/gpfs/projects/LynchGroup/spacewhale/git_spacewhale/spacewhale/shell_scripts
/gpfs/projects/LynchGroup/spacewhale
Training 10-fold val models. Resnet18, lr=0.0009
fold 1
Mon May 13 00:13:19 EDT 2019
######################################################################################################
WELCOME TO SPACEWHALE!
######################################################################################################
We will now train your model.. please be patient
Using resnet18 Your trained model will be named resnet18_fold1
------------------------------------------------------------------------------
<torch.utils.data.dataloader.DataLoader object at 0x2aaaf73d6438>
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: 0.6981 Acc: 0.6389 Err: 0.3611
TP: 3807.0000  TN: 3407.0000  FP: 2300.0000  FN: 1777.0000
Epoch 1/23
----------
train Loss: 0.5048 Acc: 0.7607 Err: 0.2393
TP: 4911.0000  TN: 3678.0000  FP: 2004.0000  FN: 698.0000
Epoch 2/23
----------
train Loss: 0.4532 Acc: 0.7909 Err: 0.2091
TP: 4938.0000  TN: 3992.0000  FP: 1828.0000  FN: 533.0000
Epoch 3/23
----------
train Loss: 0.4233 Acc: 0.8150 Err: 0.1850
TP: 5397.0000  TN: 3805.0000  FP: 1711.0000  FN: 378.0000
Epoch 4/23
----------
train Loss: 0.4157 Acc: 0.8167 Err: 0.1833
TP: 5266.0000  TN: 3955.0000  FP: 1680.0000  FN: 390.0000
Epoch 5/23
----------
train Loss: 0.4161 Acc: 0.8163 Err: 0.1837
TP: 5306.0000  TN: 3911.0000  FP: 1672.0000  FN: 402.0000
Epoch 6/23
----------
train Loss: 0.3881 Acc: 0.8323 Err: 0.1677
TP: 5365.0000  TN: 4032.0000  FP: 1561.0000  FN: 333.0000
Epoch 7/23
----------
train Loss: 0.3496 Acc: 0.8521 Err: 0.1479
TP: 5466.0000  TN: 4155.0000  FP: 1477.0000  FN: 193.0000
Epoch 8/23
----------
train Loss: 0.3453 Acc: 0.8540 Err: 0.1460
TP: 5431.0000  TN: 4212.0000  FP: 1426.0000  FN: 222.0000
Epoch 9/23
----------
train Loss: 0.3444 Acc: 0.8520 Err: 0.1480
TP: 5449.0000  TN: 4171.0000  FP: 1456.0000  FN: 215.0000
Epoch 10/23
----------
train Loss: 0.3359 Acc: 0.8524 Err: 0.1476
TP: 5372.0000  TN: 4252.0000  FP: 1443.0000  FN: 224.0000
Epoch 11/23
----------
train Loss: 0.3364 Acc: 0.8557 Err: 0.1443
TP: 5358.0000  TN: 4304.0000  FP: 1430.0000  FN: 199.0000
Epoch 12/23
----------
train Loss: 0.3316 Acc: 0.8570 Err: 0.1430
TP: 5397.0000  TN: 4279.0000  FP: 1408.0000  FN: 207.0000
Epoch 13/23
----------
train Loss: 0.3343 Acc: 0.8556 Err: 0.1444
TP: 5471.0000  TN: 4190.0000  FP: 1419.0000  FN: 211.0000
Epoch 14/23
----------
train Loss: 0.3244 Acc: 0.8593 Err: 0.1407
TP: 5425.0000  TN: 4277.0000  FP: 1366.0000  FN: 223.0000
Epoch 15/23
----------
train Loss: 0.3280 Acc: 0.8585 Err: 0.1415
TP: 5439.0000  TN: 4254.0000  FP: 1405.0000  FN: 193.0000
Epoch 16/23
----------
train Loss: 0.3264 Acc: 0.8610 Err: 0.1390
TP: 5364.0000  TN: 4358.0000  FP: 1347.0000  FN: 222.0000
Epoch 17/23
----------
train Loss: 0.3208 Acc: 0.8614 Err: 0.1386
TP: 5405.0000  TN: 4321.0000  FP: 1353.0000  FN: 212.0000
Epoch 18/23
----------
train Loss: 0.3305 Acc: 0.8568 Err: 0.1432
TP: 5540.0000  TN: 4134.0000  FP: 1405.0000  FN: 212.0000
Epoch 19/23
----------
train Loss: 0.3228 Acc: 0.8597 Err: 0.1403
TP: 5390.0000  TN: 4317.0000  FP: 1354.0000  FN: 230.0000
Epoch 20/23
----------
train Loss: 0.3147 Acc: 0.8683 Err: 0.1317
TP: 5562.0000  TN: 4242.0000  FP: 1294.0000  FN: 193.0000
Epoch 21/23
----------
train Loss: 0.3232 Acc: 0.8633 Err: 0.1367
TP: 5578.0000  TN: 4170.0000  FP: 1346.0000  FN: 197.0000
Epoch 22/23
----------
train Loss: 0.3227 Acc: 0.8630 Err: 0.1370
TP: 5537.0000  TN: 4207.0000  FP: 1380.0000  FN: 167.0000
Epoch 23/23
----------
train Loss: 0.3297 Acc: 0.8555 Err: 0.1445
TP: 5371.0000  TN: 4289.0000  FP: 1432.0000  FN: 199.0000
-----------------------------------------------------------
Training complete in 61m 24s
-----------------------------------------------------------
Mon May 13 01:16:10 EDT 2019
fold 2
Mon May 13 01:16:10 EDT 2019
######################################################################################################
WELCOME TO SPACEWHALE!
