tdpeuter/2025ML-project-neural_compression
tdpeuter/2025ML-project-neural_compression
Archived
1
Fork 0
Code Issues Pull requests Releases 1 Activity Actions

feat: measured autoencoder for very small files as well

Browse source
This commit is contained in:
RobinMeersman 2025-12-18 21:22:51 +01:00
parent 3bf3667849
commit cad44c3be4
3 changed files with 42 additions and 29 deletions
Download patch file Download diff file Expand all files Collapse all files

48
results/compress/compression_results.csv
View file

@ -1,25 +1,25 @@
model_type,model_name,context_length,dataset_type,input_file_name,original_file_size,compressed_file_size,mse_loss,compression_time,decompression_time
autoencoder,auto-genome-full-256.pt,256,genome,genome.fna,4699745,4259288,83.62875366210938,636915773,27887947
autoencoder,auto-genome-full-256.pt,256,genome,genome_large.fna,23498433,21295512,83.59369659423828,1932602305,7778175
autoencoder,auto-genome-full-256.pt,256,genome,genome_xlarge.fna,46996793,42591024,83.58621215820312,3850901316,10996509
autoencoder,auto-genome-full-128.pt,128,genome,genome.fna,4699745,9399552,83.01229095458984,390656081,5804539
autoencoder,auto-genome-full-128.pt,128,genome,genome_large.fna,23498433,46996992,83.01190185546875,1932561312,10575739
autoencoder,auto-genome-full-128.pt,128,genome,genome_xlarge.fna,46996793,93993728,83.00253295898438,3873777067,18670984
cnn,cnn-genome-full-256.pt,256,genome,genome_small.fna,1367,1743,0.0,1029290599,890595665
cnn,cnn-genome-full-256.pt,256,genome,genome_xsmall.fna,1043,1343,0.0,686878467,683701323
cnn,cnn-genome-full-256.pt,256,genome,genome_xxsmall.fna,800,1038,0.0,531354486,527072394
cnn,cnn-genome-full-128.pt,128,genome,genome_small.fna,1367,1682,0.0,829554150,851934528
cnn,cnn-genome-full-128.pt,128,genome,genome_xsmall.fna,1043,1300,0.0,654742547,637221301
cnn,cnn-genome-full-128.pt,128,genome,genome_xxsmall.fna,800,1006,0.0,483840337,488870786
autoencoder,auto-enwik9-full-256.pt,256,enwik9,text.txt,6488666,6184668,786.6799926757812,551986635,10536259
autoencoder,auto-enwik9-full-256.pt,256,enwik9,text_large.txt,12977332,12369092,786.6173706054688,1065897991,5763879
autoencoder,auto-enwik9-full-256.pt,256,enwik9,text_xlarge.txt,25954664,24738184,786.6337890625,2139223055,8369164
autoencoder,auto-enwik9-full-128.pt,128,enwik9,text.txt,6488666,12774636,206.2792510986328,545577194,20624030
autoencoder,auto-enwik9-full-128.pt,128,enwik9,text_large.txt,12977332,25549272,206.24131774902344,1073396133,60871642
autoencoder,auto-enwik9-full-128.pt,128,enwik9,text_xlarge.txt,25954664,51098292,206.33023071289062,2145601924,59481825
cnn,cnn-enwik9-full-256.pt,256,enwik9,text_small.txt,1022,1561,0.0,693378115,671294958
cnn,cnn-enwik9-full-256.pt,256,enwik9,text_xsmall.txt,825,1268,0.0,550333502,550062973
cnn,cnn-enwik9-full-256.pt,256,enwik9,text_xxsmall.txt,492,790,0.0,333745012,332073466
cnn,cnn-enwik9-full-128.pt,128,enwik9,text_small.txt,1022,1129,0.0,629310179,621317553
cnn,cnn-enwik9-full-128.pt,128,enwik9,text_xsmall.txt,825,882,0.0,504538600,504907940
cnn,cnn-enwik9-full-128.pt,128,enwik9,text_xxsmall.txt,492,571,0.0,305443187,308964670
autoencoder,auto-genome-full-256.pt,256,genome,genome.fna,4699745,4259288,83.62875366210938,806860910,45252425
autoencoder,auto-genome-full-256.pt,256,genome,genome_large.fna,23498433,21295512,83.59369659423828,2029608027,7888492
autoencoder,auto-genome-full-256.pt,256,genome,genome_xlarge.fna,46996793,42591024,83.58621215820312,3893661459,11828570
autoencoder,auto-genome-full-128.pt,128,genome,genome.fna,4699745,9399552,83.01229095458984,398403410,6667159
autoencoder,auto-genome-full-128.pt,128,genome,genome_large.fna,23498433,46996992,83.01190185546875,2039699733,18597914
autoencoder,auto-genome-full-128.pt,128,genome,genome_xlarge.fna,46996793,93993728,83.00253295898438,3914176203,19137168
cnn,cnn-genome-full-256.pt,256,genome,genome_small.fna,1367,1743,0.0,1066176734,933083718
cnn,cnn-genome-full-256.pt,256,genome,genome_xsmall.fna,1043,1343,0.0,741888902,796896774
cnn,cnn-genome-full-256.pt,256,genome,genome_xxsmall.fna,800,1038,0.0,542462371,712222705
cnn,cnn-genome-full-128.pt,128,genome,genome_small.fna,1367,1682,0.0,967421587,1046043100
cnn,cnn-genome-full-128.pt,128,genome,genome_xsmall.fna,1043,1300,0.0,632559455,629773982
cnn,cnn-genome-full-128.pt,128,genome,genome_xxsmall.fna,800,1006,0.0,481589710,488065247
autoencoder,auto-enwik9-full-256.pt,256,enwik9,text.txt,6488666,6184668,786.6799926757812,564278454,16857177
autoencoder,auto-enwik9-full-256.pt,256,enwik9,text_large.txt,12977332,12369092,786.6173706054688,1079811645,6431677
autoencoder,auto-enwik9-full-256.pt,256,enwik9,text_xlarge.txt,25954664,24738184,786.6337890625,2163648216,8789889
autoencoder,auto-enwik9-full-128.pt,128,enwik9,text.txt,6488666,12774636,206.2792510986328,559830918,20974298
autoencoder,auto-enwik9-full-128.pt,128,enwik9,text_large.txt,12977332,25549272,206.24131774902344,1166762858,62279675
autoencoder,auto-enwik9-full-128.pt,128,enwik9,text_xlarge.txt,25954664,51098292,206.33023071289062,2161884920,54375265
cnn,cnn-enwik9-full-256.pt,256,enwik9,text_small.txt,1022,1561,0.0,827390609,666215221
cnn,cnn-enwik9-full-256.pt,256,enwik9,text_xsmall.txt,825,1268,0.0,669703293,539488777
cnn,cnn-enwik9-full-256.pt,256,enwik9,text_xxsmall.txt,492,790,0.0,327867710,327564434
cnn,cnn-enwik9-full-128.pt,128,enwik9,text_small.txt,1022,1129,0.0,647518999,620040573
cnn,cnn-enwik9-full-128.pt,128,enwik9,text_xsmall.txt,825,882,0.0,500985855,613062076
cnn,cnn-enwik9-full-128.pt,128,enwik9,text_xxsmall.txt,492,571,0.0,302816347,308070825

