Comments (2)
tkipf
commented on September 4, 2024
Interesting - haven't seen this before. Could be an issue related to python 3.5. Would you mind trying this in python 2.7? I'll look into it in the meantime.
from keras-gcn.
tigerneil
commented on September 4, 2024
I check it now. Python 2.7 works with tensorflow 1.0 and keras-1.2.2.
Using TensorFlow backend.
Loading cora dataset...
Dataset has 2708 nodes, 5429 edges, 1432 features.
Using local pooling filters...
W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use SSE3 instructions, but these are available on your machine and could speed up CPU computations.
W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use SSE4.1 instructions, but these are available on your machine and could speed up CPU computations.
W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use SSE4.2 instructions, but these are available on your machine and could speed up CPU computations.
W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use AVX instructions, but these are available on your machine and could speed up CPU computations.
W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use AVX2 instructions, but these are available on your machine and could speed up CPU computations.
W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use FMA instructions, but these are available on your machine and could speed up CPU computations.
Epoch: 0001 train_loss= 1.9408 train_acc= 0.5500 val_loss= 1.9420 val_acc= 0.4733 time= 0.9435
Epoch: 0002 train_loss= 1.9354 train_acc= 0.5786 val_loss= 1.9379 val_acc= 0.5100 time= 0.1498
Epoch: 0003 train_loss= 1.9291 train_acc= 0.6214 val_loss= 1.9332 val_acc= 0.5600 time= 0.1436
Epoch: 0004 train_loss= 1.9219 train_acc= 0.6714 val_loss= 1.9278 val_acc= 0.5767 time= 0.1404
Epoch: 0005 train_loss= 1.9141 train_acc= 0.6857 val_loss= 1.9221 val_acc= 0.5867 time= 0.1386
Epoch: 0006 train_loss= 1.9058 train_acc= 0.7000 val_loss= 1.9162 val_acc= 0.5867 time= 0.1397
Epoch: 0007 train_loss= 1.8970 train_acc= 0.7071 val_loss= 1.9098 val_acc= 0.5800 time= 0.1421
Epoch: 0008 train_loss= 1.8875 train_acc= 0.7143 val_loss= 1.9030 val_acc= 0.5767 time= 0.1479
Epoch: 0009 train_loss= 1.8774 train_acc= 0.7071 val_loss= 1.8958 val_acc= 0.5633 time= 0.1428
Epoch: 0010 train_loss= 1.8668 train_acc= 0.6786 val_loss= 1.8881 val_acc= 0.5600 time= 0.1438
Epoch: 0011 train_loss= 1.8556 train_acc= 0.6643 val_loss= 1.8801 val_acc= 0.5433 time= 0.1393
Epoch: 0012 train_loss= 1.8439 train_acc= 0.6571 val_loss= 1.8716 val_acc= 0.5267 time= 0.1376
Epoch: 0013 train_loss= 1.8317 train_acc= 0.6357 val_loss= 1.8628 val_acc= 0.5200 time= 0.1468
Epoch: 0014 train_loss= 1.8190 train_acc= 0.6357 val_loss= 1.8536 val_acc= 0.5167 time= 0.1538