######################################################################################################
We will now train your model.. please be patient
Using resnet18 Your trained model will be named resnet18_fold2
------------------------------------------------------------------------------
<torch.utils.data.dataloader.DataLoader object at 0x2aaaf73d5358>
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: 0.7097 Acc: 0.6396 Err: 0.3604
TP: 3997.0000  TN: 3225.0000  FP: 2414.0000  FN: 1655.0000
Epoch 1/23
----------
train Loss: 0.5268 Acc: 0.7471 Err: 0.2529
TP: 4864.0000  TN: 3571.0000  FP: 2034.0000  FN: 822.0000
Epoch 2/23
----------
train Loss: 0.4794 Acc: 0.7746 Err: 0.2254
TP: 4951.0000  TN: 3795.0000  FP: 1850.0000  FN: 695.0000
Epoch 3/23
----------
train Loss: 0.4667 Acc: 0.7786 Err: 0.2214
TP: 5070.0000  TN: 3721.0000  FP: 1890.0000  FN: 610.0000
Epoch 4/23
----------
train Loss: 0.4561 Acc: 0.7855 Err: 0.2145
TP: 5102.0000  TN: 3767.0000  FP: 1841.0000  FN: 581.0000
Epoch 5/23
----------
train Loss: 0.4486 Acc: 0.7856 Err: 0.2144
TP: 5058.0000  TN: 3812.0000  FP: 1854.0000  FN: 567.0000
Epoch 6/23
----------
train Loss: 0.4331 Acc: 0.7998 Err: 0.2002
TP: 5179.0000  TN: 3852.0000  FP: 1762.0000  FN: 498.0000
Epoch 7/23
----------
train Loss: 0.3963 Acc: 0.8234 Err: 0.1766
TP: 5392.0000  TN: 3905.0000  FP: 1709.0000  FN: 285.0000
Epoch 8/23
----------
train Loss: 0.3789 Acc: 0.8310 Err: 0.1690
TP: 5376.0000  TN: 4007.0000  FP: 1606.0000  FN: 302.0000
Epoch 9/23
----------
train Loss: 0.3724 Acc: 0.8315 Err: 0.1685
TP: 5269.0000  TN: 4120.0000  FP: 1536.0000  FN: 366.0000
Epoch 10/23
----------
train Loss: 0.3658 Acc: 0.8369 Err: 0.1631
TP: 5256.0000  TN: 4193.0000  FP: 1475.0000  FN: 367.0000
Epoch 11/23
----------
train Loss: 0.3637 Acc: 0.8375 Err: 0.1625
TP: 5390.0000  TN: 4066.0000  FP: 1504.0000  FN: 331.0000
Epoch 12/23
----------
train Loss: 0.3567 Acc: 0.8412 Err: 0.1588
TP: 5357.0000  TN: 4141.0000  FP: 1485.0000  FN: 308.0000
Epoch 13/23
----------
train Loss: 0.3630 Acc: 0.8374 Err: 0.1626
TP: 5328.0000  TN: 4127.0000  FP: 1492.0000  FN: 344.0000
Epoch 14/23
----------
train Loss: 0.3581 Acc: 0.8431 Err: 0.1569
TP: 5394.0000  TN: 4126.0000  FP: 1433.0000  FN: 338.0000
Epoch 15/23
----------
train Loss: 0.3520 Acc: 0.8394 Err: 0.1606
TP: 5284.0000  TN: 4194.0000  FP: 1469.0000  FN: 344.0000
Epoch 16/23
----------
train Loss: 0.3623 Acc: 0.8371 Err: 0.1629
TP: 5252.0000  TN: 4200.0000  FP: 1504.0000  FN: 335.0000
Epoch 17/23
----------
train Loss: 0.3559 Acc: 0.8424 Err: 0.1576
TP: 5358.0000  TN: 4153.0000  FP: 1447.0000  FN: 333.0000
Epoch 18/23
----------
train Loss: 0.3623 Acc: 0.8364 Err: 0.1636
TP: 5314.0000  TN: 4130.0000  FP: 1494.0000  FN: 353.0000
Epoch 19/23
----------
train Loss: 0.3424 Acc: 0.8474 Err: 0.1526
TP: 5394.0000  TN: 4174.0000  FP: 1412.0000  FN: 311.0000
Epoch 20/23
----------
train Loss: 0.3522 Acc: 0.8433 Err: 0.1567
TP: 5420.0000  TN: 4102.0000  FP: 1455.0000  FN: 314.0000
Epoch 21/23
----------
train Loss: 0.3547 Acc: 0.8436 Err: 0.1564
TP: 5356.0000  TN: 4169.0000  FP: 1483.0000  FN: 283.0000
Epoch 22/23
----------
train Loss: 0.3616 Acc: 0.8408 Err: 0.1592
TP: 5332.0000  TN: 4162.0000  FP: 1489.0000  FN: 308.0000
Epoch 23/23
----------
train Loss: 0.3632 Acc: 0.8362 Err: 0.1638
TP: 5391.0000  TN: 4050.0000  FP: 1540.0000  FN: 310.0000
-----------------------------------------------------------
Training complete in 60m 59s
-----------------------------------------------------------
Mon May 13 02:17:47 EDT 2019
fold 3
Mon May 13 02:17:47 EDT 2019
######################################################################################################
WELCOME TO SPACEWHALE!
