fix byte count with float * 4

This commit is contained in:
colin 2020-07-20 16:00:32 +08:00
parent 3d062150e9
commit 039310704e
2 changed files with 268 additions and 449 deletions

View File

@ -1,257 +1,257 @@
int RN50_conv1_weight[]={0,9407,}; int RN50_conv1_weight[]={0,37631,};
int RN50_bn1_running_mean[]={9408,9471,}; int RN50_bn1_running_mean[]={37632,37887,};
int RN50_bn1_running_var[]={9472,9535,}; int RN50_bn1_running_var[]={37888,38143,};
int RN50_bn1_weight[]={9536,9599,}; int RN50_bn1_weight[]={38144,38399,};
int RN50_bn1_bias[]={9600,9663,}; int RN50_bn1_bias[]={38400,38655,};
int RN50_layer1__modules_0_conv1_weight[]={9664,13759,}; int RN50_layer1__modules_0_conv1_weight[]={38656,55039,};
int RN50_layer1__modules_0_bn1_running_mean[]={13760,13823,}; int RN50_layer1__modules_0_bn1_running_mean[]={55040,55295,};
int RN50_layer1__modules_0_bn1_running_var[]={13824,13887,}; int RN50_layer1__modules_0_bn1_running_var[]={55296,55551,};
int RN50_layer1__modules_0_bn1_weight[]={13888,13951,}; int RN50_layer1__modules_0_bn1_weight[]={55552,55807,};
int RN50_layer1__modules_0_bn1_bias[]={13952,14015,}; int RN50_layer1__modules_0_bn1_bias[]={55808,56063,};
int RN50_layer1__modules_0_conv2_weight[]={14016,50879,}; int RN50_layer1__modules_0_conv2_weight[]={56064,203519,};
int RN50_layer1__modules_0_bn2_running_mean[]={50880,50943,}; int RN50_layer1__modules_0_bn2_running_mean[]={203520,203775,};
int RN50_layer1__modules_0_bn2_running_var[]={50944,51007,}; int RN50_layer1__modules_0_bn2_running_var[]={203776,204031,};
int RN50_layer1__modules_0_bn2_weight[]={51008,51071,}; int RN50_layer1__modules_0_bn2_weight[]={204032,204287,};
int RN50_layer1__modules_0_bn2_bias[]={51072,51135,}; int RN50_layer1__modules_0_bn2_bias[]={204288,204543,};
int RN50_layer1__modules_0_conv3_weight[]={51136,67519,}; int RN50_layer1__modules_0_conv3_weight[]={204544,270079,};
int RN50_layer1__modules_0_bn3_running_mean[]={67520,67775,}; int RN50_layer1__modules_0_bn3_running_mean[]={270080,271103,};
int RN50_layer1__modules_0_bn3_running_var[]={67776,68031,}; int RN50_layer1__modules_0_bn3_running_var[]={271104,272127,};
int RN50_layer1__modules_0_bn3_weight[]={68032,68287,}; int RN50_layer1__modules_0_bn3_weight[]={272128,273151,};
int RN50_layer1__modules_0_bn3_bias[]={68288,68543,}; int RN50_layer1__modules_0_bn3_bias[]={273152,274175,};
int RN50_layer1__modules_0_downsample__modules_0_weight[]={68544,84927,}; int RN50_layer1__modules_0_downsample__modules_0_weight[]={274176,339711,};
int RN50_layer1__modules_0_downsample__modules_1_running_mean[]={84928,85183,}; int RN50_layer1__modules_0_downsample__modules_1_running_mean[]={339712,340735,};
int RN50_layer1__modules_0_downsample__modules_1_running_var[]={85184,85439,}; int RN50_layer1__modules_0_downsample__modules_1_running_var[]={340736,341759,};
int RN50_layer1__modules_0_downsample__modules_1_weight[]={85440,85695,}; int RN50_layer1__modules_0_downsample__modules_1_weight[]={341760,342783,};
int RN50_layer1__modules_0_downsample__modules_1_bias[]={85696,85951,}; int RN50_layer1__modules_0_downsample__modules_1_bias[]={342784,343807,};
int RN50_layer2__modules_0_conv1_weight[]={85952,118719,}; int RN50_layer2__modules_0_conv1_weight[]={343808,474879,};
int RN50_layer2__modules_0_bn1_running_mean[]={118720,118847,}; int RN50_layer2__modules_0_bn1_running_mean[]={474880,475391,};
int RN50_layer2__modules_0_bn1_running_var[]={118848,118975,}; int RN50_layer2__modules_0_bn1_running_var[]={475392,475903,};
int RN50_layer2__modules_0_bn1_weight[]={118976,119103,}; int RN50_layer2__modules_0_bn1_weight[]={475904,476415,};
int RN50_layer2__modules_0_bn1_bias[]={119104,119231,}; int RN50_layer2__modules_0_bn1_bias[]={476416,476927,};
int RN50_layer2__modules_0_conv2_weight[]={119232,266687,}; int RN50_layer2__modules_0_conv2_weight[]={476928,1066751,};
int RN50_layer2__modules_0_bn2_running_mean[]={266688,266815,}; int RN50_layer2__modules_0_bn2_running_mean[]={1066752,1067263,};
int RN50_layer2__modules_0_bn2_running_var[]={266816,266943,}; int RN50_layer2__modules_0_bn2_running_var[]={1067264,1067775,};
int RN50_layer2__modules_0_bn2_weight[]={266944,267071,}; int RN50_layer2__modules_0_bn2_weight[]={1067776,1068287,};
int RN50_layer2__modules_0_bn2_bias[]={267072,267199,}; int RN50_layer2__modules_0_bn2_bias[]={1068288,1068799,};
int RN50_layer2__modules_0_conv3_weight[]={267200,332735,}; int RN50_layer2__modules_0_conv3_weight[]={1068800,1330943,};
int RN50_layer2__modules_0_bn3_running_mean[]={332736,333247,}; int RN50_layer2__modules_0_bn3_running_mean[]={1330944,1332991,};
int RN50_layer2__modules_0_bn3_running_var[]={333248,333759,}; int RN50_layer2__modules_0_bn3_running_var[]={1332992,1335039,};
int RN50_layer2__modules_0_bn3_weight[]={333760,334271,}; int RN50_layer2__modules_0_bn3_weight[]={1335040,1337087,};
int RN50_layer2__modules_0_bn3_bias[]={334272,334783,}; int RN50_layer2__modules_0_bn3_bias[]={1337088,1339135,};
int RN50_layer2__modules_0_downsample__modules_0_weight[]={334784,465855,}; int RN50_layer2__modules_0_downsample__modules_0_weight[]={1339136,1863423,};
int RN50_layer2__modules_0_downsample__modules_1_running_mean[]={465856,466367,}; int RN50_layer2__modules_0_downsample__modules_1_running_mean[]={1863424,1865471,};
int RN50_layer2__modules_0_downsample__modules_1_running_var[]={466368,466879,}; int RN50_layer2__modules_0_downsample__modules_1_running_var[]={1865472,1867519,};