Epoch: 0015 train_loss= 1.8059 train_acc= 0.6143 val_loss= 1.8440 val_acc= 0.5000 time= 0.1485
Epoch: 0016 train_loss= 1.7923 train_acc= 0.6143 val_loss= 1.8341 val_acc= 0.4967 time= 0.1380
Epoch: 0017 train_loss= 1.7783 train_acc= 0.6071 val_loss= 1.8239 val_acc= 0.4933 time= 0.1382
Epoch: 0018 train_loss= 1.7639 train_acc= 0.6071 val_loss= 1.8133 val_acc= 0.4933 time= 0.1420
Epoch: 0019 train_loss= 1.7492 train_acc= 0.5929 val_loss= 1.8025 val_acc= 0.4900 time= 0.1437
Epoch: 0020 train_loss= 1.7342 train_acc= 0.5929 val_loss= 1.7916 val_acc= 0.4867 time= 0.1394
Epoch: 0021 train_loss= 1.7189 train_acc= 0.5929 val_loss= 1.7805 val_acc= 0.4867 time= 0.1436
Epoch: 0022 train_loss= 1.7033 train_acc= 0.5929 val_loss= 1.7690 val_acc= 0.4867 time= 0.1489
Epoch: 0023 train_loss= 1.6875 train_acc= 0.5857 val_loss= 1.7575 val_acc= 0.4833 time= 0.1354
Epoch: 0024 train_loss= 1.6715 train_acc= 0.5786 val_loss= 1.7458 val_acc= 0.4800 time= 0.1378
Epoch: 0025 train_loss= 1.6552 train_acc= 0.5714 val_loss= 1.7340 val_acc= 0.4767 time= 0.1405
Epoch: 0026 train_loss= 1.6389 train_acc= 0.5714 val_loss= 1.7220 val_acc= 0.4767 time= 0.1400
Epoch: 0027 train_loss= 1.6224 train_acc= 0.5714 val_loss= 1.7099 val_acc= 0.4800 time= 0.1405
Epoch: 0028 train_loss= 1.6059 train_acc= 0.5786 val_loss= 1.6977 val_acc= 0.4800 time= 0.1407
Epoch: 0029 train_loss= 1.5892 train_acc= 0.5857 val_loss= 1.6854 val_acc= 0.4833 time= 0.1390
Epoch: 0030 train_loss= 1.5725 train_acc= 0.5929 val_loss= 1.6730 val_acc= 0.4900 time= 0.1404
Epoch: 0031 train_loss= 1.5557 train_acc= 0.6071 val_loss= 1.6605 val_acc= 0.4933 time= 0.1392
Epoch: 0032 train_loss= 1.5389 train_acc= 0.6143 val_loss= 1.6480 val_acc= 0.4933 time= 0.1433
Epoch: 0033 train_loss= 1.5222 train_acc= 0.6214 val_loss= 1.6354 val_acc= 0.4933 time= 0.1436
Epoch: 0034 train_loss= 1.5054 train_acc= 0.6214 val_loss= 1.6229 val_acc= 0.4967 time= 0.1358
Epoch: 0035 train_loss= 1.4887 train_acc= 0.6214 val_loss= 1.6104 val_acc= 0.5067 time= 0.1478
Epoch: 0036 train_loss= 1.4721 train_acc= 0.6214 val_loss= 1.5979 val_acc= 0.5133 time= 0.1464
Epoch: 0037 train_loss= 1.4557 train_acc= 0.6286 val_loss= 1.5855 val_acc= 0.5200 time= 0.1377
Epoch: 0038 train_loss= 1.4394 train_acc= 0.6357 val_loss= 1.5731 val_acc= 0.5300 time= 0.1458
Epoch: 0039 train_loss= 1.4233 train_acc= 0.6429 val_loss= 1.5609 val_acc= 0.5400 time= 0.1348
Epoch: 0040 train_loss= 1.4073 train_acc= 0.6571 val_loss= 1.5486 val_acc= 0.5533 time= 0.1324
Epoch: 0041 train_loss= 1.3914 train_acc= 0.6643 val_loss= 1.5364 val_acc= 0.5667 time= 0.1418
Epoch: 0042 train_loss= 1.3757 train_acc= 0.6857 val_loss= 1.5243 val_acc= 0.5800 time= 0.1387