######################################################################################################
We will now train your model.. please be patient
Using resnet18 Your trained model will be named resnet18_fold3
------------------------------------------------------------------------------
<torch.utils.data.dataloader.DataLoader object at 0x2aaaf73d6518>
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: 0.7317 Acc: 0.6171 Err: 0.3829
TP: 3744.0000  TN: 3224.0000  FP: 2451.0000  FN: 1872.0000
Epoch 1/23
----------
train Loss: 0.5686 Acc: 0.7177 Err: 0.2823
TP: 4592.0000  TN: 3511.0000  FP: 2162.0000  FN: 1026.0000
Epoch 2/23
----------
train Loss: 0.5054 Acc: 0.7615 Err: 0.2385
TP: 4835.0000  TN: 3763.0000  FP: 1962.0000  FN: 731.0000
Epoch 3/23
----------
train Loss: 0.4669 Acc: 0.7854 Err: 0.2146
TP: 4923.0000  TN: 3945.0000  FP: 1808.0000  FN: 615.0000
Epoch 4/23
----------
train Loss: 0.4517 Acc: 0.7925 Err: 0.2075
TP: 5021.0000  TN: 3927.0000  FP: 1752.0000  FN: 591.0000
Epoch 5/23
----------
train Loss: 0.4427 Acc: 0.8011 Err: 0.1989
TP: 5191.0000  TN: 3854.0000  FP: 1737.0000  FN: 509.0000
Epoch 6/23
----------
train Loss: 0.4213 Acc: 0.8132 Err: 0.1868
TP: 5173.0000  TN: 4009.0000  FP: 1625.0000  FN: 484.0000
Epoch 7/23
----------
train Loss: 0.3833 Acc: 0.8317 Err: 0.1683
TP: 5220.0000  TN: 4171.0000  FP: 1539.0000  FN: 361.0000
Epoch 8/23
----------
train Loss: 0.3635 Acc: 0.8425 Err: 0.1575
TP: 5331.0000  TN: 4182.0000  FP: 1455.0000  FN: 323.0000
Epoch 9/23
----------
train Loss: 0.3568 Acc: 0.8466 Err: 0.1534
TP: 5348.0000  TN: 4211.0000  FP: 1388.0000  FN: 344.0000
Epoch 10/23
----------
train Loss: 0.3612 Acc: 0.8439 Err: 0.1561
TP: 5296.0000  TN: 4232.0000  FP: 1426.0000  FN: 337.0000
Epoch 11/23
----------
train Loss: 0.3543 Acc: 0.8492 Err: 0.1508
TP: 5394.0000  TN: 4194.0000  FP: 1387.0000  FN: 316.0000
Epoch 12/23
----------
train Loss: 0.3575 Acc: 0.8448 Err: 0.1552
TP: 5253.0000  TN: 4286.0000  FP: 1385.0000  FN: 367.0000
Epoch 13/23
----------
train Loss: 0.3599 Acc: 0.8438 Err: 0.1562
TP: 5276.0000  TN: 4251.0000  FP: 1409.0000  FN: 355.0000
Epoch 14/23
----------
train Loss: 0.3520 Acc: 0.8471 Err: 0.1529
TP: 5333.0000  TN: 4232.0000  FP: 1417.0000  FN: 309.0000
Epoch 15/23
----------
train Loss: 0.3415 Acc: 0.8544 Err: 0.1456
TP: 5326.0000  TN: 4321.0000  FP: 1321.0000  FN: 323.0000
Epoch 16/23
----------
train Loss: 0.3448 Acc: 0.8501 Err: 0.1499
TP: 5345.0000  TN: 4254.0000  FP: 1375.0000  FN: 317.0000
Epoch 17/23
----------
train Loss: 0.3454 Acc: 0.8509 Err: 0.1491
TP: 5241.0000  TN: 4366.0000  FP: 1354.0000  FN: 330.0000
Epoch 18/23
----------
train Loss: 0.3461 Acc: 0.8512 Err: 0.1488
TP: 5323.0000  TN: 4288.0000  FP: 1350.0000  FN: 330.0000
Epoch 19/23
----------
train Loss: 0.3405 Acc: 0.8561 Err: 0.1439
TP: 5308.0000  TN: 4358.0000  FP: 1337.0000  FN: 288.0000
Epoch 20/23
----------
train Loss: 0.3463 Acc: 0.8521 Err: 0.1479
TP: 5359.0000  TN: 4262.0000  FP: 1343.0000  FN: 327.0000
Epoch 21/23
----------
train Loss: 0.3473 Acc: 0.8501 Err: 0.1499
TP: 5331.0000  TN: 4268.0000  FP: 1383.0000  FN: 309.0000
Epoch 22/23
----------
train Loss: 0.3480 Acc: 0.8467 Err: 0.1533
TP: 5294.0000  TN: 4266.0000  FP: 1395.0000  FN: 336.0000
Epoch 23/23
----------
train Loss: 0.3535 Acc: 0.8448 Err: 0.1552
TP: 5195.0000  TN: 4344.0000  FP: 1437.0000  FN: 315.0000
-----------------------------------------------------------
Training complete in 60m 50s
-----------------------------------------------------------
Mon May 13 03:19:17 EDT 2019
fold 4
Mon May 13 03:19:17 EDT 2019
######################################################################################################
WELCOME TO SPACEWHALE!
