{"id":420,"date":"2014-09-11T23:34:29","date_gmt":"2014-09-11T14:34:29","guid":{"rendered":"https:\/\/www.dogrow.net\/nnet\/?p=420"},"modified":"2025-04-24T02:35:20","modified_gmt":"2025-04-23T17:35:20","slug":"blog25","status":"publish","type":"post","link":"https:\/\/www.dogrow.net\/nnet\/blog25\/","title":{"rendered":"(25) cuda-convnet2\u3067MNIST\u81ea\u52d5\u8a8d\u8b58(\u305d\u306e1)"},"content":{"rendered":"<p><span class=\"my_fc_deeppinkB\">cuda-convnet2<\/span>\u4e0a\u3067 <a href=\"https:\/\/www.dogrow.net\/nnet\/blog15\/\">(15) cuda-convnet\u3067MNIST\u81ea\u52d5\u8a8d\u8b58(\u305d\u306e2)<\/a> \u3068\u307b\u307c\u540c\u3058\u30cd\u30c3\u30c8\u30ef\u30fc\u30af\u69cb\u6210\u3067\u5b66\u7fd2\u3055\u305b\u3066\u307f\u305f\u3002<\/p>\n<p>\u300c\u307e\u3063\u305f\u304f\u540c\u3058\u300d \u3067\u306f\u306a\u304f \u300c\u307b\u307c\u540c\u3058\u300d \u306a\u306e\u306f\u3001\u540c\u3058\u306b\u51fa\u6765\u306a\u3044\u70b9\u304c\u3042\u3063\u305f\u305f\u3081&#8230;<\/p>\n<p>cuda-convnet2 \u3067\u306f\u3001convolution\u5c64\u306e\u30d5\u30a3\u30eb\u30bf\u30fc\u6570 <span class=\"my_fc_deeppinkB\">filters<\/span> \u306e\u5024\u304c <span class=\"my_fc_deeppinkB\">32\u306e\u500d\u6570<\/span>\u3067\u306a\u3044\u3068\u30a8\u30e9\u30fc\u306b\u306a\u308b\u3002<br \/>\ncuda-convnet \u306e\u3068\u304d\u3068\u540c\u3058 filters=16 \u3092\u6307\u5b9a\u3057\u305f\u3089\u3001\u4ee5\u4e0b\u306e\u3088\u3046\u306a\u30a8\u30e9\u30fc\u304c\u51fa\u3066\u6b62\u307e\u3063\u305f\u3002<\/p>\n<pre>1.1 (0.00%)...python: src\/img_acts.cu:1204: void _imgActs(NVMatrix&amp;, NVMatrix&amp;, NVMatrix&amp;,\r\nint, int, int, int, int, int, int, float, float, bool):\r\nAssertion `numFilters % (32*numGroups) == 0' failed.\r\n<\/pre>\n<h1 class=\"my_h\">1. \u6e96\u5099<\/h1>\n<p>(1) \u5165\u529b\u30c7\u30fc\u30bf\u306f<a href=\"https:\/\/www.dogrow.net\/nnet\/?p=179\">(14) cuda-convnet\u3067MNIST\u81ea\u52d5\u8a8d\u8b58(\u305d\u306e1)<\/a> \u3067\u4f5c\u6210\u3057\u305f\u3082\u306e\u3092\u305d\u306e\u307e\u307e\u4f7f\u7528<br \/>\n(2) <span class=\"my_fc_deeppinkB\">convnet.py<\/span> \u306b <span class=\"my_fc_deeppinkB\">MNIST\u7528data provider <\/span>\u3092\u8ffd\u52a0<\/p>\n<pre>from convdata import ImageDataProvider, CIFARDataProvider, DummyConvNetLogRegDataProvider, MNISTDataProvider\r\n :\r\nDataProvider.register_data_provider('MNIST', 'MNIST data provider', MNISTDataProvider)\r\n<\/pre>\n<p>(3) <span class=\"my_fc_deeppinkB\">convdata.py <\/span>\u306b <span class=\"my_fc_deeppinkB\">MNIST\u7528data provider <\/span>\u3092\u8ffd\u52a0\u5b9f\u88c5<\/p>\n<pre>class MNISTDataProvider(LabeledDataProvider):\r\n :\r\n<\/pre>\n<p>(4) \u30cd\u30c3\u30c8\u30ef\u30fc\u30af\u5b9a\u7fa9\u30d5\u30a1\u30a4\u30eb\u3092\u4f5c\u6210(CIFAR10\u7528\u306e\u3082\u306e\u3092\u30b3\u30d4\u30fc\u3057\u3066\u7de8\u96c6)<br \/>\n<span class=\"my_fc_blueB\"> layers-MNIST.cfg<\/span><\/p>\n<pre>[data]\r\ntype=data\r\ndataIdx=0\r\n\r\n[labels]\r\ntype=data\r\ndataIdx=1\r\n\r\n[conv1]\r\ntype=conv\r\ninputs=data\r\nchannels=1\r\nfilters=32\r\npadding=0\r\nstride=1\r\nfilterSize=5\r\nneuron=tanh[1,1]\r\ninitW=0.0001\r\nsumWidth=4\r\nsharedBiases=1\r\ngpu=0\r\n\r\n[pool1]\r\ntype=pool\r\npool=max\r\ninputs=conv1\r\nstart=0\r\nsizeX=2\r\nstride=2\r\noutputsX=0\r\nchannels=32\r\n\r\n[conv2]\r\ntype=conv\r\ninputs=pool1\r\nfilters=32\r\npadding=0\r\nstride=1\r\nfilterSize=5\r\nchannels=32\r\nneuron=tanh[1,1]\r\ninitW=0.01\r\nsumWidth=2\r\nsharedBiases=1\r\n\r\n[pool2]\r\ntype=pool\r\npool=avg\r\ninputs=conv2\r\nstart=0\r\nsizeX=2\r\nstride=2\r\noutputsX=0\r\nchannels=32\r\n\r\n[fcOut]\r\ntype=fc\r\noutputs=10\r\ninputs=pool2\r\ninitW=0.01\r\ninitB=0.1\r\n\r\n[probs]\r\ntype=softmax\r\ninputs=fcOut\r\n\r\n[logprob]\r\ntype=cost.logreg\r\ninputs=labels,probs\r\ngpu=0\r\n<\/pre>\n<p><span class=\"my_fc_blueB\">layer-params-MNIST.cfg<\/span><\/p>\n<pre>[conv1]\r\nepsW=0.01\r\nepsB=0.01\r\nmomW=0.9\r\nmomB=0.9\r\nwc=0.0001\r\n\r\n[conv2]\r\nepsW=0.01\r\nepsB=0.01\r\nmomW=0.9\r\nmomB=0.9\r\nwc=0.0001\r\n\r\n[fcOut]\r\nepsW=0.01\r\nepsB=0.01\r\nmomW=0.9\r\nmomB=0.9\r\nwc=0.0001\r\n\r\n[logprob]\r\ncoeff=1\r\n<\/pre>\n<h1 class=\"my_h\">2. \u5b9f\u884c\u7d50\u679c<\/h1>\n<p><span class=\"my_fc_deeppinkB\">10epochs<\/span> \u3067 <span class=\"my_fc_deeppinkB\">97.0% <\/span>\u306e\u6b63\u89e3\u7387\u3060\u3063\u305f\u3002<\/p>\n<pre>=========================\r\nRunning on CUDA device(s) 0\r\nCurrent time: Thu Sep 11 23:26:07 2014\r\nSaving checkpoints to \/home\/user\/cuda\/cuda-convnet2\/save\/MNIST\/ConvNet__2014-09-11_23.26.06\r\n=========================\r\n1.1 (0.00%)... logprob:  1.172366, 0.338300, 0.338300 (0.408 sec)\r\n1.2 (1.67%)... logprob:  0.644550, 0.195300, 0.195300 (0.283 sec)\r\n1.3 (3.33%)... logprob:  0.534813, 0.158900, 0.158900 (0.261 sec)\r\n1.4 (5.00%)... logprob:  0.490603, 0.137000, 0.137000 (0.266 sec)\r\n1.5 (6.67%)... logprob:  0.414907, 0.118000, 0.118000 (0.270 sec)\r\n1.6 (8.33%)... logprob:  0.323441, 0.090700, 0.090700\r\n======================Test output======================\r\nlogprob:  0.331363, 0.096700, 0.096700\r\n----------------------Averages-------------------------\r\nlogprob:  0.331363, 0.096700, 0.096700\r\n-------------------------------------------------------\r\nLayer 'conv1' weights[0]: 5.603852e-02 [4.257733e-04] [7.597867e-03]\r\nLayer 'conv1' biases: 4.830383e-03 [1.214175e-05]\r\nLayer 'conv2' weights[0]: 1.724966e-02 [6.070063e-05] [3.518947e-03]\r\nLayer 'conv2' biases: 1.526958e-02 [5.254558e-05]\r\nLayer 'fcOut' weights[0]: 