Epoch: 0043 train_loss= 1.3601 train_acc= 0.7000 val_loss= 1.5123 val_acc= 0.5900 time= 0.1473
Epoch: 0044 train_loss= 1.3444 train_acc= 0.7357 val_loss= 1.5003 val_acc= 0.6000 time= 0.1377
Epoch: 0045 train_loss= 1.3290 train_acc= 0.7500 val_loss= 1.4883 val_acc= 0.6033 time= 0.1422
Epoch: 0046 train_loss= 1.3138 train_acc= 0.7571 val_loss= 1.4764 val_acc= 0.6233 time= 0.1388
Epoch: 0047 train_loss= 1.2988 train_acc= 0.7500 val_loss= 1.4648 val_acc= 0.6300 time= 0.1411
Epoch: 0048 train_loss= 1.2839 train_acc= 0.7714 val_loss= 1.4530 val_acc= 0.6367 time= 0.1347
Epoch: 0049 train_loss= 1.2694 train_acc= 0.7857 val_loss= 1.4415 val_acc= 0.6467 time= 0.1407
Epoch: 0050 train_loss= 1.2551 train_acc= 0.7929 val_loss= 1.4303 val_acc= 0.6600 time= 0.1460
Epoch: 0051 train_loss= 1.2411 train_acc= 0.8000 val_loss= 1.4192 val_acc= 0.6700 time= 0.1424
Epoch: 0052 train_loss= 1.2274 train_acc= 0.8214 val_loss= 1.4084 val_acc= 0.6800 time= 0.1388
Epoch: 0053 train_loss= 1.2139 train_acc= 0.8214 val_loss= 1.3977 val_acc= 0.6900 time= 0.1387
Epoch: 0054 train_loss= 1.2007 train_acc= 0.8214 val_loss= 1.3874 val_acc= 0.7033 time= 0.1441
Epoch: 0055 train_loss= 1.1876 train_acc= 0.8214 val_loss= 1.3769 val_acc= 0.7067 time= 0.1390
Epoch: 0056 train_loss= 1.1747 train_acc= 0.8286 val_loss= 1.3667 val_acc= 0.7133 time= 0.1387
Epoch: 0057 train_loss= 1.1619 train_acc= 0.8429 val_loss= 1.3565 val_acc= 0.7233 time= 0.1512
Epoch: 0058 train_loss= 1.1494 train_acc= 0.8429 val_loss= 1.3467 val_acc= 0.7233 time= 0.1443
Epoch: 0059 train_loss= 1.1370 train_acc= 0.8500 val_loss= 1.3370 val_acc= 0.7233 time= 0.1367
Epoch: 0060 train_loss= 1.1247 train_acc= 0.8571 val_loss= 1.3275 val_acc= 0.7267 time= 0.1414
Epoch: 0061 train_loss= 1.1129 train_acc= 0.8643 val_loss= 1.3183 val_acc= 0.7267 time= 0.1509
Epoch: 0062 train_loss= 1.1011 train_acc= 0.8643 val_loss= 1.3091 val_acc= 0.7333 time= 0.1428
Epoch: 0063 train_loss= 1.0894 train_acc= 0.8643 val_loss= 1.2998 val_acc= 0.7367 time= 0.1381
Epoch: 0064 train_loss= 1.0779 train_acc= 0.8714 val_loss= 1.2906 val_acc= 0.7367 time= 0.1487
Epoch: 0065 train_loss= 1.0668 train_acc= 0.8786 val_loss= 1.2816 val_acc= 0.7400 time= 0.1438
Epoch: 0066 train_loss= 1.0558 train_acc= 0.8857 val_loss= 1.2727 val_acc= 0.7433 time= 0.1345
Epoch: 0067 train_loss= 1.0448 train_acc= 0.8857 val_loss= 1.2640 val_acc= 0.7433 time= 0.1384
Epoch: 0068 train_loss= 1.0340 train_acc= 0.8857 val_loss= 1.2554 val_acc= 0.7433 time= 0.1385
Epoch: 0069 train_loss= 1.0235 train_acc= 0.8857 val_loss= 1.2471 val_acc= 0.7467 time= 0.1439
Epoch: 0070 train_loss= 1.0133 train_acc= 0.8857 val_loss= 1.2390 val_acc= 0.7500 time= 0.1400