######################################################################################################
We will now train your model.. please be patient
Using resnet18 Your trained model will be named resnet18_fold4
------------------------------------------------------------------------------
<torch.utils.data.dataloader.DataLoader object at 0x2aaaf73d6438>
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: 0.7584 Acc: 0.6123 Err: 0.3877
TP: 3762.0000  TN: 3152.0000  FP: 2501.0000  FN: 1876.0000
Epoch 1/23
----------
train Loss: 0.6055 Acc: 0.6966 Err: 0.3034
TP: 4641.0000  TN: 3224.0000  FP: 2341.0000  FN: 1085.0000
Epoch 2/23
----------
train Loss: 0.5217 Acc: 0.7511 Err: 0.2489
TP: 4774.0000  TN: 3707.0000  FP: 2012.0000  FN: 798.0000
Epoch 3/23
----------
train Loss: 0.4933 Acc: 0.7709 Err: 0.2291
TP: 5010.0000  TN: 3694.0000  FP: 1950.0000  FN: 637.0000
Epoch 4/23
----------
train Loss: 0.4705 Acc: 0.7858 Err: 0.2142
TP: 5018.0000  TN: 3854.0000  FP: 1864.0000  FN: 555.0000
Epoch 5/23
----------
train Loss: 0.4572 Acc: 0.7926 Err: 0.2074
TP: 5106.0000  TN: 3843.0000  FP: 1808.0000  FN: 534.0000
Epoch 6/23
----------
train Loss: 0.4369 Acc: 0.8062 Err: 0.1938
TP: 5205.0000  TN: 3898.0000  FP: 1728.0000  FN: 460.0000
Epoch 7/23
----------
train Loss: 0.4040 Acc: 0.8211 Err: 0.1789
TP: 5258.0000  TN: 4013.0000  FP: 1672.0000  FN: 348.0000
Epoch 8/23
----------
train Loss: 0.3854 Acc: 0.8311 Err: 0.1689
TP: 5246.0000  TN: 4138.0000  FP: 1529.0000  FN: 378.0000
Epoch 9/23
----------
train Loss: 0.3874 Acc: 0.8322 Err: 0.1678
TP: 5264.0000  TN: 4132.0000  FP: 1525.0000  FN: 370.0000
Epoch 10/23
----------
train Loss: 0.3817 Acc: 0.8368 Err: 0.1632
TP: 5282.0000  TN: 4166.0000  FP: 1495.0000  FN: 348.0000
Epoch 11/23
----------
train Loss: 0.3758 Acc: 0.8393 Err: 0.1607
TP: 5330.0000  TN: 4147.0000  FP: 1448.0000  FN: 366.0000
Epoch 12/23
----------
train Loss: 0.3715 Acc: 0.8374 Err: 0.1626
TP: 5264.0000  TN: 4191.0000  FP: 1456.0000  FN: 380.0000
Epoch 13/23
----------
train Loss: 0.3707 Acc: 0.8395 Err: 0.1605
TP: 5368.0000  TN: 4111.0000  FP: 1459.0000  FN: 353.0000
Epoch 14/23
----------
train Loss: 0.3809 Acc: 0.8328 Err: 0.1672
TP: 5344.0000  TN: 4059.0000  FP: 1547.0000  FN: 341.0000
Epoch 15/23
----------
train Loss: 0.3648 Acc: 0.8451 Err: 0.1549
TP: 5326.0000  TN: 4216.0000  FP: 1394.0000  FN: 355.0000
Epoch 16/23
----------
train Loss: 0.3774 Acc: 0.8354 Err: 0.1646
TP: 5306.0000  TN: 4126.0000  FP: 1490.0000  FN: 369.0000
Epoch 17/23
----------
train Loss: 0.3762 Acc: 0.8337 Err: 0.1663
TP: 5160.0000  TN: 4253.0000  FP: 1503.0000  FN: 375.0000
Epoch 18/23
----------
train Loss: 0.3717 Acc: 0.8379 Err: 0.1621
TP: 5195.0000  TN: 4266.0000  FP: 1470.0000  FN: 360.0000
Epoch 19/23
----------
train Loss: 0.3675 Acc: 0.8418 Err: 0.1582
TP: 5377.0000  TN: 4128.0000  FP: 1415.0000  FN: 371.0000
Epoch 20/23
----------
train Loss: 0.3669 Acc: 0.8392 Err: 0.1608
TP: 5244.0000  TN: 4231.0000  FP: 1454.0000  FN: 362.0000
Epoch 21/23
----------
train Loss: 0.3756 Acc: 0.8377 Err: 0.1623
TP: 5321.0000  TN: 4138.0000  FP: 1495.0000  FN: 337.0000
Epoch 22/23
----------
train Loss: 0.3740 Acc: 0.8346 Err: 0.1654
TP: 5138.0000  TN: 4285.0000  FP: 1522.0000  FN: 346.0000
Epoch 23/23
----------
train Loss: 0.3689 Acc: 0.8401 Err: 0.1599
TP: 5342.0000  TN: 4144.0000  FP: 1439.0000  FN: 366.0000
-----------------------------------------------------------
Training complete in 60m 54s
-----------------------------------------------------------
Mon May 13 04:20:43 EDT 2019
fold 5
Mon May 13 04:20:43 EDT 2019
######################################################################################################
WELCOME TO SPACEWHALE!