int RN50_layer2__modules_0_downsample__modules_1_weight[]={466880,467391,}; int RN50_layer2__modules_0_downsample__modules_1_weight[]={1867520,1869567,};
int RN50_layer2__modules_0_downsample__modules_1_bias[]={467392,467903,}; int RN50_layer2__modules_0_downsample__modules_1_bias[]={1869568,1871615,};
int RN50_layer2__modules_1_conv1_weight[]={467904,533439,}; int RN50_layer2__modules_1_conv1_weight[]={1871616,2133759,};
int RN50_layer2__modules_1_bn1_running_mean[]={533440,533567,}; int RN50_layer2__modules_1_bn1_running_mean[]={2133760,2134271,};
int RN50_layer2__modules_1_bn1_running_var[]={533568,533695,}; int RN50_layer2__modules_1_bn1_running_var[]={2134272,2134783,};
int RN50_layer2__modules_1_bn1_weight[]={533696,533823,}; int RN50_layer2__modules_1_bn1_weight[]={2134784,2135295,};
int RN50_layer2__modules_1_bn1_bias[]={533824,533951,}; int RN50_layer2__modules_1_bn1_bias[]={2135296,2135807,};
int RN50_layer2__modules_1_conv2_weight[]={533952,681407,}; int RN50_layer2__modules_1_conv2_weight[]={2135808,2725631,};
int RN50_layer2__modules_1_bn2_running_mean[]={681408,681535,}; int RN50_layer2__modules_1_bn2_running_mean[]={2725632,2726143,};
int RN50_layer2__modules_1_bn2_running_var[]={681536,681663,}; int RN50_layer2__modules_1_bn2_running_var[]={2726144,2726655,};
int RN50_layer2__modules_1_bn2_weight[]={681664,681791,}; int RN50_layer2__modules_1_bn2_weight[]={2726656,2727167,};
int RN50_layer2__modules_1_bn2_bias[]={681792,681919,}; int RN50_layer2__modules_1_bn2_bias[]={2727168,2727679,};
int RN50_layer2__modules_1_conv3_weight[]={681920,747455,}; int RN50_layer2__modules_1_conv3_weight[]={2727680,2989823,};
int RN50_layer2__modules_1_bn3_running_mean[]={747456,747967,}; int RN50_layer2__modules_1_bn3_running_mean[]={2989824,2991871,};
int RN50_layer2__modules_1_bn3_running_var[]={747968,748479,}; int RN50_layer2__modules_1_bn3_running_var[]={2991872,2993919,};
int RN50_layer2__modules_1_bn3_weight[]={748480,748991,}; int RN50_layer2__modules_1_bn3_weight[]={2993920,2995967,};
int RN50_layer2__modules_1_bn3_bias[]={748992,749503,}; int RN50_layer2__modules_1_bn3_bias[]={2995968,2998015,};
int RN50_layer2__modules_2_conv1_weight[]={749504,815039,}; int RN50_layer2__modules_2_conv1_weight[]={2998016,3260159,};
int RN50_layer2__modules_2_bn1_running_mean[]={815040,815167,}; int RN50_layer2__modules_2_bn1_running_mean[]={3260160,3260671,};
int RN50_layer2__modules_2_bn1_running_var[]={815168,815295,}; int RN50_layer2__modules_2_bn1_running_var[]={3260672,3261183,};
int RN50_layer2__modules_2_bn1_weight[]={815296,815423,}; int RN50_layer2__modules_2_bn1_weight[]={3261184,3261695,};
int RN50_layer2__modules_2_bn1_bias[]={815424,815551,}; int RN50_layer2__modules_2_bn1_bias[]={3261696,3262207,};
int RN50_layer2__modules_2_conv2_weight[]={815552,963007,}; int RN50_layer2__modules_2_conv2_weight[]={3262208,3852031,};
int RN50_layer2__modules_2_bn2_running_mean[]={963008,963135,}; int RN50_layer2__modules_2_bn2_running_mean[]={3852032,3852543,};
int RN50_layer2__modules_2_bn2_running_var[]={963136,963263,}; int RN50_layer2__modules_2_bn2_running_var[]={3852544,3853055,};
int RN50_layer2__modules_2_bn2_weight[]={963264,963391,}; int RN50_layer2__modules_2_bn2_weight[]={3853056,3853567,};
int RN50_layer2__modules_2_bn2_bias[]={963392,963519,}; int RN50_layer2__modules_2_bn2_bias[]={3853568,3854079,};
int RN50_layer2__modules_2_conv3_weight[]={963520,1029055,}; int RN50_layer2__modules_2_conv3_weight[]={3854080,4116223,};
int RN50_layer2__modules_2_bn3_running_mean[]={1029056,1029567,}; int RN50_layer2__modules_2_bn3_running_mean[]={4116224,4118271,};
int RN50_layer2__modules_2_bn3_running_var[]={1029568,1030079,}; int RN50_layer2__modules_2_bn3_running_var[]={4118272,4120319,};
int RN50_layer2__modules_2_bn3_weight[]={1030080,1030591,}; int RN50_layer2__modules_2_bn3_weight[]={4120320,4122367,};
int RN50_layer2__modules_2_bn3_bias[]={1030592,1031103,}; int RN50_layer2__modules_2_bn3_bias[]={4122368,4124415,};
int RN50_layer2__modules_3_conv1_weight[]={1031104,1096639,}; int RN50_layer2__modules_3_conv1_weight[]={4124416,4386559,};
int RN50_layer2__modules_3_bn1_running_mean[]={1096640,1096767,}; int RN50_layer2__modules_3_bn1_running_mean[]={4386560,4387071,};
int RN50_layer2__modules_3_bn1_running_var[]={1096768,1096895,}; int RN50_layer2__modules_3_bn1_running_var[]={4387072,4387583,};
int RN50_layer2__modules_3_bn1_weight[]={1096896,1097023,}; int RN50_layer2__modules_3_bn1_weight[]={4387584,4388095,};
int RN50_layer2__modules_3_bn1_bias[]={1097024,1097151,}; int RN50_layer2__modules_3_bn1_bias[]={4388096,4388607,};
int RN50_layer2__modules_3_conv2_weight[]={1097152,1244607,}; int RN50_layer2__modules_3_conv2_weight[]={4388608,4978431,};
int RN50_layer2__modules_3_bn2_running_mean[]={1244608,1244735,}; int RN50_layer2__modules_3_bn2_running_mean[]={4978432,4978943,};
int RN50_layer2__modules_3_bn2_running_var[]={1244736,1244863,}; int RN50_layer2__modules_3_bn2_running_var[]={4978944,4979455,};
int RN50_layer2__modules_3_bn2_weight[]={1244864,1244991,}; int RN50_layer2__modules_3_bn2_weight[]={4979456,4979967,};
int RN50_layer2__modules_3_bn2_bias[]={1244992,1245119,}; int RN50_layer2__modules_3_bn2_bias[]={4979968,4980479,};
int RN50_layer2__modules_3_conv3_weight[]={1245120,1310655,}; int RN50_layer2__modules_3_conv3_weight[]={4980480,5242623,};
int RN50_layer2__modules_3_bn3_running_mean[]={1310656,1311167,}; int RN50_layer2__modules_3_bn3_running_mean[]={5242624,5244671,};