1 model_type model_name context_length dataset_type input_file_name original_file_size compressed_file_size mse_loss compression_time decompression_time
2 autoencoder auto-genome-full-256.pt 256 genome genome.fna 4699745 4259288 83.62875366210938 636915773 806860910 27887947 45252425
3 autoencoder auto-genome-full-256.pt 256 genome genome_large.fna 23498433 21295512 83.59369659423828 1932602305 2029608027 7778175 7888492
4 autoencoder auto-genome-full-256.pt 256 genome genome_xlarge.fna 46996793 42591024 83.58621215820312 3850901316 3893661459 10996509 11828570
5 autoencoder auto-genome-full-128.pt 128 genome genome.fna 4699745 9399552 83.01229095458984 390656081 398403410 5804539 6667159
6 autoencoder auto-genome-full-128.pt 128 genome genome_large.fna 23498433 46996992 83.01190185546875 1932561312 2039699733 10575739 18597914
7 autoencoder auto-genome-full-128.pt 128 genome genome_xlarge.fna 46996793 93993728 83.00253295898438 3873777067 3914176203 18670984 19137168
8 cnn cnn-genome-full-256.pt 256 genome genome_small.fna 1367 1743 0.0 1029290599 1066176734 890595665 933083718
9 cnn cnn-genome-full-256.pt 256 genome genome_xsmall.fna 1043 1343 0.0 686878467 741888902 683701323 796896774
10 cnn cnn-genome-full-256.pt 256 genome genome_xxsmall.fna 800 1038 0.0 531354486 542462371 527072394 712222705
11 cnn cnn-genome-full-128.pt 128 genome genome_small.fna 1367 1682 0.0 829554150 967421587 851934528 1046043100
12 cnn cnn-genome-full-128.pt 128 genome genome_xsmall.fna 1043 1300 0.0 654742547 632559455 637221301 629773982
13 cnn cnn-genome-full-128.pt 128 genome genome_xxsmall.fna 800 1006 0.0 483840337 481589710 488870786 488065247
14 autoencoder auto-enwik9-full-256.pt 256 enwik9 text.txt 6488666 6184668 786.6799926757812 551986635 564278454 10536259 16857177
15 autoencoder auto-enwik9-full-256.pt 256 enwik9 text_large.txt 12977332 12369092 786.6173706054688 1065897991 1079811645 5763879 6431677
16 autoencoder auto-enwik9-full-256.pt 256 enwik9 text_xlarge.txt 25954664 24738184 786.6337890625 2139223055 2163648216 8369164 8789889
17 autoencoder auto-enwik9-full-128.pt 128 enwik9 text.txt 6488666 12774636 206.2792510986328 545577194 559830918 20624030 20974298
18 autoencoder auto-enwik9-full-128.pt 128 enwik9 text_large.txt 12977332 25549272 206.24131774902344 1073396133 1166762858 60871642 62279675
19 autoencoder auto-enwik9-full-128.pt 128 enwik9 text_xlarge.txt 25954664 51098292 206.33023071289062 2145601924 2161884920 59481825 54375265
20 cnn cnn-enwik9-full-256.pt 256 enwik9 text_small.txt 1022 1561 0.0 693378115 827390609 671294958 666215221
21 cnn cnn-enwik9-full-256.pt 256 enwik9 text_xsmall.txt 825 1268 0.0 550333502 669703293 550062973 539488777
22 cnn cnn-enwik9-full-256.pt 256 enwik9 text_xxsmall.txt 492 790 0.0 333745012 327867710 332073466 327564434
23 cnn cnn-enwik9-full-128.pt 128 enwik9 text_small.txt 1022 1129 0.0 629310179 647518999 621317553 620040573
24 cnn cnn-enwik9-full-128.pt 128 enwik9 text_xsmall.txt 825 882 0.0 504538600 500985855 504907940 613062076
25 cnn cnn-enwik9-full-128.pt 128 enwik9 text_xxsmall.txt 492 571 0.0 305443187 302816347 308964670 308070825