Epoch: 0071 train_loss= 1.0033 train_acc= 0.8929 val_loss= 1.2313 val_acc= 0.7533 time= 0.1514
Epoch: 0072 train_loss= 0.9935 train_acc= 0.8929 val_loss= 1.2236 val_acc= 0.7500 time= 0.1414
Epoch: 0073 train_loss= 0.9840 train_acc= 0.8929 val_loss= 1.2162 val_acc= 0.7567 time= 0.1415
Epoch: 0074 train_loss= 0.9745 train_acc= 0.8929 val_loss= 1.2087 val_acc= 0.7567 time= 0.1442
Epoch: 0075 train_loss= 0.9652 train_acc= 0.9000 val_loss= 1.2013 val_acc= 0.7633 time= 0.1379
Epoch: 0076 train_loss= 0.9560 train_acc= 0.9000 val_loss= 1.1941 val_acc= 0.7633 time= 0.1416
Epoch: 0077 train_loss= 0.9470 train_acc= 0.9000 val_loss= 1.1869 val_acc= 0.7600 time= 0.1412
Epoch: 0078 train_loss= 0.9381 train_acc= 0.9000 val_loss= 1.1798 val_acc= 0.7633 time= 0.1503
Epoch: 0079 train_loss= 0.9295 train_acc= 0.9000 val_loss= 1.1729 val_acc= 0.7633 time= 0.1399
Epoch: 0080 train_loss= 0.9211 train_acc= 0.9000 val_loss= 1.1661 val_acc= 0.7633 time= 0.1435
Epoch: 0081 train_loss= 0.9128 train_acc= 0.9000 val_loss= 1.1593 val_acc= 0.7667 time= 0.1447
Epoch: 0082 train_loss= 0.9048 train_acc= 0.9000 val_loss= 1.1527 val_acc= 0.7667 time= 0.1462
Epoch: 0083 train_loss= 0.8968 train_acc= 0.9000 val_loss= 1.1461 val_acc= 0.7667 time= 0.1380
Epoch: 0084 train_loss= 0.8889 train_acc= 0.9000 val_loss= 1.1398 val_acc= 0.7700 time= 0.1437
Epoch: 0085 train_loss= 0.8811 train_acc= 0.9000 val_loss= 1.1336 val_acc= 0.7767 time= 0.1533
Epoch: 0086 train_loss= 0.8734 train_acc= 0.9000 val_loss= 1.1273 val_acc= 0.7800 time= 0.1436
Epoch: 0087 train_loss= 0.8657 train_acc= 0.9000 val_loss= 1.1212 val_acc= 0.7800 time= 0.1486
Epoch: 0088 train_loss= 0.8581 train_acc= 0.9000 val_loss= 1.1154 val_acc= 0.7833 time= 0.1407
Epoch: 0089 train_loss= 0.8507 train_acc= 0.9000 val_loss= 1.1095 val_acc= 0.7833 time= 0.1493
Epoch: 0090 train_loss= 0.8432 train_acc= 0.9071 val_loss= 1.1038 val_acc= 0.7833 time= 0.1413
Epoch: 0091 train_loss= 0.8358 train_acc= 0.9071 val_loss= 1.0983 val_acc= 0.7833 time= 0.1462
Epoch: 0092 train_loss= 0.8287 train_acc= 0.9071 val_loss= 1.0929 val_acc= 0.7800 time= 0.1538
Epoch: 0093 train_loss= 0.8217 train_acc= 0.9071 val_loss= 1.0878 val_acc= 0.7800 time= 0.1451
Epoch: 0094 train_loss= 0.8151 train_acc= 0.9071 val_loss= 1.0830 val_acc= 0.7800 time= 0.1487
Epoch: 0095 train_loss= 0.8086 train_acc= 0.9143 val_loss= 1.0782 val_acc= 0.7800 time= 0.1450
Epoch: 0096 train_loss= 0.8021 train_acc= 0.9143 val_loss= 1.0731 val_acc= 0.7833 time= 0.1482
Epoch: 0097 train_loss= 0.7957 train_acc= 0.9143 val_loss= 1.0681 val_acc= 0.7867 time= 0.1432
Epoch: 0098 train_loss= 0.7894 train_acc= 0.9143 val_loss= 1.0630 val_acc= 0.7767 time= 0.1399
Epoch: 0099 train_loss= 0.7829 train_acc= 0.9143 val_loss= 1.0579 val_acc= 0.7767 time= 0.1429
