vq-pocket / evaluation.json
ARotting's picture
Publish VQ-VAE and conditional autoregressive visual-token prior
9dd581e verified
Raw
History Blame Contribute Delete
1.78 kB
{
"model": "VQ-Pocket",
"method": "VQ-VAE with a class-conditional autoregressive latent-token prior",
"autoencoder_parameters": 14193,
"prior_parameters": 28512,
"codebook_size": 32,
"tokens_per_image": 16,
"best_vq_epoch": 98,
"best_prior_epoch": 178,
"prior_training_nll": 0.7916229416096884,
"reconstruction": {
"pixel_mse": 0.006734587252140045,
"judge_accuracy": 0.9592592592592593,
"active_codes": 32,
"codebook_size": 32,
"codebook_perplexity": 22.71870231628418,
"examples": 270
},
"generation": {
"judge_accuracy": 0.9559999704360962,
"judge_accuracy_by_class": {
"0": 0.9800000190734863,
"1": 0.9700000286102295,
"2": 0.949999988079071,
"3": 0.9599999785423279,
"4": 0.9200000166893005,
"5": 0.9700000286102295,
"6": 0.9800000190734863,
"7": 0.9800000190734863,
"8": 0.9300000071525574,
"9": 0.9200000166893005
},
"mean_pixel_variance_by_class": {
"0": 0.021453002467751503,
"1": 0.05069272592663765,
"2": 0.038569375872612,
"3": 0.03150773420929909,
"4": 0.03649989888072014,
"5": 0.03785640373826027,
"6": 0.023341484367847443,
"7": 0.035609740763902664,
"8": 0.03689037263393402,
"9": 0.03489069640636444
},
"unique_code_sequence_fraction_by_class": {
"0": 0.99,
"1": 1.0,
"2": 1.0,
"3": 1.0,
"4": 1.0,
"5": 1.0,
"6": 0.98,
"7": 1.0,
"8": 0.99,
"9": 1.0
},
"mean_unique_code_sequence_fraction": 0.9960000000000001,
"samples": 1000,
"sampling_temperature": 0.85
},
"judge": "Frozen Tiny Vision student, 98.52% real-image test accuracy"
}