/gpfs/projects/LynchGroup/spacewhale/git_spacewhale/spacewhale/shell_scripts
/gpfs/projects/LynchGroup/spacewhale
Training 10-fold val models. Resnet18, lr=0.0009
fold 8
Mon May 13 13:05:46 EDT 2019
######################################################################################################
WELCOME TO SPACEWHALE!
######################################################################################################
We will now train your model.. please be patient
Using resnet18 Your trained model will be named resnet18_fold8
------------------------------------------------------------------------------
<torch.utils.data.dataloader.DataLoader object at 0x2aaaf3da8fd0>
Your dataset size is: 11291
You have 2 classes in your dataset
------------------------------------------------------------------------------
Labels for the dataset are:
water = 0
whale = 1
------------------------------------------------------------------------------
Data loaded into gpu
------------------------------------------------------------------------------
Epoch 0/23
----------
train Loss: 0.7434 Acc: 0.6135 Err: 0.3865
TP: 3716.0000  TN: 3211.0000  FP: 2461.0000  FN: 1903.0000
Epoch 1/23
----------
train Loss: 0.6073 Acc: 0.6918 Err: 0.3082
TP: 4533.0000  TN: 3278.0000  FP: 2372.0000  FN: 1108.0000
Epoch 2/23
----------
train Loss: 0.5335 Acc: 0.7400 Err: 0.2600
TP: 4901.0000  TN: 3454.0000  FP: 2159.0000  FN: 777.0000
Epoch 3/23
----------
train Loss: 0.5032 Acc: 0.7714 Err: 0.2286
TP: 5155.0000  TN: 3555.0000  FP: 1958.0000  FN: 623.0000
Epoch 4/23
----------
train Loss: 0.4869 Acc: 0.7787 Err: 0.2213
TP: 5088.0000  TN: 3704.0000  FP: 1921.0000  FN: 578.0000
Epoch 5/23
----------
train Loss: 0.4626 Acc: 0.7972 Err: 0.2028
TP: 5179.0000  TN: 3822.0000  FP: 1760.0000  FN: 530.0000
Epoch 6/23
----------
train Loss: 0.4466 Acc: 0.7976 Err: 0.2024
TP: 5091.0000  TN: 3915.0000  FP: 1719.0000  FN: 566.0000
Epoch 7/23
----------
train Loss: 0.4134 Acc: 0.8175 Err: 0.1825
TP: 5232.0000  TN: 3998.0000  FP: 1687.0000  FN: 374.0000
Epoch 8/23
----------
train Loss: 0.4026 Acc: 0.8236 Err: 0.1764
TP: 5302.0000  TN: 3997.0000  FP: 1592.0000  FN: 400.0000
Epoch 9/23
----------
train Loss: 0.3890 Acc: 0.8317 Err: 0.1683
TP: 5348.0000  TN: 4043.0000  FP: 1548.0000  FN: 352.0000
Epoch 10/23
----------
train Loss: 0.3943 Acc: 0.8255 Err: 0.1745
TP: 5243.0000  TN: 4078.0000  FP: 1585.0000  FN: 385.0000
Epoch 11/23
----------
train Loss: 0.3880 Acc: 0.8303 Err: 0.1697
TP: 5235.0000  TN: 4140.0000  FP: 1542.0000  FN: 374.0000
Epoch 12/23
----------
train Loss: 0.3872 Acc: 0.8294 Err: 0.1706
TP: 5256.0000  TN: 4109.0000  FP: 1536.0000  FN: 390.0000
Epoch 13/23
----------
train Loss: 0.3788 Acc: 0.8402 Err: 0.1598
TP: 5428.0000  TN: 4059.0000  FP: 1452.0000  FN: 352.0000
Epoch 14/23
----------