######################################################################################################
We will now train your model.. please be patient
Using resnet18 Your trained model will be named resnet18_fold5
------------------------------------------------------------------------------
<torch.utils.data.dataloader.DataLoader object at 0x2aaaf3da9f60>
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: 0.7306 Acc: 0.6076 Err: 0.3924
TP: 3725.0000  TN: 3135.0000  FP: 2518.0000  FN: 1913.0000
Epoch 1/23
----------
train Loss: 0.5644 Acc: 0.7168 Err: 0.2832
TP: 4592.0000  TN: 3501.0000  FP: 2148.0000  FN: 1050.0000
Epoch 2/23
----------
train Loss: 0.5114 Acc: 0.7541 Err: 0.2459
TP: 4927.0000  TN: 3588.0000  FP: 1997.0000  FN: 779.0000
Epoch 3/23
----------
train Loss: 0.4790 Acc: 0.7729 Err: 0.2271
TP: 4984.0000  TN: 3743.0000  FP: 1889.0000  FN: 675.0000
Epoch 4/23
----------
train Loss: 0.4597 Acc: 0.7853 Err: 0.2147
TP: 4992.0000  TN: 3875.0000  FP: 1853.0000  FN: 571.0000
Epoch 5/23
----------
train Loss: 0.4457 Acc: 0.8026 Err: 0.1974
TP: 5051.0000  TN: 4011.0000  FP: 1712.0000  FN: 517.0000
Epoch 6/23
----------
train Loss: 0.4365 Acc: 0.8054 Err: 0.1946
TP: 5125.0000  TN: 3969.0000  FP: 1687.0000  FN: 510.0000
Epoch 7/23
----------
train Loss: 0.4075 Acc: 0.8162 Err: 0.1838
TP: 5164.0000  TN: 4052.0000  FP: 1644.0000  FN: 431.0000
Epoch 8/23
----------
train Loss: 0.3898 Acc: 0.8261 Err: 0.1739
TP: 5164.0000  TN: 4163.0000  FP: 1560.0000  FN: 404.0000
Epoch 9/23
----------
train Loss: 0.3942 Acc: 0.8238 Err: 0.1762
TP: 5164.0000  TN: 4137.0000  FP: 1557.0000  FN: 433.0000
Epoch 10/23
----------
train Loss: 0.3725 Acc: 0.8362 Err: 0.1638
TP: 5322.0000  TN: 4120.0000  FP: 1472.0000  FN: 377.0000
Epoch 11/23
----------
train Loss: 0.3743 Acc: 0.8371 Err: 0.1629
TP: 5174.0000  TN: 4278.0000  FP: 1454.0000  FN: 385.0000
Epoch 12/23
----------
train Loss: 0.3652 Acc: 0.8416 Err: 0.1584
TP: 5279.0000  TN: 4224.0000  FP: 1435.0000  FN: 353.0000
Epoch 13/23
----------
train Loss: 0.3626 Acc: 0.8425 Err: 0.1575
TP: 5351.0000  TN: 4162.0000  FP: 1415.0000  FN: 363.0000
Epoch 14/23
----------
train Loss: 0.3681 Acc: 0.8364 Err: 0.1636
TP: 5203.0000  TN: 4241.0000  FP: 1450.0000  FN: 397.0000
Epoch 15/23
----------
train Loss: 0.3601 Acc: 0.8432 Err: 0.1568
TP: 5293.0000  TN: 4228.0000  FP: 1405.0000  FN: 365.0000
Epoch 16/23
----------
train Loss: 0.3637 Acc: 0.8390 Err: 0.1610
TP: 5231.0000  TN: 4242.0000  FP: 1448.0000  FN: 370.0000
Epoch 17/23
----------
train Loss: 0.3585 Acc: 0.8440 Err: 0.1560
TP: 5273.0000  TN: 4257.0000  FP: 1417.0000  FN: 344.0000
Epoch 18/23
----------
train Loss: 0.3635 Acc: 0.8394 Err: 0.1606
TP: 5256.0000  TN: 4222.0000  FP: 1445.0000  FN: 368.0000
Epoch 19/23
----------
train Loss: 0.3593 Acc: 0.8442 Err: 0.1558
TP: 5294.0000  TN: 4238.0000  FP: 1430.0000  FN: 329.0000
Epoch 20/23
----------
train Loss: 0.3703 Acc: 0.8378 Err: 0.1622
TP: 5205.0000  TN: 4255.0000  FP: 1443.0000  FN: 388.0000
Epoch 21/23
----------
train Loss: 0.3603 Acc: 0.8424 Err: 0.1576
TP: 5243.0000  TN: 4269.0000  FP: 1397.0000  FN: 382.0000
Epoch 22/23
----------
train Loss: 0.3630 Acc: 0.8412 Err: 0.1588
TP: 5275.0000  TN: 4223.0000  FP: 1398.0000  FN: 395.0000
Epoch 23/23
----------
train Loss: 0.3671 Acc: 0.8408 Err: 0.1592
TP: 5280.0000  TN: 4213.0000  FP: 1429.0000  FN: 369.0000
-----------------------------------------------------------
Training complete in 60m 58s
-----------------------------------------------------------
Mon May 13 05:22:15 EDT 2019
fold 6
Mon May 13 05:22:15 EDT 2019
######################################################################################################
WELCOME TO SPACEWHALE!
