{
"epoch": 18,
"train": 0.09323946791999124,
"val": 0.0869463943925343,
"pitch_mae_deg": 2.83258318901062,
"roll_mae_deg": 2.469459056854248,
"yaw_mae_deg": 1.6592215299606323
},
{
"epoch": 19,
"train": 0.09272424481134804,
"val": 0.0835315509650268,
"pitch_mae_deg": 2.7636806964874268,
"roll_mae_deg": 2.4162306785583496,
"yaw_mae_deg": 1.668568730354309
},
{
"epoch": 20,
"train": 0.09233342655512934,
"val": 0.08383207366262611,
"pitch_mae_deg": 2.770354747772217,
"roll_mae_deg": 2.4920639991760254,
"yaw_mae_deg": 1.6237024068832397
},
{
"epoch": 21,
"train": 0.09185766826731216,
"val": 0.08318848182496272,
"pitch_mae_deg": 2.7563376426696777,
"roll_mae_deg": 2.4593088626861572,
"yaw_mae_deg": 1.712731122970581
},
{
"epoch": 22,
"train": 0.09151670299443013,
"val": 0.08192426515252967,
"pitch_mae_deg": 2.74179744720459,
"roll_mae_deg": 2.418275833129883,
"yaw_mae_deg": 1.71445631980896
},
{
"epoch": 23,
"train": 0.09108457101112871,
"val": 0.0820473910946595,
"pitch_mae_deg": 2.7692880630493164,
"roll_mae_deg": 2.402466058731079,
"yaw_mae_deg": 1.641359806060791
},
{
"epoch": 24,
"train": 0.0906762100339506,
"val": 0.08174176327884197,
"pitch_mae_deg": 2.733238458633423,
"roll_mae_deg": 2.4820797443389893,
"yaw_mae_deg": 1.6439942121505737
},
{
"epoch": 25,
"train": 0.09034998959712985,
"val": 0.08133541057376485,
"pitch_mae_deg": 2.7302887439727783,
"roll_mae_deg": 2.4201176166534424,
"yaw_mae_deg": 1.6617894172668457
},
{
"epoch": 26,
"train": 0.09008330495711457,
"val": 0.08046494296898968,
"pitch_mae_deg": 2.7038564682006836,
"roll_mae_deg": 2.3806567192077637,
"yaw_mae_deg": 1.6689109802246094
},
{
"epoch": 27,
"train": 0.08978113147476037,
"val": 0.07989089151746348,
"pitch_mae_deg": 2.692418336868286,
"roll_mae_deg": 2.4487438201904297,
"yaw_mae_deg": 1.6251274347305298
},
{
"epoch": 28,
"train": 0.08945507099516169,
"val": 0.07935293018817902,
"pitch_mae_deg": 2.6850106716156006,
"roll_mae_deg": 2.3853209018707275,
"yaw_mae_deg": 1.5958898067474365
},
{
"epoch": 29,
"train": 0.0891421977581348,
"val": 0.07996009172577608,
"pitch_mae_deg": 2.693944215774536,
"roll_mae_deg": 2.375354528427124,
"yaw_mae_deg": 1.6029860973358154
},
{
"epoch": 30,
"train": 0.08896089701846822,
"val": 0.0793423713429978,
"pitch_mae_deg": 2.6876747608184814,
"roll_mae_deg": 2.370105743408203,
"yaw_mae_deg": 1.6090757846832275
},
{
"epoch": 31,
"train": 0.08868927482551209,
"val": 0.0788348114216014,
"pitch_mae_deg": 2.680671453475952,
"roll_mae_deg": 2.3722896575927734,
"yaw_mae_deg": 1.5897678136825562
},
{
"epoch": 32,
"train": 0.08841876725914989,
"val": 0.07828495494629208,
"pitch_mae_deg": 2.6755311489105225,
"roll_mae_deg": 2.3592045307159424,
"yaw_mae_deg": 1.5938224792480469
},
{
"epoch": 33,
"train": 0.08829338179738142,
"val": 0.07879007970424075,
"pitch_mae_deg": 2.672231674194336,
"roll_mae_deg": 2.3470544815063477,
"yaw_mae_deg": 1.583457112312317
},
{
"epoch": 34,
"train": 0.08804849298661294,
"val": 0.07809831976498428,
"pitch_mae_deg": 2.6717796325683594,
"roll_mae_deg": 2.345898151397705,
"yaw_mae_deg": 1.5844926834106445
},
{
"epoch": 35,
"train": 0.08788964650137973,
"val": 0.07806965493057903,
"pitch_mae_deg": 2.665562629699707,
"roll_mae_deg": 2.343658924102783,
"yaw_mae_deg": 1.5944466590881348
},
{
"epoch": 36,
"train": 0.08776004950435745,
"val": 0.07801351490381517,
"pitch_mae_deg": 2.6699180603027344,
"roll_mae_deg": 2.347235918045044,
"yaw_mae_deg": 1.588186502456665
},
{
"epoch": 37,
"train": 0.08765846724136074,
"val": 0.07789983218045611,
"pitch_mae_deg": 2.6638052463531494,
"roll_mae_deg": 2.3336102962493896,
"yaw_mae_deg": 1.5877548456192017
},
{
"epoch": 38,
"train": 0.08762438727969014,
"val": 0.0777415705746726,
"pitch_mae_deg": 2.659308433532715,
"roll_mae_deg": 2.336526393890381,
"yaw_mae_deg": 1.5783231258392334
},
{
"epoch": 39,
"train": 0.08753714936622983,
"val": 0.0779279994925386,
"pitch_mae_deg": 2.662292003631592,
"roll_mae_deg": 2.334559440612793,
"yaw_mae_deg": 1.5846630334854126
},
{
"epoch": 40,
"train": 0.08748793931207821,
"val": 0.07779885426555809,
"pitch_mae_deg": 2.6598613262176514,
"roll_mae_deg": 2.335223436355591,
"yaw_mae_deg": 1.578811764717102
}
]
}