int RN50_layer2__modules_3_bn3_running_var[]={1311168,1311679,}; int RN50_layer2__modules_3_bn3_running_var[]={5244672,5246719,};
int RN50_layer2__modules_3_bn3_weight[]={1311680,1312191,}; int RN50_layer2__modules_3_bn3_weight[]={5246720,5248767,};
int RN50_layer2__modules_3_bn3_bias[]={1312192,1312703,}; int RN50_layer2__modules_3_bn3_bias[]={5248768,5250815,};
int RN50_layer3__modules_0_conv1_weight[]={1312704,1443775,}; int RN50_layer3__modules_0_conv1_weight[]={5250816,5775103,};
int RN50_layer3__modules_0_bn1_running_mean[]={1443776,1444031,}; int RN50_layer3__modules_0_bn1_running_mean[]={5775104,5776127,};
int RN50_layer3__modules_0_bn1_running_var[]={1444032,1444287,}; int RN50_layer3__modules_0_bn1_running_var[]={5776128,5777151,};
int RN50_layer3__modules_0_bn1_weight[]={1444288,1444543,}; int RN50_layer3__modules_0_bn1_weight[]={5777152,5778175,};
int RN50_layer3__modules_0_bn1_bias[]={1444544,1444799,}; int RN50_layer3__modules_0_bn1_bias[]={5778176,5779199,};
int RN50_layer3__modules_0_conv2_weight[]={1444800,2034623,}; int RN50_layer3__modules_0_conv2_weight[]={5779200,8138495,};
int RN50_layer3__modules_0_bn2_running_mean[]={2034624,2034879,}; int RN50_layer3__modules_0_bn2_running_mean[]={8138496,8139519,};
int RN50_layer3__modules_0_bn2_running_var[]={2034880,2035135,}; int RN50_layer3__modules_0_bn2_running_var[]={8139520,8140543,};
int RN50_layer3__modules_0_bn2_weight[]={2035136,2035391,}; int RN50_layer3__modules_0_bn2_weight[]={8140544,8141567,};
int RN50_layer3__modules_0_bn2_bias[]={2035392,2035647,}; int RN50_layer3__modules_0_bn2_bias[]={8141568,8142591,};
int RN50_layer3__modules_0_conv3_weight[]={2035648,2297791,}; int RN50_layer3__modules_0_conv3_weight[]={8142592,9191167,};
int RN50_layer3__modules_0_bn3_running_mean[]={2297792,2298815,}; int RN50_layer3__modules_0_bn3_running_mean[]={9191168,9195263,};
int RN50_layer3__modules_0_bn3_running_var[]={2298816,2299839,}; int RN50_layer3__modules_0_bn3_running_var[]={9195264,9199359,};
int RN50_layer3__modules_0_bn3_weight[]={2299840,2300863,}; int RN50_layer3__modules_0_bn3_weight[]={9199360,9203455,};
int RN50_layer3__modules_0_bn3_bias[]={2300864,2301887,}; int RN50_layer3__modules_0_bn3_bias[]={9203456,9207551,};
int RN50_layer3__modules_0_downsample__modules_0_weight[]={2301888,2826175,}; int RN50_layer3__modules_0_downsample__modules_0_weight[]={9207552,11304703,};
int RN50_layer3__modules_0_downsample__modules_1_running_mean[]={2826176,2827199,}; int RN50_layer3__modules_0_downsample__modules_1_running_mean[]={11304704,11308799,};
int RN50_layer3__modules_0_downsample__modules_1_running_var[]={2827200,2828223,}; int RN50_layer3__modules_0_downsample__modules_1_running_var[]={11308800,11312895,};
int RN50_layer3__modules_0_downsample__modules_1_weight[]={2828224,2829247,}; int RN50_layer3__modules_0_downsample__modules_1_weight[]={11312896,11316991,};
int RN50_layer3__modules_0_downsample__modules_1_bias[]={2829248,2830271,}; int RN50_layer3__modules_0_downsample__modules_1_bias[]={11316992,11321087,};
int RN50_layer3__modules_1_conv1_weight[]={2830272,3092415,}; int RN50_layer3__modules_1_conv1_weight[]={11321088,12369663,};
int RN50_layer3__modules_1_bn1_running_mean[]={3092416,3092671,}; int RN50_layer3__modules_1_bn1_running_mean[]={12369664,12370687,};
int RN50_layer3__modules_1_bn1_running_var[]={3092672,3092927,}; int RN50_layer3__modules_1_bn1_running_var[]={12370688,12371711,};
int RN50_layer3__modules_1_bn1_weight[]={3092928,3093183,}; int RN50_layer3__modules_1_bn1_weight[]={12371712,12372735,};
int RN50_layer3__modules_1_bn1_bias[]={3093184,3093439,}; int RN50_layer3__modules_1_bn1_bias[]={12372736,12373759,};
int RN50_layer3__modules_1_conv2_weight[]={3093440,3683263,}; int RN50_layer3__modules_1_conv2_weight[]={12373760,14733055,};
int RN50_layer3__modules_1_bn2_running_mean[]={3683264,3683519,}; int RN50_layer3__modules_1_bn2_running_mean[]={14733056,14734079,};
int RN50_layer3__modules_1_bn2_running_var[]={3683520,3683775,}; int RN50_layer3__modules_1_bn2_running_var[]={14734080,14735103,};
int RN50_layer3__modules_1_bn2_weight[]={3683776,3684031,}; int RN50_layer3__modules_1_bn2_weight[]={14735104,14736127,};
int RN50_layer3__modules_1_bn2_bias[]={3684032,3684287,}; int RN50_layer3__modules_1_bn2_bias[]={14736128,14737151,};
int RN50_layer3__modules_1_conv3_weight[]={3684288,3946431,}; int RN50_layer3__modules_1_conv3_weight[]={14737152,15785727,};
int RN50_layer3__modules_1_bn3_running_mean[]={3946432,3947455,}; int RN50_layer3__modules_1_bn3_running_mean[]={15785728,15789823,};
int RN50_layer3__modules_1_bn3_running_var[]={3947456,3948479,}; int RN50_layer3__modules_1_bn3_running_var[]={15789824,15793919,};
int RN50_layer3__modules_1_bn3_weight[]={3948480,3949503,}; int RN50_layer3__modules_1_bn3_weight[]={15793920,15798015,};
int RN50_layer3__modules_1_bn3_bias[]={3949504,3950527,}; int RN50_layer3__modules_1_bn3_bias[]={15798016,15802111,};
int RN50_layer3__modules_2_conv1_weight[]={3950528,4212671,}; int RN50_layer3__modules_2_conv1_weight[]={15802112,16850687,};
int RN50_layer3__modules_2_bn1_running_mean[]={4212672,4212927,}; int RN50_layer3__modules_2_bn1_running_mean[]={16850688,16851711,};
int RN50_layer3__modules_2_bn1_running_var[]={4212928,4213183,}; int RN50_layer3__modules_2_bn1_running_var[]={16851712,16852735,};
int RN50_layer3__modules_2_bn1_weight[]={4213184,4213439,}; int RN50_layer3__modules_2_bn1_weight[]={16852736,16853759,};