######################################################################################################
We will now train your model.. please be patient
Using resnet18 Your trained model will be named resnet18_fold6
------------------------------------------------------------------------------
<torch.utils.data.dataloader.DataLoader object at 0x2aaaf73d53c8>
Your dataset size is: 11315
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: 0.7300 Acc: 0.6100 Err: 0.3900
TP: 3634.0000  TN: 3268.0000  FP: 2444.0000  FN: 1969.0000
Epoch 1/23
----------
train Loss: 0.5626 Acc: 0.7188 Err: 0.2812
TP: 4742.0000  TN: 3391.0000  FP: 2237.0000  FN: 945.0000
Epoch 2/23
----------
train Loss: 0.5105 Acc: 0.7568 Err: 0.2432
TP: 5034.0000  TN: 3529.0000  FP: 2046.0000  FN: 706.0000
Epoch 3/23
----------
train Loss: 0.4725 Acc: 0.7868 Err: 0.2132
TP: 5158.0000  TN: 3745.0000  FP: 1841.0000  FN: 571.0000
Epoch 4/23
----------
train Loss: 0.4468 Acc: 0.8013 Err: 0.1987
TP: 5095.0000  TN: 3972.0000  FP: 1721.0000  FN: 527.0000
Epoch 5/23
----------
train Loss: 0.4382 Acc: 0.8063 Err: 0.1937
TP: 5146.0000  TN: 3977.0000  FP: 1684.0000  FN: 508.0000
Epoch 6/23
----------
train Loss: 0.4404 Acc: 0.8031 Err: 0.1969
TP: 5169.0000  TN: 3918.0000  FP: 1720.0000  FN: 508.0000
Epoch 7/23
----------
train Loss: 0.3954 Acc: 0.8271 Err: 0.1729
TP: 5318.0000  TN: 4041.0000  FP: 1602.0000  FN: 354.0000
Epoch 8/23
----------
train Loss: 0.3733 Acc: 0.8387 Err: 0.1613
TP: 5234.0000  TN: 4256.0000  FP: 1482.0000  FN: 343.0000
Epoch 9/23
----------
train Loss: 0.3891 Acc: 0.8292 Err: 0.1708
TP: 5309.0000  TN: 4073.0000  FP: 1573.0000  FN: 360.0000
Epoch 10/23
----------
train Loss: 0.3834 Acc: 0.8337 Err: 0.1663
TP: 5243.0000  TN: 4190.0000  FP: 1498.0000  FN: 384.0000
Epoch 11/23
----------
train Loss: 0.3775 Acc: 0.8302 Err: 0.1698
TP: 5155.0000  TN: 4239.0000  FP: 1554.0000  FN: 367.0000
Epoch 12/23
----------
train Loss: 0.3666 Acc: 0.8408 Err: 0.1592
TP: 5382.0000  TN: 4132.0000  FP: 1469.0000  FN: 332.0000
Epoch 13/23
----------
train Loss: 0.3682 Acc: 0.8363 Err: 0.1637
TP: 5303.0000  TN: 4160.0000  FP: 1496.0000  FN: 356.0000
Epoch 14/23
----------
train Loss: 0.3623 Acc: 0.8436 Err: 0.1564
TP: 5295.0000  TN: 4250.0000  FP: 1457.0000  FN: 313.0000
Epoch 15/23
----------
train Loss: 0.3547 Acc: 0.8465 Err: 0.1535
TP: 5412.0000  TN: 4166.0000  FP: 1432.0000  FN: 305.0000
Epoch 16/23
----------
train Loss: 0.3706 Acc: 0.8383 Err: 0.1617
TP: 5359.0000  TN: 4126.0000  FP: 1518.0000  FN: 312.0000
Epoch 17/23
----------
train Loss: 0.3598 Acc: 0.8438 Err: 0.1562
TP: 5348.0000  TN: 4200.0000  FP: 1415.0000  FN: 352.0000
Epoch 18/23
----------
train Loss: 0.3619 Acc: 0.8410 Err: 0.1590
TP: 5292.0000  TN: 4224.0000  FP: 1465.0000  FN: 334.0000
Epoch 19/23
----------
train Loss: 0.3637 Acc: 0.8432 Err: 0.1568
TP: 5358.0000  TN: 4183.0000  FP: 1452.0000  FN: 322.0000
Epoch 20/23
----------
train Loss: 0.3565 Acc: 0.8419 Err: 0.1581
TP: 5298.0000  TN: 4228.0000  FP: 1455.0000  FN: 334.0000
Epoch 21/23
----------
train Loss: 0.3719 Acc: 0.8401 Err: 0.1599
TP: 5357.0000  TN: 4149.0000  FP: 1450.0000  FN: 359.0000
Epoch 22/23
----------
train Loss: 0.3564 Acc: 0.8453 Err: 0.1547
TP: 5372.0000  TN: 4193.0000  FP: 1418.0000  FN: 332.0000
Epoch 23/23
----------
train Loss: 0.3514 Acc: 0.8503 Err: 0.1497
TP: 5359.0000  TN: 4262.0000  FP: 1369.0000  FN: 325.0000
-----------------------------------------------------------
Training complete in 61m 8s
-----------------------------------------------------------
Mon May 13 06:23:58 EDT 2019
fold 7
Mon May 13 06:23:58 EDT 2019
######################################################################################################
WELCOME TO SPACEWHALE!