train Loss: 0.3804 Acc: 0.8362 Err: 0.1638
TP: 5256.0000  TN: 4185.0000  FP: 1430.0000  FN: 420.0000
Epoch 15/23
----------
train Loss: 0.3672 Acc: 0.8426 Err: 0.1574
TP: 5348.0000  TN: 4166.0000  FP: 1401.0000  FN: 376.0000
Epoch 16/23
----------
train Loss: 0.3643 Acc: 0.8457 Err: 0.1543
TP: 5342.0000  TN: 4207.0000  FP: 1397.0000  FN: 345.0000
Epoch 17/23
----------
train Loss: 0.3725 Acc: 0.8395 Err: 0.1605
TP: 5240.0000  TN: 4239.0000  FP: 1454.0000  FN: 358.0000
Epoch 18/23
----------
train Loss: 0.3770 Acc: 0.8334 Err: 0.1666
TP: 5220.0000  TN: 4190.0000  FP: 1484.0000  FN: 397.0000
Epoch 19/23
----------
train Loss: 0.3805 Acc: 0.8349 Err: 0.1651
TP: 5208.0000  TN: 4219.0000  FP: 1472.0000  FN: 392.0000
Epoch 20/23
----------
train Loss: 0.3752 Acc: 0.8349 Err: 0.1651
TP: 5224.0000  TN: 4203.0000  FP: 1480.0000  FN: 384.0000
Epoch 21/23
----------
train Loss: 0.3722 Acc: 0.8419 Err: 0.1581
TP: 5292.0000  TN: 4214.0000  FP: 1417.0000  FN: 368.0000
Epoch 22/23
----------
train Loss: 0.3732 Acc: 0.8389 Err: 0.1611
TP: 5345.0000  TN: 4127.0000  FP: 1435.0000  FN: 384.0000
Epoch 23/23
----------
train Loss: 0.3691 Acc: 0.8351 Err: 0.1649
TP: 5182.0000  TN: 4247.0000  FP: 1490.0000  FN: 372.0000
-----------------------------------------------------------
Training complete in 60m 43s
-----------------------------------------------------------
Mon May 13 14:06:43 EDT 2019
fold 9
Mon May 13 14:06:43 EDT 2019
######################################################################################################
WELCOME TO SPACEWHALE!
######################################################################################################
We will now train your model.. please be patient
Using resnet18 Your trained model will be named resnet18_fold9
------------------------------------------------------------------------------
<torch.utils.data.dataloader.DataLoader object at 0x2aaaf73d6470>
Your dataset size is: 11290
You have 2 classes in your dataset
------------------------------------------------------------------------------
Labels for the dataset are:
water = 0
whale = 1
------------------------------------------------------------------------------
Data loaded into gpu
------------------------------------------------------------------------------
Epoch 0/23
----------
train Loss: 0.7010 Acc: 0.6426 Err: 0.3574
TP: 4040.0000  TN: 3215.0000  FP: 2368.0000  FN: 1667.0000
Epoch 1/23
----------
train Loss: 0.5428 Acc: 0.7390 Err: 0.2610
TP: 4712.0000  TN: 3631.0000  FP: 2085.0000  FN: 862.0000
Epoch 2/23
----------
train Loss: 0.4993 Acc: 0.7702 Err: 0.2298
TP: 4898.0000  TN: 3797.0000  FP: 1882.0000  FN: 713.0000
Epoch 3/23
----------
train Loss: 0.4593 Acc: 0.7954 Err: 0.2046
TP: 5140.0000  TN: 3840.0000  FP: 1748.0000  FN: 562.0000
Epoch 4/23