int RN50_layer3__modules_2_bn1_bias[]={4213440,4213695,}; int RN50_layer3__modules_2_bn1_bias[]={16853760,16854783,};
int RN50_layer3__modules_2_conv2_weight[]={4213696,4803519,}; int RN50_layer3__modules_2_conv2_weight[]={16854784,19214079,};
int RN50_layer3__modules_2_bn2_running_mean[]={4803520,4803775,}; int RN50_layer3__modules_2_bn2_running_mean[]={19214080,19215103,};
int RN50_layer3__modules_2_bn2_running_var[]={4803776,4804031,}; int RN50_layer3__modules_2_bn2_running_var[]={19215104,19216127,};
int RN50_layer3__modules_2_bn2_weight[]={4804032,4804287,}; int RN50_layer3__modules_2_bn2_weight[]={19216128,19217151,};
int RN50_layer3__modules_2_bn2_bias[]={4804288,4804543,}; int RN50_layer3__modules_2_bn2_bias[]={19217152,19218175,};
int RN50_layer3__modules_2_conv3_weight[]={4804544,5066687,}; int RN50_layer3__modules_2_conv3_weight[]={19218176,20266751,};
int RN50_layer3__modules_2_bn3_running_mean[]={5066688,5067711,}; int RN50_layer3__modules_2_bn3_running_mean[]={20266752,20270847,};
int RN50_layer3__modules_2_bn3_running_var[]={5067712,5068735,}; int RN50_layer3__modules_2_bn3_running_var[]={20270848,20274943,};
int RN50_layer3__modules_2_bn3_weight[]={5068736,5069759,}; int RN50_layer3__modules_2_bn3_weight[]={20274944,20279039,};
int RN50_layer3__modules_2_bn3_bias[]={5069760,5070783,}; int RN50_layer3__modules_2_bn3_bias[]={20279040,20283135,};
int RN50_layer3__modules_3_conv1_weight[]={5070784,5332927,}; int RN50_layer3__modules_3_conv1_weight[]={20283136,21331711,};
int RN50_layer3__modules_3_bn1_running_mean[]={5332928,5333183,}; int RN50_layer3__modules_3_bn1_running_mean[]={21331712,21332735,};
int RN50_layer3__modules_3_bn1_running_var[]={5333184,5333439,}; int RN50_layer3__modules_3_bn1_running_var[]={21332736,21333759,};
int RN50_layer3__modules_3_bn1_weight[]={5333440,5333695,}; int RN50_layer3__modules_3_bn1_weight[]={21333760,21334783,};
int RN50_layer3__modules_3_bn1_bias[]={5333696,5333951,}; int RN50_layer3__modules_3_bn1_bias[]={21334784,21335807,};
int RN50_layer3__modules_3_conv2_weight[]={5333952,5923775,}; int RN50_layer3__modules_3_conv2_weight[]={21335808,23695103,};
int RN50_layer3__modules_3_bn2_running_mean[]={5923776,5924031,}; int RN50_layer3__modules_3_bn2_running_mean[]={23695104,23696127,};
int RN50_layer3__modules_3_bn2_running_var[]={5924032,5924287,}; int RN50_layer3__modules_3_bn2_running_var[]={23696128,23697151,};
int RN50_layer3__modules_3_bn2_weight[]={5924288,5924543,}; int RN50_layer3__modules_3_bn2_weight[]={23697152,23698175,};
int RN50_layer3__modules_3_bn2_bias[]={5924544,5924799,}; int RN50_layer3__modules_3_bn2_bias[]={23698176,23699199,};
int RN50_layer3__modules_3_conv3_weight[]={5924800,6186943,}; int RN50_layer3__modules_3_conv3_weight[]={23699200,24747775,};
int RN50_layer3__modules_3_bn3_running_mean[]={6186944,6187967,}; int RN50_layer3__modules_3_bn3_running_mean[]={24747776,24751871,};
int RN50_layer3__modules_3_bn3_running_var[]={6187968,6188991,}; int RN50_layer3__modules_3_bn3_running_var[]={24751872,24755967,};
int RN50_layer3__modules_3_bn3_weight[]={6188992,6190015,}; int RN50_layer3__modules_3_bn3_weight[]={24755968,24760063,};
int RN50_layer3__modules_3_bn3_bias[]={6190016,6191039,}; int RN50_layer3__modules_3_bn3_bias[]={24760064,24764159,};
int RN50_layer3__modules_4_conv1_weight[]={6191040,6453183,}; int RN50_layer3__modules_4_conv1_weight[]={24764160,25812735,};
int RN50_layer3__modules_4_bn1_running_mean[]={6453184,6453439,}; int RN50_layer3__modules_4_bn1_running_mean[]={25812736,25813759,};
int RN50_layer3__modules_4_bn1_running_var[]={6453440,6453695,}; int RN50_layer3__modules_4_bn1_running_var[]={25813760,25814783,};
int RN50_layer3__modules_4_bn1_weight[]={6453696,6453951,}; int RN50_layer3__modules_4_bn1_weight[]={25814784,25815807,};
int RN50_layer3__modules_4_bn1_bias[]={6453952,6454207,}; int RN50_layer3__modules_4_bn1_bias[]={25815808,25816831,};
int RN50_layer3__modules_4_conv2_weight[]={6454208,7044031,}; int RN50_layer3__modules_4_conv2_weight[]={25816832,28176127,};
int RN50_layer3__modules_4_bn2_running_mean[]={7044032,7044287,}; int RN50_layer3__modules_4_bn2_running_mean[]={28176128,28177151,};
int RN50_layer3__modules_4_bn2_running_var[]={7044288,7044543,}; int RN50_layer3__modules_4_bn2_running_var[]={28177152,28178175,};
int RN50_layer3__modules_4_bn2_weight[]={7044544,7044799,}; int RN50_layer3__modules_4_bn2_weight[]={28178176,28179199,};
int RN50_layer3__modules_4_bn2_bias[]={7044800,7045055,}; int RN50_layer3__modules_4_bn2_bias[]={28179200,28180223,};
int RN50_layer3__modules_4_conv3_weight[]={7045056,7307199,}; int RN50_layer3__modules_4_conv3_weight[]={28180224,29228799,};
int RN50_layer3__modules_4_bn3_running_mean[]={7307200,7308223,}; int RN50_layer3__modules_4_bn3_running_mean[]={29228800,29232895,};
int RN50_layer3__modules_4_bn3_running_var[]={7308224,7309247,}; int RN50_layer3__modules_4_bn3_running_var[]={29232896,29236991,};
int RN50_layer3__modules_4_bn3_weight[]={7309248,7310271,}; int RN50_layer3__modules_4_bn3_weight[]={29236992,29241087,};
int RN50_layer3__modules_4_bn3_bias[]={7310272,7311295,}; int RN50_layer3__modules_4_bn3_bias[]={29241088,29245183,};
int RN50_layer3__modules_5_conv1_weight[]={7311296,7573439,}; int RN50_layer3__modules_5_conv1_weight[]={29245184,30293759,};
int RN50_layer3__modules_5_bn1_running_mean[]={7573440,7573695,}; int RN50_layer3__modules_5_bn1_running_mean[]={30293760,30294783,};