5.033513e-02 [1.485135e-04] [2.950494e-03]\r\nLayer 'fcOut' biases: 1.051513e-01 [2.423674e-04]\r\n-------------------------------------------------------\r\nSaved checkpoint to \/home\/user\/cuda\/cuda-convnet2\/save\/MNIST\/ConvNet__2014-09-11_23.26.06\r\n======================================================= (0.386 sec)\r\n2.1 (10.00%)... logprob:  0.318453, 0.086400, 0.086400 (0.262 sec)\r\n2.2 (11.67%)... logprob:  0.310761, 0.089500, 0.089500 (0.272 sec)\r\n2.3 (13.33%)... logprob:  0.286774, 0.080500, 0.080500 (0.277 sec)\r\n2.4 (15.00%)... logprob:  0.278840, 0.075800, 0.075800 (0.268 sec)\r\n2.5 (16.67%)... logprob:  0.254464, 0.074000, 0.074000 (0.260 sec)\r\n2.6 (18.33%)... logprob:  0.205112, 0.055300, 0.055300\r\n======================Test output======================\r\nlogprob:  0.212422, 0.060000, 0.060000\r\n----------------------Averages-------------------------\r\nlogprob:  0.212422, 0.060000, 0.060000\r\n-------------------------------------------------------\r\nLayer 'conv1' weights[0]: 7.594936e-02 [4.058031e-04] [5.343074e-03]\r\nLayer 'conv1' biases: 6.179797e-03 [1.451384e-05]\r\nLayer 'conv2' weights[0]: 2.133178e-02 [6.337569e-05] [2.970952e-03]\r\nLayer 'conv2' biases: 2.470282e-02 [9.729735e-05]\r\nLayer 'fcOut' weights[0]: 6.420852e-02 [1.101083e-04] [1.714855e-03]\r\nLayer 'fcOut' biases: 1.128721e-01 [1.821996e-04]\r\n-------------------------------------------------------\r\nSaved checkpoint to \/home\/user\/cuda\/cuda-convnet2\/save\/MNIST\/ConvNet__2014-09-11_23.26.06\r\n======================================================= (0.381 sec)\r\n3.1 (20.00%)... logprob:  0.218257, 0.060000, 0.060000 (0.261 sec)\r\n3.2 (21.67%)... logprob:  0.221481, 0.064700, 0.064700 (0.260 sec)\r\n3.3 (23.33%)... logprob:  0.210569, 0.059100, 0.059100 (0.269 sec)\r\n3.4 (25.00%)... logprob:  0.210470, 0.059600, 0.059600 (0.280 sec)\r\n3.5 (26.67%)... logprob:  0.197011, 0.057800, 0.057800 (0.276 sec)\r\n3.6 (28.33%)... logprob:  0.163356, 0.045600, 0.045600\r\n======================Test output======================\r\nlogprob:  0.174262, 0.049500, 0.049500\r\n----------------------Averages-------------------------\r\nlogprob:  0.174262, 0.049500, 0.049500\r\n-------------------------------------------------------\r\nLayer 'conv1' weights[0]: 8.960275e-02 [4.249032e-04] [4.742078e-03]\r\nLayer 'conv1' biases: 7.505222e-03 [1.565793e-05]\r\nLayer 'conv2' weights[0]: 2.407989e-02 [6.371664e-05] [2.646052e-03]\r\nLayer 'conv2' biases: 3.122083e-02 [1.076589e-04]\r\nLayer 'fcOut' weights[0]: 7.343277e-02 [1.054850e-04] [1.436484e-03]\r\nLayer 'fcOut' biases: 1.184271e-01 [2.027215e-04]\r\n-------------------------------------------------------\r\nSaved checkpoint to \/home\/user\/cuda\/cuda-convnet2\/save\/MNIST\/ConvNet__2014-09-11_23.26.06\r\n======================================================= (0.390 sec)\r\n4.1 (30.00%)... logprob:  0.177056, 0.049900, 0.049900 (0.267 sec)\r\n4.2 (31.67%)... logprob:  0.177898, 0.052100, 0.052100 (0.260 sec)\r\n4.3 (33.33%)... logprob:  0.175247, 0.050700, 0.050700 (0.268 sec)\r\n4.4 (35.00%)... logprob:  0.171205, 0.047300, 0.047300 (0.276 sec)\r\n4.5 (36.67%)... logprob:  0.165775, 0.048300, 0.048300 (0.277 sec)\r\n4.6 (38.33%)... logprob:  0.138243, 0.037900, 0.037900\r\n======================Test output======================\r\nlogprob:  0.145980, 0.043900, 0.043900\r\n----------------------Averages-------------------------\r\nlogprob:  0.145980, 0.043900, 0.043900\r\n-------------------------------------------------------\r\nLayer 'conv1' weights[0]: 1.005846e-01 [2.952142e-04] [2.934983e-03]\r\nLayer 'conv1' biases: 8.529577e-03 [8.077021e-06]\r\nLayer 'conv2' weights[0]: 2.600699e-02 [4.605853e-05] [1.771006e-03]\r\nLayer 'conv2' biases: 3.634325e-02 [5.782335e-05]\r\nLayer 'fcOut' weights[0]: 8.008937e-02 [8.605960e-05] [1.074545e-03]\r\nLayer 'fcOut' biases: 1.239006e-01 [1.301457e-04]\r\n-------------------------------------------------------\r\nSaved checkpoint to \/home\/user\/cuda\/cuda-convnet2\/save\/MNIST\/ConvNet__2014-09-11_23.26.06\r\n======================================================= (0.394 sec)\r\n5.1 (40.00%)... logprob:  0.154051, 0.043600, 0.043600 (0.265 sec)\r\n5.2 (41.67%)... logprob:  0.152657, 0.042800, 0.042800 (0.260 sec)\r\n5.3 (43.33%)... logprob:  0.157166, 0.045600, 0.045600 (0.269 sec)\r\n5.4 (45.00%)... logprob:  0.156089, 0.043000, 0.043000 (0.275 sec)\r\n5.5 (46.67%)... logprob:  0.151101, 0.044100, 0.044100 (0.279 sec)\r\n5.6 (48.33%)... logprob:  0.127177, 0.034000, 0.034000\r\n======================Test output======================\r\nlogprob:  0.134478, 0.040300, 0.040300\r\n----------------------Averages-------------------------\r\nlogprob:  0.134478, 0.040300, 0.040300\r\n-------------------------------------------------------\r\nLayer 'conv1' weights[0]: 1.092488e-01 [3.290545e-04] [3.011972e-03]\r\nLayer 'conv1' biases: 9.419627e-03 [9.917402e-06]\r\nLayer 'conv2' weights[0]: 2.765511e-02 [5.169003e-05] [1.869095e-03]\r\nLayer 'conv2' biases: 4.023369e-02 [7.040862e-05]\r\nLayer 'fcOut' weights[0]: 8.545814e-02 [8.551481e-05] [1.000663e-03]\r\nLayer 'fcOut' biases: 1.289145e-01 [1.510616e-04]\r\n-------------------------------------------------------\r\nSaved checkpoint to \/home\/user\/cuda\/cuda-convnet2\/save\/MNIST\/ConvNet__2014-09-11_23.26.06\r\n======================================================= (0.390 sec)\r\n6.1 (50.00%)... logprob:  0.138790, 0.039100, 0.039100 (0.256 sec)\r\n6.2 (51.67%)... logprob:  0.136038, 