Epoch: 0100 train_loss= 0.7766 train_acc= 0.9143 val_loss= 1.0527 val_acc= 0.7767 time= 0.1422
Epoch: 0101 train_loss= 0.7703 train_acc= 0.9143 val_loss= 1.0477 val_acc= 0.7767 time= 0.1440
Epoch: 0102 train_loss= 0.7640 train_acc= 0.9143 val_loss= 1.0430 val_acc= 0.7767 time= 0.1502
Epoch: 0103 train_loss= 0.7579 train_acc= 0.9143 val_loss= 1.0383 val_acc= 0.7767 time= 0.1459
Epoch: 0104 train_loss= 0.7518 train_acc= 0.9143 val_loss= 1.0337 val_acc= 0.7767 time= 0.1439
Epoch: 0105 train_loss= 0.7459 train_acc= 0.9143 val_loss= 1.0293 val_acc= 0.7767 time= 0.1505
Epoch: 0106 train_loss= 0.7402 train_acc= 0.9143 val_loss= 1.0249 val_acc= 0.7767 time= 0.1469
Epoch: 0107 train_loss= 0.7344 train_acc= 0.9143 val_loss= 1.0203 val_acc= 0.7800 time= 0.1423
Epoch: 0108 train_loss= 0.7288 train_acc= 0.9143 val_loss= 1.0156 val_acc= 0.7833 time= 0.1567
Epoch: 0109 train_loss= 0.7233 train_acc= 0.9286 val_loss= 1.0112 val_acc= 0.7900 time= 0.1416
Epoch: 0110 train_loss= 0.7178 train_acc= 0.9286 val_loss= 1.0069 val_acc= 0.7900 time= 0.1464
Epoch: 0111 train_loss= 0.7123 train_acc= 0.9286 val_loss= 1.0026 val_acc= 0.7900 time= 0.1464
Epoch: 0112 train_loss= 0.7069 train_acc= 0.9286 val_loss= 0.9984 val_acc= 0.7933 time= 0.1484
Epoch: 0113 train_loss= 0.7015 train_acc= 0.9286 val_loss= 0.9941 val_acc= 0.7933 time= 0.1427
Epoch: 0114 train_loss= 0.6961 train_acc= 0.9286 val_loss= 0.9897 val_acc= 0.7933 time= 0.1393
Epoch: 0115 train_loss= 0.6908 train_acc= 0.9286 val_loss= 0.9854 val_acc= 0.7933 time= 0.1440
Epoch: 0116 train_loss= 0.6857 train_acc= 0.9286 val_loss= 0.9811 val_acc= 0.7933 time= 0.1505
Epoch: 0117 train_loss= 0.6806 train_acc= 0.9286 val_loss= 0.9768 val_acc= 0.7900 time= 0.1404
Epoch: 0118 train_loss= 0.6757 train_acc= 0.9286 val_loss= 0.9726 val_acc= 0.7867 time= 0.1445
Epoch: 0119 train_loss= 0.6709 train_acc= 0.9286 val_loss= 0.9686 val_acc= 0.7867 time= 0.1512
Epoch: 0120 train_loss= 0.6664 train_acc= 0.9286 val_loss= 0.9652 val_acc= 0.7867 time= 0.1468
Epoch: 0121 train_loss= 0.6619 train_acc= 0.9357 val_loss= 0.9620 val_acc= 0.7867 time= 0.1462
Epoch: 0122 train_loss= 0.6575 train_acc= 0.9357 val_loss= 0.9590 val_acc= 0.7867 time= 0.1423
Epoch: 0123 train_loss= 0.6530 train_acc= 0.9357 val_loss= 0.9561 val_acc= 0.7867 time= 0.1418
Epoch: 0124 train_loss= 0.6486 train_acc= 0.9357 val_loss= 0.9534 val_acc= 0.7900 time= 0.1365
Epoch: 0125 train_loss= 0.6443 train_acc= 0.9357 val_loss= 0.9509 val_acc= 0.7900 time= 0.1422
Epoch: 0126 train_loss= 0.6401 train_acc= 0.9357 val_loss= 0.9487 val_acc= 0.7967 time= 0.1448
Epoch: 0127 train_loss= 0.6359 train_acc= 0.9357 val_loss= 0.9465 val_acc= 0.7967 time= 0.1384