13
results/compress/compression_results_auto_small.csv Normal file
View file

@ -0,0 +1,13 @@
model_type,model_name,context_length,dataset_type,input_file_name,original_file_size,compressed_file_size,mse_loss,compression_time,decompression_time
autoencoder,auto-genome-full-256.pt,256,genome,genome_small.fna,1367,1392,220.29188537597656,237708436,29378622
autoencoder,auto-genome-full-256.pt,256,genome,genome_xsmall.fna,1043,1160,263.97027587890625,5293080,4488761
autoencoder,auto-genome-full-256.pt,256,genome,genome_xxsmall.fna,800,928,319.5350036621094,4873340,4381310
autoencoder,auto-genome-full-128.pt,128,genome,genome_small.fna,1367,2816,120.52304077148438,251659317,5284661
autoencoder,auto-genome-full-128.pt,128,genome,genome_xsmall.fna,1043,2304,133.8379669189453,152590538,4432469
autoencoder,auto-genome-full-128.pt,128,genome,genome_xxsmall.fna,800,1792,159.2862548828125,153622653,4532139
autoencoder,auto-enwik9-full-256.pt,256,enwik9,text_small.txt,1022,976,746.8033447265625,6699780,22065927
autoencoder,auto-enwik9-full-256.pt,256,enwik9,text_xsmall.txt,825,976,787.5345458984375,3715750,3665629
autoencoder,auto-enwik9-full-256.pt,256,enwik9,text_xxsmall.txt,492,488,828.8658447265625,4892560,4176979
autoencoder,auto-enwik9-full-128.pt,128,enwik9,text_small.txt,1022,2016,231.42955017089844,5005880,4400159
autoencoder,auto-enwik9-full-128.pt,128,enwik9,text_xsmall.txt,825,1764,236.55636596679688,5024449,4180100
autoencoder,auto-enwik9-full-128.pt,128,enwik9,text_xxsmall.txt,492,1008,237.20529174804688,4856779,4145850
1 model_type model_name context_length dataset_type input_file_name original_file_size compressed_file_size mse_loss compression_time decompression_time
2 autoencoder auto-genome-full-256.pt 256 genome genome_small.fna 1367 1392 220.29188537597656 237708436 29378622
3 autoencoder auto-genome-full-256.pt 256 genome genome_xsmall.fna 1043 1160 263.97027587890625 5293080 4488761
4 autoencoder auto-genome-full-256.pt 256 genome genome_xxsmall.fna 800 928 319.5350036621094 4873340 4381310
5 autoencoder auto-genome-full-128.pt 128 genome genome_small.fna 1367 2816 120.52304077148438 251659317 5284661
6 autoencoder auto-genome-full-128.pt 128 genome genome_xsmall.fna 1043 2304 133.8379669189453 152590538 4432469
7 autoencoder auto-genome-full-128.pt 128 genome genome_xxsmall.fna 800 1792 159.2862548828125 153622653 4532139
8 autoencoder auto-enwik9-full-256.pt 256 enwik9 text_small.txt 1022 976 746.8033447265625 6699780 22065927
9 autoencoder auto-enwik9-full-256.pt 256 enwik9 text_xsmall.txt 825 976 787.5345458984375 3715750 3665629
10 autoencoder auto-enwik9-full-256.pt 256 enwik9 text_xxsmall.txt 492 488 828.8658447265625 4892560 4176979
11 autoencoder auto-enwik9-full-128.pt 128 enwik9 text_small.txt 1022 2016 231.42955017089844 5005880 4400159
12 autoencoder auto-enwik9-full-128.pt 128 enwik9 text_xsmall.txt 825 1764 236.55636596679688 5024449 4180100
13 autoencoder auto-enwik9-full-128.pt 128 enwik9 text_xxsmall.txt 492 1008 237.20529174804688 4856779 4145850