######################################################################################################
We will now train your model.. please be patient
Using resnet18 Your trained model will be named resnet18_fold7
------------------------------------------------------------------------------
<torch.utils.data.dataloader.DataLoader object at 0x2aaaf73d6630>
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: 0.6842 Acc: 0.6504 Err: 0.3496
TP: 3976.0000  TN: 3368.0000  FP: 2247.0000  FN: 1700.0000
Epoch 1/23
----------
train Loss: 0.5253 Acc: 0.7536 Err: 0.2464
TP: 4750.0000  TN: 3759.0000  FP: 1909.0000  FN: 873.0000
Epoch 2/23
----------
train Loss: 0.4783 Acc: 0.7853 Err: 0.2147
TP: 5054.0000  TN: 3813.0000  FP: 1813.0000  FN: 611.0000
Epoch 3/23
----------
train Loss: 0.4595 Acc: 0.7911 Err: 0.2089
TP: 5072.0000  TN: 3860.0000  FP: 1770.0000  FN: 589.0000
Epoch 4/23
----------
train Loss: 0.4378 Acc: 0.8094 Err: 0.1906
TP: 5214.0000  TN: 3925.0000  FP: 1622.0000  FN: 530.0000
Epoch 5/23
----------
train Loss: 0.4347 Acc: 0.8052 Err: 0.1948
TP: 5096.0000  TN: 3996.0000  FP: 1663.0000  FN: 536.0000
Epoch 6/23
----------
train Loss: 0.4249 Acc: 0.8116 Err: 0.1884
TP: 5139.0000  TN: 4025.0000  FP: 1651.0000  FN: 476.0000
Epoch 7/23
----------
train Loss: 0.3789 Acc: 0.8350 Err: 0.1650
TP: 5272.0000  TN: 4156.0000  FP: 1513.0000  FN: 350.0000
Epoch 8/23
----------
train Loss: 0.3745 Acc: 0.8354 Err: 0.1646
TP: 5219.0000  TN: 4213.0000  FP: 1490.0000  FN: 369.0000
Epoch 9/23
----------
train Loss: 0.3688 Acc: 0.8377 Err: 0.1623
TP: 5211.0000  TN: 4248.0000  FP: 1453.0000  FN: 379.0000
Epoch 10/23
----------
train Loss: 0.3499 Acc: 0.8513 Err: 0.1487
TP: 5418.0000  TN: 4194.0000  FP: 1356.0000  FN: 323.0000
Epoch 11/23
----------
train Loss: 0.3511 Acc: 0.8513 Err: 0.1487
TP: 5275.0000  TN: 4337.0000  FP: 1341.0000  FN: 338.0000
Epoch 12/23
----------
train Loss: 0.3584 Acc: 0.8436 Err: 0.1564
TP: 5328.0000  TN: 4197.0000  FP: 1400.0000  FN: 366.0000
Epoch 13/23
----------
train Loss: 0.3391 Acc: 0.8553 Err: 0.1447
TP: 5360.0000  TN: 4297.0000  FP: 1294.0000  FN: 340.0000
Epoch 14/23
----------
train Loss: 0.3450 Acc: 0.8503 Err: 0.1497
TP: 5221.0000  TN: 4380.0000  FP: 1343.0000  FN: 347.0000
Epoch 15/23
----------
train Loss: 0.3477 Acc: 0.8485 Err: 0.1515
TP: 5310.0000  TN: 4270.0000  FP: 1339.0000  FN: 372.0000
Epoch 16/23
----------
train Loss: 0.3474 Acc: 0.8501 Err: 0.1499
TP: 5310.0000  TN: 4289.0000  FP: 1320.0000  FN: 372.0000
Epoch 17/23
----------
train Loss: 0.3416 Acc: 0.8546 Err: 0.1454
TP: 5353.0000  TN: 4296.0000  FP: 1314.0000  FN: 328.0000
Epoch 18/23
----------
train Loss: 0.3538 Acc: 0.8482 Err: 0.1518
TP: 5374.0000  TN: 4203.0000  FP: 1365.0000  FN: 349.0000
Epoch 19/23
----------
train Loss: 0.3477 Acc: 0.8486 Err: 0.1514
TP: 5253.0000  TN: 4328.0000  FP: 1390.0000  FN: 320.0000
Epoch 20/23
----------
train Loss: 0.3418 Acc: 0.8496 Err: 0.1504
TP: 5212.0000  TN: 4381.0000  FP: 1344.0000  FN: 354.0000
Epoch 21/23
----------