Epoch: 0128 train_loss= 0.6319 train_acc= 0.9357 val_loss= 0.9442 val_acc= 0.7967 time= 0.1418
Epoch: 0129 train_loss= 0.6281 train_acc= 0.9357 val_loss= 0.9418 val_acc= 0.7933 time= 0.1410
Epoch: 0130 train_loss= 0.6243 train_acc= 0.9357 val_loss= 0.9396 val_acc= 0.7933 time= 0.1453
Epoch: 0131 train_loss= 0.6206 train_acc= 0.9429 val_loss= 0.9374 val_acc= 0.7933 time= 0.1418
Epoch: 0132 train_loss= 0.6168 train_acc= 0.9429 val_loss= 0.9350 val_acc= 0.7933 time= 0.1438
Epoch: 0133 train_loss= 0.6131 train_acc= 0.9500 val_loss= 0.9323 val_acc= 0.7933 time= 0.1490
Epoch: 0134 train_loss= 0.6095 train_acc= 0.9500 val_loss= 0.9294 val_acc= 0.7967 time= 0.1503
Epoch: 0135 train_loss= 0.6058 train_acc= 0.9500 val_loss= 0.9265 val_acc= 0.7967 time= 0.1431
Epoch: 0136 train_loss= 0.6022 train_acc= 0.9500 val_loss= 0.9233 val_acc= 0.7967 time= 0.1386
Epoch: 0137 train_loss= 0.5986 train_acc= 0.9571 val_loss= 0.9202 val_acc= 0.7967 time= 0.1469
Epoch: 0138 train_loss= 0.5950 train_acc= 0.9571 val_loss= 0.9172 val_acc= 0.7967 time= 0.1391
Epoch: 0139 train_loss= 0.5914 train_acc= 0.9571 val_loss= 0.9141 val_acc= 0.7967 time= 0.1411
Epoch: 0140 train_loss= 0.5879 train_acc= 0.9571 val_loss= 0.9111 val_acc= 0.7967 time= 0.1439
Epoch: 0141 train_loss= 0.5843 train_acc= 0.9571 val_loss= 0.9082 val_acc= 0.8000 time= 0.1389
Epoch: 0142 train_loss= 0.5806 train_acc= 0.9571 val_loss= 0.9052 val_acc= 0.8000 time= 0.1467
Epoch: 0143 train_loss= 0.5770 train_acc= 0.9571 val_loss= 0.9021 val_acc= 0.7967 time= 0.1491
Epoch: 0144 train_loss= 0.5733 train_acc= 0.9571 val_loss= 0.8985 val_acc= 0.7967 time= 0.1456
Epoch: 0145 train_loss= 0.5697 train_acc= 0.9643 val_loss= 0.8947 val_acc= 0.7967 time= 0.1430
Epoch: 0146 train_loss= 0.5661 train_acc= 0.9643 val_loss= 0.8914 val_acc= 0.7967 time= 0.1439
Epoch: 0147 train_loss= 0.5626 train_acc= 0.9643 val_loss= 0.8883 val_acc= 0.7967 time= 0.1561
Epoch: 0148 train_loss= 0.5592 train_acc= 0.9643 val_loss= 0.8854 val_acc= 0.7967 time= 0.1422
Epoch: 0149 train_loss= 0.5557 train_acc= 0.9643 val_loss= 0.8825 val_acc= 0.7967 time= 0.1459
Epoch: 0150 train_loss= 0.5522 train_acc= 0.9643 val_loss= 0.8799 val_acc= 0.8000 time= 0.1418
Epoch: 0151 train_loss= 0.5488 train_acc= 0.9643 val_loss= 0.8772 val_acc= 0.8000 time= 0.1412
Epoch: 0152 train_loss= 0.5455 train_acc= 0.9643 val_loss= 0.8747 val_acc= 0.8067 time= 0.1406
Epoch: 0153 train_loss= 0.5423 train_acc= 0.9643 val_loss= 0.8723 val_acc= 0.8067 time= 0.1425
Epoch: 0154 train_loss= 0.5391 train_acc= 0.9643 val_loss= 0.8700 val_acc= 0.8067 time= 0.1539
Epoch: 0155 train_loss= 0.5360 train_acc= 0.9643 val_loss= 0.8675 val_acc= 0.8067 time= 0.1423