int RN50_layer3__modules_5_bn1_running_var[]={7573696,7573951,}; int RN50_layer3__modules_5_bn1_running_var[]={30294784,30295807,};
int RN50_layer3__modules_5_bn1_weight[]={7573952,7574207,}; int RN50_layer3__modules_5_bn1_weight[]={30295808,30296831,};
int RN50_layer3__modules_5_bn1_bias[]={7574208,7574463,}; int RN50_layer3__modules_5_bn1_bias[]={30296832,30297855,};
int RN50_layer3__modules_5_conv2_weight[]={7574464,8164287,}; int RN50_layer3__modules_5_conv2_weight[]={30297856,32657151,};
int RN50_layer3__modules_5_bn2_running_mean[]={8164288,8164543,}; int RN50_layer3__modules_5_bn2_running_mean[]={32657152,32658175,};
int RN50_layer3__modules_5_bn2_running_var[]={8164544,8164799,}; int RN50_layer3__modules_5_bn2_running_var[]={32658176,32659199,};
int RN50_layer3__modules_5_bn2_weight[]={8164800,8165055,}; int RN50_layer3__modules_5_bn2_weight[]={32659200,32660223,};
int RN50_layer3__modules_5_bn2_bias[]={8165056,8165311,}; int RN50_layer3__modules_5_bn2_bias[]={32660224,32661247,};
int RN50_layer3__modules_5_conv3_weight[]={8165312,8427455,}; int RN50_layer3__modules_5_conv3_weight[]={32661248,33709823,};
int RN50_layer3__modules_5_bn3_running_mean[]={8427456,8428479,}; int RN50_layer3__modules_5_bn3_running_mean[]={33709824,33713919,};
int RN50_layer3__modules_5_bn3_running_var[]={8428480,8429503,}; int RN50_layer3__modules_5_bn3_running_var[]={33713920,33718015,};
int RN50_layer3__modules_5_bn3_weight[]={8429504,8430527,}; int RN50_layer3__modules_5_bn3_weight[]={33718016,33722111,};
int RN50_layer3__modules_5_bn3_bias[]={8430528,8431551,}; int RN50_layer3__modules_5_bn3_bias[]={33722112,33726207,};
int RN50_layer4__modules_0_conv1_weight[]={8431552,8955839,}; int RN50_layer4__modules_0_conv1_weight[]={33726208,35823359,};
int RN50_layer4__modules_0_bn1_running_mean[]={8955840,8956351,}; int RN50_layer4__modules_0_bn1_running_mean[]={35823360,35825407,};
int RN50_layer4__modules_0_bn1_running_var[]={8956352,8956863,}; int RN50_layer4__modules_0_bn1_running_var[]={35825408,35827455,};
int RN50_layer4__modules_0_bn1_weight[]={8956864,8957375,}; int RN50_layer4__modules_0_bn1_weight[]={35827456,35829503,};
int RN50_layer4__modules_0_bn1_bias[]={8957376,8957887,}; int RN50_layer4__modules_0_bn1_bias[]={35829504,35831551,};
int RN50_layer4__modules_0_conv2_weight[]={8957888,11317183,}; int RN50_layer4__modules_0_conv2_weight[]={35831552,45268735,};
int RN50_layer4__modules_0_bn2_running_mean[]={11317184,11317695,}; int RN50_layer4__modules_0_bn2_running_mean[]={45268736,45270783,};
int RN50_layer4__modules_0_bn2_running_var[]={11317696,11318207,}; int RN50_layer4__modules_0_bn2_running_var[]={45270784,45272831,};
int RN50_layer4__modules_0_bn2_weight[]={11318208,11318719,}; int RN50_layer4__modules_0_bn2_weight[]={45272832,45274879,};
int RN50_layer4__modules_0_bn2_bias[]={11318720,11319231,}; int RN50_layer4__modules_0_bn2_bias[]={45274880,45276927,};
int RN50_layer4__modules_0_conv3_weight[]={11319232,12367807,}; int RN50_layer4__modules_0_conv3_weight[]={45276928,49471231,};
int RN50_layer4__modules_0_bn3_running_mean[]={12367808,12369855,}; int RN50_layer4__modules_0_bn3_running_mean[]={49471232,49479423,};
int RN50_layer4__modules_0_bn3_running_var[]={12369856,12371903,}; int RN50_layer4__modules_0_bn3_running_var[]={49479424,49487615,};
int RN50_layer4__modules_0_bn3_weight[]={12371904,12373951,}; int RN50_layer4__modules_0_bn3_weight[]={49487616,49495807,};
int RN50_layer4__modules_0_bn3_bias[]={12373952,12375999,}; int RN50_layer4__modules_0_bn3_bias[]={49495808,49503999,};
int RN50_layer4__modules_0_downsample__modules_0_weight[]={12376000,14473151,}; int RN50_layer4__modules_0_downsample__modules_0_weight[]={49504000,57892607,};
int RN50_layer4__modules_0_downsample__modules_1_running_mean[]={14473152,14475199,}; int RN50_layer4__modules_0_downsample__modules_1_running_mean[]={57892608,57900799,};
int RN50_layer4__modules_0_downsample__modules_1_running_var[]={14475200,14477247,}; int RN50_layer4__modules_0_downsample__modules_1_running_var[]={57900800,57908991,};
int RN50_layer4__modules_0_downsample__modules_1_weight[]={14477248,14479295,}; int RN50_layer4__modules_0_downsample__modules_1_weight[]={57908992,57917183,};
int RN50_layer4__modules_0_downsample__modules_1_bias[]={14479296,14481343,}; int RN50_layer4__modules_0_downsample__modules_1_bias[]={57917184,57925375,};
int RN50_layer4__modules_1_conv1_weight[]={14481344,15529919,}; int RN50_layer4__modules_1_conv1_weight[]={57925376,62119679,};
int RN50_layer4__modules_1_bn1_running_mean[]={15529920,15530431,}; int RN50_layer4__modules_1_bn1_running_mean[]={62119680,62121727,};
int RN50_layer4__modules_1_bn1_running_var[]={15530432,15530943,}; int RN50_layer4__modules_1_bn1_running_var[]={62121728,62123775,};
int RN50_layer4__modules_1_bn1_weight[]={15530944,15531455,}; int RN50_layer4__modules_1_bn1_weight[]={62123776,62125823,};
int RN50_layer4__modules_1_bn1_bias[]={15531456,15531967,}; int RN50_layer4__modules_1_bn1_bias[]={62125824,62127871,};
int RN50_layer4__modules_1_conv2_weight[]={15531968,17891263,}; int RN50_layer4__modules_1_conv2_weight[]={62127872,71565055,};
int RN50_layer4__modules_1_bn2_running_mean[]={17891264,17891775,}; int RN50_layer4__modules_1_bn2_running_mean[]={71565056,71567103,};
int RN50_layer4__modules_1_bn2_running_var[]={17891776,17892287,}; int RN50_layer4__modules_1_bn2_running_var[]={71567104,71569151,};
int RN50_layer4__modules_1_bn2_weight[]={17892288,17892799,}; int RN50_layer4__modules_1_bn2_weight[]={71569152,71571199,};