----------
train Loss: 0.4501 Acc: 0.7990 Err: 0.2010
TP: 5054.0000  TN: 3967.0000  FP: 1714.0000  FN: 555.0000
Epoch 5/23
----------
train Loss: 0.4351 Acc: 0.8102 Err: 0.1898
TP: 5106.0000  TN: 4041.0000  FP: 1620.0000  FN: 523.0000
Epoch 6/23
----------
train Loss: 0.4344 Acc: 0.8081 Err: 0.1919
TP: 5097.0000  TN: 4026.0000  FP: 1666.0000  FN: 501.0000
Epoch 7/23
----------
train Loss: 0.3899 Acc: 0.8294 Err: 0.1706
TP: 5246.0000  TN: 4118.0000  FP: 1547.0000  FN: 379.0000
Epoch 8/23
----------
train Loss: 0.3612 Acc: 0.8441 Err: 0.1559
TP: 5228.0000  TN: 4302.0000  FP: 1406.0000  FN: 354.0000
Epoch 9/23
----------
train Loss: 0.3707 Acc: 0.8399 Err: 0.1601
TP: 5212.0000  TN: 4270.0000  FP: 1444.0000  FN: 364.0000
Epoch 10/23
----------
train Loss: 0.3705 Acc: 0.8414 Err: 0.1586
TP: 5270.0000  TN: 4229.0000  FP: 1431.0000  FN: 360.0000
Epoch 11/23
----------
train Loss: 0.3587 Acc: 0.8463 Err: 0.1537
TP: 5316.0000  TN: 4239.0000  FP: 1378.0000  FN: 357.0000
Epoch 12/23
----------
train Loss: 0.3599 Acc: 0.8434 Err: 0.1566
TP: 5256.0000  TN: 4266.0000  FP: 1426.0000  FN: 342.0000
Epoch 13/23
----------
train Loss: 0.3599 Acc: 0.8447 Err: 0.1553
TP: 5248.0000  TN: 4289.0000  FP: 1402.0000  FN: 351.0000
Epoch 14/23
----------
train Loss: 0.3478 Acc: 0.8509 Err: 0.1491
TP: 5271.0000  TN: 4336.0000  FP: 1342.0000  FN: 341.0000
Epoch 15/23
----------
train Loss: 0.3493 Acc: 0.8515 Err: 0.1485
TP: 5265.0000  TN: 4348.0000  FP: 1350.0000  FN: 327.0000
Epoch 16/23
----------
train Loss: 0.3529 Acc: 0.8477 Err: 0.1523
TP: 5325.0000  TN: 4246.0000  FP: 1380.0000  FN: 339.0000
Epoch 17/23
----------
train Loss: 0.3550 Acc: 0.8471 Err: 0.1529
TP: 5363.0000  TN: 4201.0000  FP: 1391.0000  FN: 335.0000
Epoch 18/23
----------
train Loss: 0.3512 Acc: 0.8470 Err: 0.1530
TP: 5211.0000  TN: 4352.0000  FP: 1378.0000  FN: 349.0000
Epoch 19/23
----------
train Loss: 0.3483 Acc: 0.8492 Err: 0.1508
TP: 5273.0000  TN: 4314.0000  FP: 1358.0000  FN: 345.0000
Epoch 20/23
----------
train Loss: 0.3411 Acc: 0.8587 Err: 0.1413
TP: 5434.0000  TN: 4261.0000  FP: 1276.0000  FN: 319.0000
Epoch 21/23
----------
train Loss: 0.3513 Acc: 0.8476 Err: 0.1524
TP: 5338.0000  TN: 4231.0000  FP: 1366.0000  FN: 355.0000
Epoch 22/23
----------
train Loss: 0.3497 Acc: 0.8487 Err: 0.1513
TP: 5285.0000  TN: 4297.0000  FP: 1319.0000  FN: 389.0000
Epoch 23/23
----------
train Loss: 0.3540 Acc: 0.8461 Err: 0.1539
TP: 5236.0000  TN: 4316.0000  FP: 1358.0000  FN: 380.0000
-----------------------------------------------------------
Training complete in 60m 49s
-----------------------------------------------------------
Mon May 13 15:08:07 EDT 2019
fold 10
Mon May 13 15:08:07 EDT 2019
######################################################################################################
WELCOME TO SPACEWHALE!