Epoch: 0156 train_loss= 0.5330 train_acc= 0.9643 val_loss= 0.8650 val_acc= 0.8067 time= 0.1420
Epoch: 0157 train_loss= 0.5300 train_acc= 0.9643 val_loss= 0.8626 val_acc= 0.8033 time= 0.1407
Epoch: 0158 train_loss= 0.5272 train_acc= 0.9643 val_loss= 0.8602 val_acc= 0.8033 time= 0.1442
Epoch: 0159 train_loss= 0.5243 train_acc= 0.9643 val_loss= 0.8578 val_acc= 0.8000 time= 0.1411
Epoch: 0160 train_loss= 0.5215 train_acc= 0.9643 val_loss= 0.8555 val_acc= 0.8000 time= 0.1412
Epoch: 0161 train_loss= 0.5188 train_acc= 0.9643 val_loss= 0.8531 val_acc= 0.8033 time= 0.1542
Epoch: 0162 train_loss= 0.5161 train_acc= 0.9571 val_loss= 0.8506 val_acc= 0.8033 time= 0.1432
Epoch: 0163 train_loss= 0.5133 train_acc= 0.9571 val_loss= 0.8484 val_acc= 0.8000 time= 0.1370
Epoch: 0164 train_loss= 0.5107 train_acc= 0.9571 val_loss= 0.8464 val_acc= 0.8033 time= 0.1406
Epoch: 0165 train_loss= 0.5081 train_acc= 0.9571 val_loss= 0.8444 val_acc= 0.8033 time= 0.1425
Epoch: 0166 train_loss= 0.5055 train_acc= 0.9571 val_loss= 0.8424 val_acc= 0.8033 time= 0.1440
Epoch: 0167 train_loss= 0.5029 train_acc= 0.9643 val_loss= 0.8405 val_acc= 0.8033 time= 0.1422
Epoch: 0168 train_loss= 0.5004 train_acc= 0.9643 val_loss= 0.8389 val_acc= 0.8033 time= 0.1493
Epoch: 0169 train_loss= 0.4978 train_acc= 0.9643 val_loss= 0.8377 val_acc= 0.8033 time= 0.1457
Epoch: 0170 train_loss= 0.4953 train_acc= 0.9643 val_loss= 0.8365 val_acc= 0.8067 time= 0.1543
Epoch: 0171 train_loss= 0.4930 train_acc= 0.9643 val_loss= 0.8354 val_acc= 0.8100 time= 0.1442
Epoch: 0172 train_loss= 0.4907 train_acc= 0.9643 val_loss= 0.8341 val_acc= 0.8100 time= 0.1488
Epoch: 0173 train_loss= 0.4886 train_acc= 0.9714 val_loss= 0.8331 val_acc= 0.8100 time= 0.1410
Epoch: 0174 train_loss= 0.4865 train_acc= 0.9714 val_loss= 0.8317 val_acc= 0.8100 time= 0.1422
Epoch: 0175 train_loss= 0.4842 train_acc= 0.9714 val_loss= 0.8302 val_acc= 0.8133 time= 0.1536
Epoch: 0176 train_loss= 0.4821 train_acc= 0.9714 val_loss= 0.8287 val_acc= 0.8167 time= 0.1517
Epoch: 0177 train_loss= 0.4799 train_acc= 0.9714 val_loss= 0.8269 val_acc= 0.8200 time= 0.1452
Epoch: 0178 train_loss= 0.4777 train_acc= 0.9714 val_loss= 0.8250 val_acc= 0.8233 time= 0.1411
Epoch: 0179 train_loss= 0.4756 train_acc= 0.9714 val_loss= 0.8232 val_acc= 0.8233 time= 0.1417
Epoch: 0180 train_loss= 0.4734 train_acc= 0.9714 val_loss= 0.8214 val_acc= 0.8233 time= 0.1455
Epoch: 0181 train_loss= 0.4712 train_acc= 0.9714 val_loss= 0.8190 val_acc= 0.8200 time= 0.1392
Epoch: 0182 train_loss= 0.4690 train_acc= 0.9714 val_loss= 0.8168 val_acc= 0.8200 time= 0.1400
Epoch: 0183 train_loss= 0.4669 train_acc= 0.9714 val_loss= 0.8148 val_acc= 0.8200 time= 0.1422
Epoch: 0184 train_loss= 0.4648 train_acc= 0.9714 val_loss= 0.8128 val_acc= 0.8167 time= 0.1375