0.040000, 0.040000 (0.267 sec)\r\n6.3 (53.33%)... logprob:  0.140736, 0.043300, 0.043300 (0.271 sec)\r\n6.4 (55.00%)... logprob:  0.140494, 0.040500, 0.040500 (0.257 sec)\r\n6.5 (56.67%)... logprob:  0.135578, 0.042900, 0.042900 (0.260 sec)\r\n6.6 (58.33%)... logprob:  0.117202, 0.034200, 0.034200\r\n======================Test output======================\r\nlogprob:  0.125607, 0.037000, 0.037000\r\n----------------------Averages-------------------------\r\nlogprob:  0.125607, 0.037000, 0.037000\r\n-------------------------------------------------------\r\nLayer 'conv1' weights[0]: 1.185013e-01 [3.215680e-04] [2.713624e-03]\r\nLayer 'conv1' biases: 1.045737e-02 [8.683801e-06]\r\nLayer 'conv2' weights[0]: 2.906979e-02 [5.124793e-05] [1.762928e-03]\r\nLayer 'conv2' biases: 4.338235e-02 [6.073256e-05]\r\nLayer 'fcOut' weights[0]: 8.998768e-02 [8.469566e-05] [9.411917e-04]\r\nLayer 'fcOut' biases: 1.330563e-01 [1.375708e-04]\r\n-------------------------------------------------------\r\nSaved checkpoint to \/home\/user\/cuda\/cuda-convnet2\/save\/MNIST\/ConvNet__2014-09-11_23.26.06\r\n======================================================= (0.389 sec)\r\n7.1 (60.00%)... logprob:  0.127772, 0.036500, 0.036500 (0.264 sec)\r\n7.2 (61.67%)... logprob:  0.129048, 0.035300, 0.035300 (0.264 sec)\r\n7.3 (63.33%)... logprob:  0.126389, 0.036900, 0.036900 (0.257 sec)\r\n7.4 (65.00%)... logprob:  0.126924, 0.036500, 0.036500 (0.258 sec)\r\n7.5 (66.67%)... logprob:  0.124740, 0.039200, 0.039200 (0.262 sec)\r\n7.6 (68.33%)... logprob:  0.107535, 0.031300, 0.031300\r\n======================Test output======================\r\nlogprob:  0.117275, 0.036500, 0.036500\r\n----------------------Averages-------------------------\r\nlogprob:  0.117275, 0.036500, 0.036500\r\n-------------------------------------------------------\r\nLayer 'conv1' weights[0]: 1.253645e-01 [3.182444e-04] [2.538553e-03]\r\nLayer 'conv1' biases: 1.130659e-02 [9.655061e-06]\r\nLayer 'conv2' weights[0]: 3.027309e-02 [5.097299e-05] [1.683772e-03]\r\nLayer 'conv2' biases: 4.638661e-02 [6.874600e-05]\r\nLayer 'fcOut' weights[0]: 9.390774e-02 [8.618318e-05] [9.177431e-04]\r\nLayer 'fcOut' biases: 1.369651e-01 [1.598123e-04]\r\n-------------------------------------------------------\r\nSaved checkpoint to \/home\/user\/cuda\/cuda-convnet2\/save\/MNIST\/ConvNet__2014-09-11_23.26.06\r\n======================================================= (0.395 sec)\r\n8.1 (70.00%)... logprob:  0.118632, 0.034100, 0.034100 (0.279 sec)\r\n8.2 (71.67%)... logprob:  0.116539, 0.033800, 0.033800 (0.284 sec)\r\n8.3 (73.33%)... logprob:  0.119332, 0.033300, 0.033300 (0.263 sec)\r\n8.4 (75.00%)... logprob:  0.117164, 0.035000, 0.035000 (0.259 sec)\r\n8.5 (76.67%)... logprob:  0.115454, 