int RN50_layer4__modules_1_bn2_bias[]={17892800,17893311,}; int RN50_layer4__modules_1_bn2_bias[]={71571200,71573247,};
int RN50_layer4__modules_1_conv3_weight[]={17893312,18941887,}; int RN50_layer4__modules_1_conv3_weight[]={71573248,75767551,};
int RN50_layer4__modules_1_bn3_running_mean[]={18941888,18943935,}; int RN50_layer4__modules_1_bn3_running_mean[]={75767552,75775743,};
int RN50_layer4__modules_1_bn3_running_var[]={18943936,18945983,}; int RN50_layer4__modules_1_bn3_running_var[]={75775744,75783935,};
int RN50_layer4__modules_1_bn3_weight[]={18945984,18948031,}; int RN50_layer4__modules_1_bn3_weight[]={75783936,75792127,};
int RN50_layer4__modules_1_bn3_bias[]={18948032,18950079,}; int RN50_layer4__modules_1_bn3_bias[]={75792128,75800319,};
int RN50_layer4__modules_2_conv1_weight[]={18950080,19998655,}; int RN50_layer4__modules_2_conv1_weight[]={75800320,79994623,};
int RN50_layer4__modules_2_bn1_running_mean[]={19998656,19999167,}; int RN50_layer4__modules_2_bn1_running_mean[]={79994624,79996671,};
int RN50_layer4__modules_2_bn1_running_var[]={19999168,19999679,}; int RN50_layer4__modules_2_bn1_running_var[]={79996672,79998719,};
int RN50_layer4__modules_2_bn1_weight[]={19999680,20000191,}; int RN50_layer4__modules_2_bn1_weight[]={79998720,80000767,};
int RN50_layer4__modules_2_bn1_bias[]={20000192,20000703,}; int RN50_layer4__modules_2_bn1_bias[]={80000768,80002815,};
int RN50_layer4__modules_2_conv2_weight[]={20000704,22359999,}; int RN50_layer4__modules_2_conv2_weight[]={80002816,89439999,};
int RN50_layer4__modules_2_bn2_running_mean[]={22360000,22360511,}; int RN50_layer4__modules_2_bn2_running_mean[]={89440000,89442047,};
int RN50_layer4__modules_2_bn2_running_var[]={22360512,22361023,}; int RN50_layer4__modules_2_bn2_running_var[]={89442048,89444095,};
int RN50_layer4__modules_2_bn2_weight[]={22361024,22361535,}; int RN50_layer4__modules_2_bn2_weight[]={89444096,89446143,};
int RN50_layer4__modules_2_bn2_bias[]={22361536,22362047,}; int RN50_layer4__modules_2_bn2_bias[]={89446144,89448191,};
int RN50_layer4__modules_2_conv3_weight[]={22362048,23410623,}; int RN50_layer4__modules_2_conv3_weight[]={89448192,93642495,};
int RN50_layer4__modules_2_bn3_running_mean[]={23410624,23412671,}; int RN50_layer4__modules_2_bn3_running_mean[]={93642496,93650687,};
int RN50_layer4__modules_2_bn3_running_var[]={23412672,23414719,}; int RN50_layer4__modules_2_bn3_running_var[]={93650688,93658879,};
int RN50_layer4__modules_2_bn3_weight[]={23414720,23416767,}; int RN50_layer4__modules_2_bn3_weight[]={93658880,93667071,};
int RN50_layer4__modules_2_bn3_bias[]={23416768,23418815,}; int RN50_layer4__modules_2_bn3_bias[]={93667072,93675263,};
int RN50_fc_weight[]={23418816,25466815,}; int RN50_fc_weight[]={93675264,101867263,};
int RN50_fc_bias[]={25466816,25467815,}; int RN50_fc_bias[]={101867264,101871263,};
int input_0[]={25467816,25618343,}; int input_0[]={101871264,102473375,};
int output_0[]={25618344,25619343,}; int output_0[]={102473376,102477375,};
int input_1[]={25619344,25769871,}; int input_1[]={102477376,103079487,};
int output_1[]={25769872,25770871,}; int output_1[]={103079488,103083487,};
int input_2[]={25770872,25921399,}; int input_2[]={103083488,103685599,};
int output_2[]={25921400,25922399,}; int output_2[]={103685600,103689599,};
int input_3[]={25922400,26072927,}; int input_3[]={103689600,104291711,};
int output_3[]={26072928,26073927,}; int output_3[]={104291712,104295711,};
int input_4[]={26073928,26224455,}; int input_4[]={104295712,104897823,};
int output_4[]={26224456,26225455,}; int output_4[]={104897824,104901823,};
int input_5[]={26225456,26375983,}; int input_5[]={104901824,105503935,};
int output_5[]={26375984,26376983,}; int output_5[]={105503936,105507935,};
int input_6[]={26376984,26527511,}; int input_6[]={105507936,106110047,};
int output_6[]={26527512,26528511,}; int output_6[]={106110048,106114047,};
int input_7[]={26528512,26679039,}; int input_7[]={106114048,106716159,};
int output_7[]={26679040,26680039,}; int output_7[]={106716160,106720159,};
int input_8[]={26680040,26830567,}; int input_8[]={106720160,107322271,};
int output_8[]={26830568,26831567,}; int output_8[]={107322272,107326271,};
int input_9[]={26831568,26982095,}; int input_9[]={107326272,107928383,};
int output_9[]={26982096,26983095,}; int output_9[]={107928384,107932383,};

View File

@ -18,8 +18,6 @@ from struct import Struct
CurrentPath = os.path.split(os.path.realpath(__file__))[0]+"/" CurrentPath = os.path.split(os.path.realpath(__file__))[0]+"/"
resnet50 = models.resnet50(pretrained=True) resnet50 = models.resnet50(pretrained=True)
# torch.save(resnet50, CurrentPath+'params.pth') # torch.save(resnet50, CurrentPath+'params.pth')
resnet50 = torch.load(CurrentPath+'params.pth') resnet50 = torch.load(CurrentPath+'params.pth')
@ -235,7 +233,7 @@ def printDick(d, head, obj):
for a in array: for a in array:
bs = struct.pack("f", a) bs = struct.pack("f", a)
binaryfile.write(bs) binaryfile.write(bs)
currentbyte = currentbyte+1 currentbyte = currentbyte+4
strg += str(currentbyte-1) + "," strg += str(currentbyte-1) + ","
strg = strg + "};\n" strg = strg + "};\n"
if d[item] == "BatchNorm2d": if d[item] == "BatchNorm2d":
@ -245,7 +243,7 @@ def printDick(d, head, obj):
for a in array: for a in array:
bs = struct.pack("f", a) bs = struct.pack("f", a)
binaryfile.write(bs) binaryfile.write(bs)
currentbyte = currentbyte+1 currentbyte = currentbyte+4