train Loss: 0.3502 Acc: 0.8501 Err: 0.1499
TP: 5340.0000  TN: 4259.0000  FP: 1341.0000  FN: 351.0000
Epoch 22/23
----------
train Loss: 0.3460 Acc: 0.8501 Err: 0.1499
TP: 5322.0000  TN: 4277.0000  FP: 1344.0000  FN: 348.0000
Epoch 23/23
----------
train Loss: 0.3466 Acc: 0.8510 Err: 0.1490
TP: 5362.0000  TN: 4247.0000  FP: 1345.0000  FN: 337.0000
-----------------------------------------------------------
Training complete in 60m 57s
-----------------------------------------------------------
Mon May 13 07:25:30 EDT 2019
fold 8
Mon May 13 07:25:30 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 0x2aaaf73d64a8>
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: 0.7421 Acc: 0.6154 Err: 0.3846
TP: 3836.0000  TN: 3112.0000  FP: 2556.0000  FN: 1787.0000
Epoch 1/23
----------
train Loss: 0.5908 Acc: 0.7068 Err: 0.2932
TP: 4565.0000  TN: 3416.0000  FP: 2274.0000  FN: 1036.0000
Epoch 2/23
----------
train Loss: 0.5243 Acc: 0.7546 Err: 0.2454
TP: 4892.0000  TN: 3628.0000  FP: 1991.0000  FN: 780.0000
Epoch 3/23
----------
train Loss: 0.5073 Acc: 0.7631 Err: 0.2369
TP: 4928.0000  TN: 3688.0000  FP: 1943.0000  FN: 732.0000
Epoch 4/23
----------
train Loss: 0.4651 Acc: 0.7900 Err: 0.2100
TP: 5033.0000  TN: 3887.0000  FP: 1770.0000  FN: 601.0000
Epoch 5/23
----------
train Loss: 0.4488 Acc: 0.7994 Err: 0.2006
TP: 5118.0000  TN: 3908.0000  FP: 1702.0000  FN: 563.0000
Epoch 6/23
----------
train Loss: 0.4320 Acc: 0.8077 Err: 0.1923
TP: 5068.0000  TN: 4052.0000  FP: 1667.0000  FN: 504.0000
Epoch 7/23
----------
train Loss: 0.4000 Acc: 0.8274 Err: 0.1726
TP: 5339.0000  TN: 4003.0000  FP: 1565.0000  FN: 384.0000
Epoch 8/23
----------
train Loss: 0.3790 Acc: 0.8375 Err: 0.1625
TP: 5220.0000  TN: 4236.0000  FP: 1464.0000  FN: 371.0000
Epoch 9/23
----------
train Loss: 0.3808 Acc: 0.8352 Err: 0.1648
TP: 5134.0000  TN: 4296.0000  FP: 1476.0000  FN: 385.0000
Epoch 10/23
----------
train Loss: 0.3825 Acc: 0.8316 Err: 0.1684
TP: 5286.0000  TN: 4104.0000  FP: 1515.0000  FN: 386.0000
Epoch 11/23
----------
train Loss: 0.3703 Acc: 0.8384 Err: 0.1616
TP: 5249.0000  TN: 4217.0000  FP: 1455.0000  FN: 370.0000
Epoch 12/23
----------
train Loss: 0.3742 Acc: 0.8376 Err: 0.1624
TP: 5241.0000  TN: 4216.0000  FP: 1453.0000  FN: 381.0000
Epoch 13/23
----------
train Loss: 0.3664 Acc: 0.8411 Err: 0.1589
TP: 5192.0000  TN: 4305.0000  FP: 1426.0000  FN: 368.0000
Epoch 14/23
----------
train Loss: 0.3602 Acc: 0.8408 Err: 0.1592
TP: 5252.0000  TN: 4241.0000  FP: 1447.0000  FN: 351.0000
Epoch 15/23
----------
train Loss: 0.3632 Acc: 0.8410 Err: 0.1590
TP: 5296.0000  TN: 4200.0000  FP: 1441.0000  FN: 354.0000
Epoch 16/23
----------
train Loss: 0.3639 Acc: 0.8407 Err: 0.1593
TP: 5235.0000  TN: 4257.0000  FP: 1421.0000  FN: 378.0000
Epoch 17/23
----------
train Loss: 0.3602 Acc: 0.8474 Err: 0.1526
TP: 5260.0000  TN: 4308.0000  FP: 1396.0000  FN: 327.0000
Epoch 18/23
----------
slurmstepd: error: *** JOB 4974 ON sn-nvda5 CANCELLED AT 2019-05-13T08:13:08 DUE TO TIME LIMIT ***