0.034100, 0.034100 (0.265 sec)\r\n8.6 (78.33%)... logprob:  0.098626, 0.027800, 0.027800\r\n======================Test output======================\r\nlogprob:  0.111595, 0.035600, 0.035600\r\n----------------------Averages-------------------------\r\nlogprob:  0.111595, 0.035600, 0.035600\r\n-------------------------------------------------------\r\nLayer 'conv1' weights[0]: 1.320663e-01 [2.742416e-04] [2.076545e-03]\r\nLayer 'conv1' biases: 1.205624e-02 [9.303420e-06]\r\nLayer 'conv2' weights[0]: 3.131152e-02 [4.480714e-05] [1.431011e-03]\r\nLayer 'conv2' biases: 4.911382e-02 [6.194661e-05]\r\nLayer 'fcOut' weights[0]: 9.736039e-02 [8.148113e-05] [8.369022e-04]\r\nLayer 'fcOut' biases: 1.395094e-01 [1.539289e-04]\r\n-------------------------------------------------------\r\nSaved checkpoint to \/home\/user\/cuda\/cuda-convnet2\/save\/MNIST\/ConvNet__2014-09-11_23.26.06\r\n======================================================= (0.375 sec)\r\n9.1 (80.00%)... logprob:  0.109055, 0.030600, 0.030600 (0.263 sec)\r\n9.2 (81.67%)... logprob:  0.108679, 0.031500, 0.031500 (0.276 sec)\r\n9.3 (83.33%)... logprob:  0.114341, 0.034500, 0.034500 (0.270 sec)\r\n9.4 (85.00%)... logprob:  0.113470, 0.034200, 0.034200 (0.264 sec)\r\n9.5 (86.67%)... logprob:  0.113821, 0.034900, 0.034900 (0.260 sec)\r\n9.6 (88.33%)... logprob:  0.097121, 0.027200, 0.027200\r\n======================Test output======================\r\nlogprob:  0.109638, 0.036300, 0.036300\r\n----------------------Averages-------------------------\r\nlogprob:  0.109638, 0.036300, 0.036300\r\n-------------------------------------------------------\r\nLayer 'conv1' weights[0]: 1.373190e-01 [3.058636e-04] [2.227395e-03]\r\nLayer 'conv1' biases: 1.302156e-02 [9.149435e-06]\r\nLayer 'conv2' weights[0]: 3.226066e-02 [4.938124e-05] [1.530695e-03]\r\nLayer 'conv2' biases: 5.098233e-02 [6.026183e-05]\r\nLayer 'fcOut' weights[0]: 1.004117e-01 [8.105130e-05] [8.071900e-04]\r\nLayer 'fcOut' biases: 1.419481e-01 [1.483235e-04]\r\n-------------------------------------------------------\r\nSaved checkpoint to \/home\/user\/cuda\/cuda-convnet2\/save\/MNIST\/ConvNet__2014-09-11_23.26.06\r\n======================================================= (0.374 sec)\r\n10.1 (90.00%)... logprob:  0.109652, 0.031600, 0.031600 (0.265 sec)\r\n10.2 (91.67%)... logprob:  0.106537, 0.031300, 0.031300 (0.274 sec)\r\n10.3 (93.33%)... logprob:  0.108742, 0.031500, 0.031500 (0.277 sec)\r\n10.4 (95.00%)... logprob:  0.107402, 0.031800, 0.031800 (0.281 sec)\r\n10.5 (96.67%)... logprob:  0.108577, 0.033200, 0.033200 (0.265 sec)\r\n10.6 (98.33%)... logprob:  0.089522, 0.025200, 0.025200\r\n======================Test output======================\r\nlogprob:  0.103471, 0.032400, 