experiment.ja.json

{
 "<h1><a href=\"index.html\">Evidential Deep Learning to Quantify Classification Uncertainty</a> Experiment</h1>\n<p>This trains a model based on <a href=\"index.html\">Evidential Deep Learning to Quantify Classification Uncertainty</a>  on MNIST dataset.</p>\n": "<h1><a href=\"index.html\">\u5206\u985e\u4e0d\u78ba\u5b9a\u6027\u5b9f\u9a13\u3092\u5b9a\u91cf\u5316\u3059\u308b\u305f\u3081\u306e\u30a8\u30d3\u30c7\u30f3\u30b7\u30e3\u30eb\u30c7\u30a3\u30fc\u30d7\u30e9\u30fc\u30cb\u30f3\u30b0</a></h1>\n<p>\u3053\u308c\u306b\u3088\u308a\u3001<a href=\"index.html\">\u30a8\u30d3\u30c7\u30f3\u30b7\u30e3\u30eb\u30c7\u30a3\u30fc\u30d7\u30e9\u30fc\u30cb\u30f3\u30b0\u306b\u57fa\u3065\u304f\u30e2\u30c7\u30eb\u3092\u30c8\u30ec\u30fc\u30cb\u30f3\u30b0\u3057\u3066\u3001MNIST\u30c7\u30fc\u30bf\u30bb\u30c3\u30c8\u306e\u5206\u985e\u306e\u4e0d\u78ba\u5b9f\u6027\u3092\u5b9a\u91cf\u5316\u3057\u307e\u3059</a>\u3002</p>\n",
 "<h2>Configurations</h2>\n<p>We use <a href=\"../../experiments/mnist.html#MNISTConfigs\"><span translate=no>_^_0_^_</span></a> configurations.</p>\n": "<h2>\u30b3\u30f3\u30d5\u30a3\u30ae\u30e5\u30ec\u30fc\u30b7\u30e7\u30f3</h2>\n<p><a href=\"../../experiments/mnist.html#MNISTConfigs\"><span translate=no>_^_0_^_</span></a>\u69cb\u6210\u3092\u4f7f\u7528\u3057\u307e\u3059\u3002</p>\n",
 "<h2>LeNet based model fro MNIST classification</h2>\n": "<h2>MINST \u5206\u985e\u7528\u306e Lenet \u30d9\u30fc\u30b9\u306e\u30e2\u30c7\u30eb</h2>\n",
 "<h3>Create model</h3>\n": "<h3>\u30e2\u30c7\u30eb\u4f5c\u6210</h3>\n",
 "<h3>Initialization</h3>\n": "<h3>\u521d\u671f\u5316</h3>\n",
 "<h3>KL Divergence Loss Coefficient Schedule</h3>\n": "<h3>KL \u30c0\u30a4\u30d0\u30fc\u30b8\u30a7\u30f3\u30b9\u640d\u5931\u4fc2\u6570\u30b9\u30b1\u30b8\u30e5\u30fc\u30eb</h3>\n",
 "<h3>Training or validation step</h3>\n": "<h3>\u30c8\u30ec\u30fc\u30cb\u30f3\u30b0\u307e\u305f\u306f\u691c\u8a3c\u30b9\u30c6\u30c3\u30d7</h3>\n",
 "<p> </p>\n": "<p></p>\n",
 "<p>&#x27;loss_func&#x27;: &#x27;max_likelihood_loss&#x27;, &#x27;loss_func&#x27;: &#x27;cross_entropy_bayes_risk&#x27;, </p>\n": "<p>'loss_func': 'max_likelihood_loss', 'loss_func': 'cross_entropy_bayes_risk',</p>\n",
 "<p><a href=\"index.html#CrossEntropyBayesRisk\">Cross Entropy Bayes Risk</a> </p>\n": "<p><a href=\"index.html#CrossEntropyBayesRisk\">\u30af\u30ed\u30b9\u30a8\u30f3\u30c8\u30ed\u30d4\u30fc\u30d9\u30a4\u30ba\u30ea\u30b9\u30af</a></p>\n",
 "<p><a href=\"index.html#KLDivergenceLoss\">KL Divergence regularization</a> </p>\n": "<p><a href=\"index.html#KLDivergenceLoss\">KL \u30c0\u30a4\u30d0\u30fc\u30b8\u30a7\u30f3\u30b9\u6b63\u5247\u5316</a></p>\n",
 "<p><a href=\"index.html#MaximumLikelihoodLoss\">Maximum Likelihood Loss</a> </p>\n": "<p><a href=\"index.html#MaximumLikelihoodLoss\">\u6700\u5927\u78ba\u7387\u640d\u5931</a></p>\n",