strg += str(currentbyte-1) + "," strg += str(currentbyte-1) + ","
strg = strg + "};\n" strg = strg + "};\n"
@ -255,7 +253,7 @@ def printDick(d, head, obj):
for a in array: for a in array:
bs = struct.pack("f", a) bs = struct.pack("f", a)
binaryfile.write(bs) binaryfile.write(bs)
currentbyte = currentbyte+1 currentbyte = currentbyte+4
strg += str(currentbyte-1) + "," strg += str(currentbyte-1) + ","
strg = strg + "};\n" strg = strg + "};\n"
@ -265,7 +263,7 @@ def printDick(d, head, obj):
for a in array: for a in array:
bs = struct.pack("f", a) bs = struct.pack("f", a)
binaryfile.write(bs) binaryfile.write(bs)
currentbyte = currentbyte+1 currentbyte = currentbyte+4
strg += str(currentbyte-1) + "," strg += str(currentbyte-1) + ","
strg = strg + "};\n" strg = strg + "};\n"
@ -275,7 +273,7 @@ def printDick(d, head, obj):
for a in array: for a in array:
bs = struct.pack("f", a) bs = struct.pack("f", a)
binaryfile.write(bs) binaryfile.write(bs)
currentbyte = currentbyte+1 currentbyte = currentbyte+4
strg += str(currentbyte-1) + "," strg += str(currentbyte-1) + ","
strg = strg + "};\n" strg = strg + "};\n"
@ -286,7 +284,7 @@ def printDick(d, head, obj):
for a in array: for a in array:
bs = struct.pack("f", a) bs = struct.pack("f", a)
binaryfile.write(bs) binaryfile.write(bs)
currentbyte = currentbyte+1 currentbyte = currentbyte+4
strg += str(currentbyte-1) + "," strg += str(currentbyte-1) + ","
strg = strg + "};\n" strg = strg + "};\n"
@ -296,12 +294,13 @@ def printDick(d, head, obj):
for a in array: for a in array:
bs = struct.pack("f", a) bs = struct.pack("f", a)
binaryfile.write(bs) binaryfile.write(bs)
currentbyte = currentbyte+1 currentbyte = currentbyte+4
strg += str(currentbyte-1) + "," strg += str(currentbyte-1) + ","
strg = strg + "};\n" strg = strg + "};\n"
return strg return strg
strg = '' strg = ''
strg = printDick(ResNet50, "RN50", resnet50) strg = printDick(ResNet50, "RN50", resnet50)
@ -327,7 +326,7 @@ for batch_idx, (data, target) in enumerate(val_loader):
for a in array: for a in array:
bs = struct.pack("f", a) bs = struct.pack("f", a)
binaryfile.write(bs) binaryfile.write(bs)
currentbyte = currentbyte+1 currentbyte = currentbyte+4
strg += str(currentbyte-1) + "," strg += str(currentbyte-1) + ","
strg = strg + "};\n" strg = strg + "};\n"
@ -339,7 +338,7 @@ for batch_idx, (data, target) in enumerate(val_loader):
for a in array: for a in array:
bs = struct.pack("f", a) bs = struct.pack("f", a)
binaryfile.write(bs) binaryfile.write(bs)
currentbyte = currentbyte+1 currentbyte = currentbyte+4
strg += str(currentbyte-1) + "," strg += str(currentbyte-1) + ","
strg = strg + "};\n" strg = strg + "};\n"
@ -354,183 +353,3 @@ print(strg)
print("===========================") print("===========================")
print("===========================") print("===========================")
print("===========================") print("===========================")
# ResNet(
# (conv1): Conv2d(3, 64, kernel_size=(7, 7), stride=(2, 2), padding=(3, 3), bias=False)
# (bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
# (relu): ReLU(inplace=True)
# (maxpool): MaxPool2d(kernel_size=3, stride=2, padding=1, dilation=1, ceil_mode=False)
# (layer1): Sequential(
# (0): Bottleneck(
# (conv1): Conv2d(64, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)
# (bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
# (conv2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
# (bn2): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
# (conv3): Conv2d(64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
# (bn3): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
# (relu): ReLU(inplace=True)
# (downsample): Sequential(
# (0): Conv2d(64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
# (1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
# )
# )
# (1): Bottleneck(
# (conv1): Conv2d(256, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)
# (bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
# (conv2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
# (bn2): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
# (conv3): Conv2d(64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
# (bn3): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
# (relu): ReLU(inplace=True)
# )
# (2): Bottleneck(
# (conv1): Conv2d(256, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)
# (bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
# (conv2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
# (bn2): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
# (conv3): Conv2d(64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
# (bn3): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
# (relu): ReLU(inplace=True)
# )
# )
# (layer2): Sequential(
# (0): Bottleneck(
# (conv1): Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
# (bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
# (conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
# (bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
# (conv3): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
# (bn3): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
# (relu): ReLU(inplace=True)
# (downsample): Sequential(
# (0): Conv2d(256, 512, kernel_size=(1, 1), stride=(2, 2), bias=False)
# (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
# )
# )
# (1): Bottleneck(
# (conv1): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
# (bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