0.032400\r\n----------------------Averages-------------------------\r\nlogprob:  0.103471, 0.032400, 0.032400\r\n-------------------------------------------------------\r\nLayer 'conv1' weights[0]: 1.426484e-01 [3.130984e-04] [2.194896e-03]\r\nLayer 'conv1' biases: 1.376614e-02 [7.678883e-06]\r\nLayer 'conv2' weights[0]: 3.318742e-02 [4.514968e-05] [1.360446e-03]\r\nLayer 'conv2' biases: 5.307174e-02 [5.835572e-05]\r\nLayer 'fcOut' weights[0]: 1.032455e-01 [6.837120e-05] [6.622197e-04]\r\nLayer 'fcOut' biases: 1.431666e-01 [1.101904e-04]\r\n-------------------------------------------------------\r\nSaved checkpoint to \/home\/user\/cuda\/cuda-convnet2\/save\/MNIST\/ConvNet__2014-09-11_23.26.06\r\n======================================================= (0.386 sec)\r\n11.1 (100.00%)... logprob:  0.102062, 0.029500, 0.029500 (0.265 sec)\r\n<\/pre>\n<hr class=\"my_hr_bottom\">\n","protected":false},"excerpt":{"rendered":"<p>cuda-convnet2\u4e0a\u3067 (15) cuda-convnet\u3067MNIST\u81ea\u52d5\u8a8d\u8b58(\u305d\u306e2) \u3068\u307b\u307c\u540c\u3058\u30cd\u30c3\u30c8\u30ef\u30fc\u30af\u69cb\u6210\u3067\u5b66\u7fd2\u3055\u305b\u3066\u307f\u305f\u3002 \u300c\u307e\u3063\u305f\u304f\u540c\u3058\u300d \u3067\u306f\u306a\u304f \u300c\u307b\u307c\u540c\u3058\u300d \u306a\u306e\u306f\u3001\u540c\u3058\u306b\u51fa\u6765\u306a\u3044\u70b9\u304c\u3042\u3063\u305f\u305f\u2026 <span class=\"read-more\"><a href=\"https:\/\/www.dogrow.net\/nnet\/blog25\/\">\u7d9a\u304d\u3092\u8aad\u3080 &raquo;<\/a><\/span><\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[8,10,11,18],"tags":[],"class_list":["post-420","post","type-post","status-publish","format-standard","hentry","category-cuda","category-cuda-convnet","category-cuda-convnet2","category-mnist"],"views":2750,"amp_enabled":true,"_links":{"self":[{"href":"https:\/\/www.dogrow.net\/nnet\/wp-json\/wp\/v2\/posts\/420","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.dogrow.net\/nnet\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.dogrow.net\/nnet\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.dogrow.net\/nnet\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.dogrow.net\/nnet\/wp-json\/wp\/v2\/comments?post=420"}],"version-history":[{"count":14,"href":"https:\/\/www.dogrow.net\/nnet\/wp-json\/wp\/v2\/posts\/420\/revisions"}],"predecessor-version":[{"id":776,"href":"https:\/\/www.dogrow.net\/nnet\/wp-json\/wp\/v2\/posts\/420\/revisions\/776"}],"wp:attachment":[{"href":"https:\/\/www.dogrow.net\/nnet\/wp-json\/wp\/v2\/media?parent=420"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.dogrow.net\/nnet\/wp-json\/wp\/v2\/categories?post=420"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.dogrow.net\/nnet\/wp-json\/wp\/v2\/tags?post=420"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}