######################################################################################################
We will now train your model.. please be patient
Using resnet18 Your trained model will be named resnet18_fold10
------------------------------------------------------------------------------
<torch.utils.data.dataloader.DataLoader object at 0x2aaaf73d64e0>
Your dataset size is: 11287
You have 2 classes in your dataset
------------------------------------------------------------------------------
Labels for the dataset are:
water = 0
whale = 1
------------------------------------------------------------------------------
Data loaded into gpu
------------------------------------------------------------------------------
Epoch 0/23
----------
train Loss: 0.6450 Acc: 0.6786 Err: 0.3214
TP: 4262.0000  TN: 3397.0000  FP: 2233.0000  FN: 1395.0000
Epoch 1/23
----------
train Loss: 0.5074 Acc: 0.7626 Err: 0.2374
TP: 4905.0000  TN: 3702.0000  FP: 1938.0000  FN: 742.0000
Epoch 2/23
----------
train Loss: 0.4619 Acc: 0.7904 Err: 0.2096
TP: 5016.0000  TN: 3905.0000  FP: 1767.0000  FN: 599.0000
Epoch 3/23
----------
train Loss: 0.4430 Acc: 0.8058 Err: 0.1942
TP: 5131.0000  TN: 3964.0000  FP: 1708.0000  FN: 484.0000
Epoch 4/23
----------
train Loss: 0.4254 Acc: 0.8141 Err: 0.1859
TP: 5214.0000  TN: 3975.0000  FP: 1674.0000  FN: 424.0000
Epoch 5/23
----------
train Loss: 0.4073 Acc: 0.8214 Err: 0.1786
TP: 5287.0000  TN: 3984.0000  FP: 1576.0000  FN: 440.0000
Epoch 6/23
----------
train Loss: 0.4062 Acc: 0.8221 Err: 0.1779
TP: 5133.0000  TN: 4146.0000  FP: 1566.0000  FN: 442.0000
Epoch 7/23
----------
train Loss: 0.3608 Acc: 0.8489 Err: 0.1511
TP: 5351.0000  TN: 4230.0000  FP: 1414.0000  FN: 292.0000
Epoch 8/23
----------
train Loss: 0.3545 Acc: 0.8476 Err: 0.1524
TP: 5388.0000  TN: 4179.0000  FP: 1436.0000  FN: 284.0000
Epoch 9/23
----------
train Loss: 0.3467 Acc: 0.8523 Err: 0.1477
TP: 5356.0000  TN: 4264.0000  FP: 1361.0000  FN: 306.0000
Epoch 10/23
----------
train Loss: 0.3432 Acc: 0.8517 Err: 0.1483
TP: 5356.0000  TN: 4257.0000  FP: 1381.0000  FN: 293.0000
Epoch 11/23
----------
train Loss: 0.3457 Acc: 0.8546 Err: 0.1454
TP: 5398.0000  TN: 4248.0000  FP: 1363.0000  FN: 278.0000
Epoch 12/23
----------
train Loss: 0.3431 Acc: 0.8525 Err: 0.1475
TP: 5241.0000  TN: 4381.0000  FP: 1351.0000  FN: 314.0000
Epoch 13/23
----------
train Loss: 0.3368 Acc: 0.8588 Err: 0.1412
TP: 5377.0000  TN: 4316.0000  FP: 1307.0000  FN: 287.0000
Epoch 14/23
----------
train Loss: 0.3335 Acc: 0.8584 Err: 0.1416
TP: 5367.0000  TN: 4322.0000  FP: 1311.0000  FN: 287.0000
Epoch 15/23
----------
train Loss: 0.3306 Acc: 0.8579 Err: 0.1421
TP: 5307.0000  TN: 4376.0000  FP: 1317.0000  FN: 287.0000
Epoch 16/23
----------
train Loss: 0.3438 Acc: 0.8512 Err: 0.1488
TP: 5246.0000  TN: 4361.0000  FP: 1365.0000  FN: 315.0000
Epoch 17/23
----------
train Loss: 0.3239 Acc: 0.8681 Err: 0.1319
TP: 5486.0000  TN: 4312.0000  FP: 1219.0000  FN: 270.0000
Epoch 18/23
----------
train Loss: 0.3216 Acc: 0.8629 Err: 0.1371
TP: 5446.0000  TN: 4293.0000  FP: 1273.0000  FN: 275.0000
Epoch 19/23
----------
train Loss: 0.3372 Acc: 0.8558 Err: 0.1442
TP: 5352.0000  TN: 4307.0000  FP: 1336.0000  FN: 292.0000
Epoch 20/23
----------
train Loss: 0.3380 Acc: 0.8549 Err: 0.1451
TP: 5306.0000  TN: 4343.0000  FP: 1347.0000  FN: 291.0000
Epoch 21/23
----------
train Loss: 0.3390 Acc: 0.8540 Err: 0.1460
TP: 5262.0000  TN: 4377.0000  FP: 1325.0000  FN: 323.0000
Epoch 22/23
----------
train Loss: 0.3304 Acc: 0.8613 Err: 0.1387
TP: 5348.0000  TN: 4374.0000  FP: 1258.0000  FN: 307.0000
Epoch 23/23
----------
train Loss: 0.3358 Acc: 0.8540 Err: 0.1460
TP: 5366.0000  TN: 4273.0000  FP: 1349.0000  FN: 299.0000
-----------------------------------------------------------
Training complete in 60m 44s
-----------------------------------------------------------
Mon May 13 16:09:30 EDT 2019