# (conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
# (bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
# (conv3): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
# (bn3): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
# (relu): ReLU(inplace=True)
# )
# (2): Bottleneck(
# (conv1): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
# (bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
# (conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
# (bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
# (conv3): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
# (bn3): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
# (relu): ReLU(inplace=True)
# )
# (3): Bottleneck(
# (conv1): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
# (bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
# (conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
# (bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
# (conv3): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
# (bn3): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
# (relu): ReLU(inplace=True)
# )
# )
# (layer3): Sequential(
# (0): Bottleneck(
# (conv1): Conv2d(512, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
# (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
# (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
# (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
# (conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)
# (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
# (relu): ReLU(inplace=True)
# (downsample): Sequential(
# (0): Conv2d(512, 1024, kernel_size=(1, 1), stride=(2, 2), bias=False)
# (1): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
# )
# )
# (1): Bottleneck(
# (conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
# (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
# (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
# (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
# (conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)
# (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
# (relu): ReLU(inplace=True)
# )
# (2): Bottleneck(
# (conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
# (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
# (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
# (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
# (conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)
# (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
# (relu): ReLU(inplace=True)
# )
# (3): Bottleneck(
# (conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
# (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
# (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
# (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
# (conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)
# (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
# (relu): ReLU(inplace=True)
# )
# (4): Bottleneck(
# (conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
# (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
# (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
# (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
# (conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)
# (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
# (relu): ReLU(inplace=True)
# )
# (5): Bottleneck(
# (conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
# (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
# (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
# (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
# (conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)
# (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
# (relu): ReLU(inplace=True)
# )
# )
# (layer4): Sequential(
# (0): Bottleneck(
# (conv1): Conv2d(1024, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
# (bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
# (conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
# (bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
# (conv3): Conv2d(512, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False)
# (bn3): BatchNorm2d(2048, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
# (relu): ReLU(inplace=True)
# (downsample): Sequential(
# (0): Conv2d(1024, 2048, kernel_size=(1, 1), stride=(2, 2), bias=False)
# (1): BatchNorm2d(2048, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
# )
# )
# (1): Bottleneck(
# (conv1): Conv2d(2048, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
# (bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
# (conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
# (bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
# (conv3): Conv2d(512, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False)
# (bn3): BatchNorm2d(2048, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
# (relu): ReLU(inplace=True)
# )
# (2): Bottleneck(
# (conv1): Conv2d(2048, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
# (bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
# (conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
# (bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
# (conv3): Conv2d(512, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False)
# (bn3): BatchNorm2d(2048, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
# (relu): ReLU(inplace=True)
# )
# )
# (avgpool): AdaptiveAvgPool2d(output_size=(1, 1))
# (fc): Linear(in_features=2048, out_features=1000, bias=True)
# )