Epoch: 0185 train_loss= 0.4627 train_acc= 0.9714 val_loss= 0.8109 val_acc= 0.8167 time= 0.1457
Epoch: 0186 train_loss= 0.4607 train_acc= 0.9714 val_loss= 0.8091 val_acc= 0.8133 time= 0.1489
Epoch: 0187 train_loss= 0.4587 train_acc= 0.9714 val_loss= 0.8077 val_acc= 0.8133 time= 0.1442
Epoch: 0188 train_loss= 0.4567 train_acc= 0.9714 val_loss= 0.8066 val_acc= 0.8133 time= 0.1477
Epoch: 0189 train_loss= 0.4548 train_acc= 0.9714 val_loss= 0.8056 val_acc= 0.8133 time= 0.1414
Epoch: 0190 train_loss= 0.4529 train_acc= 0.9714 val_loss= 0.8043 val_acc= 0.8167 time= 0.1460
Epoch: 0191 train_loss= 0.4510 train_acc= 0.9714 val_loss= 0.8031 val_acc= 0.8167 time= 0.1405
Epoch: 0192 train_loss= 0.4492 train_acc= 0.9714 val_loss= 0.8017 val_acc= 0.8233 time= 0.1428
Epoch: 0193 train_loss= 0.4474 train_acc= 0.9714 val_loss= 0.8005 val_acc= 0.8233 time= 0.1414
Epoch: 0194 train_loss= 0.4456 train_acc= 0.9714 val_loss= 0.7992 val_acc= 0.8233 time= 0.1407
Epoch: 0195 train_loss= 0.4438 train_acc= 0.9714 val_loss= 0.7977 val_acc= 0.8233 time= 0.1505
Epoch: 0196 train_loss= 0.4419 train_acc= 0.9714 val_loss= 0.7961 val_acc= 0.8233 time= 0.1431
Epoch: 0197 train_loss= 0.4401 train_acc= 0.9714 val_loss= 0.7944 val_acc= 0.8233 time= 0.1430
Epoch: 0198 train_loss= 0.4381 train_acc= 0.9714 val_loss= 0.7925 val_acc= 0.8233 time= 0.1456
Epoch: 0199 train_loss= 0.4364 train_acc= 0.9714 val_loss= 0.7910 val_acc= 0.8233 time= 0.1493
Epoch: 0200 train_loss= 0.4347 train_acc= 0.9714 val_loss= 0.7893 val_acc= 0.8233 time= 0.1391
Test set results: loss= 0.8438 accuracy= 0.8260
from keras-gcn.
Related Issues (20)
- name 'Y' is not defined
- multiple-graph HOT 2
- Model Fails when we change batch size HOT 4
- some problem need help HOT 1
- Face TypeError during load data HOT 2
- Cannot use GPU when output.shape[1] * nnz(a) > 2^31 HOT 10
- how to install it? No module named 'kegra'
- ValueError: setting an array element with a sequence. HOT 8
- I have multiple graph instance but they have different number of nodes.
- Using a `tf.Tensor` as a Python `bool` is not allowed in Graph execution HOT 3
- GCN apply for my own dataset but training_acc is low HOT 4
- TypeError: Using a `tf.Tensor` as a Python `bool` is not allowed. HOT 5
- Got error when fitting
- Got error when fitting
- Got error when using theano
- GCN on multiple graphs HOT 3
- Low accuracy about Cora dataset
- Can i use GCN for Information Extraction from a document?
- ValueError: Only provide the `shape` OR `batch_input_shape` argument to Input, not both at the same time. HOT 4
- Why does it increased in dimension after every layer?
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from keras-gcn.