 "<p><a href=\"index.html#SquaredErrorBayesRisk\">Squared Error Bayes Risk</a> </p>\n": "<p><a href=\"index.html#SquaredErrorBayesRisk\">\u4e8c\u4e57\u8aa4\u5dee\u30d9\u30a4\u30ba\u30ea\u30b9\u30af</a></p>\n",
 "<p><a href=\"index.html#TrackStatistics\">Stats module</a> for tracking </p>\n": "<p><a href=\"index.html#TrackStatistics\">\u8ffd\u8de1\u7528\u7d71\u8a08\u30e2\u30b8\u30e5\u30fc\u30eb</a></p>\n",
 "<p><span translate=no>_^_0_^_</span> max-pooling </p>\n": "<p><span translate=no>_^_0_^_</span>\u30de\u30c3\u30af\u30b9\u30d7\u30fc\u30ea\u30f3\u30b0</p>\n",
 "<p>Apply dropout </p>\n": "<p>\u30c9\u30ed\u30c3\u30d7\u30a2\u30a6\u30c8\u3092\u9069\u7528</p>\n",
 "<p>Apply final layer and return </p>\n": "<p>\u6700\u7d42\u30ec\u30a4\u30e4\u30fc\u3092\u9069\u7528\u3057\u3066\u623b\u308b</p>\n",
 "<p>Apply first convolution and max pooling. The result has shape <span translate=no>_^_0_^_</span> </p>\n": "<p>\u6700\u521d\u306e\u30b3\u30f3\u30dc\u30ea\u30e5\u30fc\u30b7\u30e7\u30f3\u3068\u30de\u30c3\u30af\u30b9\u30d7\u30fc\u30ea\u30f3\u30b0\u3092\u9069\u7528\u3057\u307e\u3059\u3002\u7d50\u679c\u306b\u306f\u5f62\u304c\u3042\u308a\u307e\u3059 <span translate=no>_^_0_^_</span></p>\n",
 "<p>Apply hidden layer </p>\n": "<p>\u96a0\u3057\u30ec\u30a4\u30e4\u30fc\u3092\u9069\u7528</p>\n",
 "<p>Apply second convolution and max pooling. The result has shape <span translate=no>_^_0_^_</span> </p>\n": "<p>2 \u56de\u76ee\u306e\u30b3\u30f3\u30dc\u30ea\u30e5\u30fc\u30b7\u30e7\u30f3\u3068\u6700\u5927\u30d7\u30fc\u30ea\u30f3\u30b0\u3092\u9069\u7528\u3057\u307e\u3059\u3002\u7d50\u679c\u306b\u306f\u5f62\u304c\u3042\u308a\u307e\u3059 <span translate=no>_^_0_^_</span></p>\n",
 "<p>Calculate KL Divergence regularization loss </p>\n": "<p>KL \u30c0\u30a4\u30d0\u30fc\u30b8\u30a7\u30f3\u30b9\u6b63\u5247\u5316\u640d\u5931\u306e\u8a08\u7b97</p>\n",
 "<p>Calculate gradients </p>\n": "<p>\u52fe\u914d\u306e\u8a08\u7b97</p>\n",
 "<p>Calculate loss </p>\n": "<p>\u640d\u5931\u306e\u8a08\u7b97</p>\n",
 "<p>Clear the gradients </p>\n": "<p>\u30b0\u30e9\u30c7\u30fc\u30b7\u30e7\u30f3\u3092\u30af\u30ea\u30a2</p>\n",
 "<p>Create a <a href=\"https://docs.labml.ai/api/helpers.html#labml_helpers.schedule.Piecewise\">relative piecewise schedule</a> </p>\n": "<p><a href=\"https://docs.labml.ai/api/helpers.html#labml_helpers.schedule.Piecewise\">\u76f8\u5bfe\u7684\u306a\u533a\u5206\u7684\u30b9\u30b1\u30b8\u30e5\u30fc\u30eb\u306e\u4f5c\u6210</a></p>\n",
 "<p>Create configurations </p>\n": "<p>\u69cb\u6210\u306e\u4f5c\u6210</p>\n",
 "<p>Create experiment </p>\n": "<p>\u5b9f\u9a13\u3092\u4f5c\u6210</p>\n",
 "<p>Dropout </p>\n": "<p>\u30c9\u30ed\u30c3\u30d7\u30a2\u30a6\u30c8</p>\n",
 "<p>Dropout for the hidden layer </p>\n": "<p>\u96a0\u3057\u30ec\u30a4\u30e4\u30fc\u306e\u30c9\u30ed\u30c3\u30d7\u30a2\u30a6\u30c8</p>\n",
 "<p>Final fully connected layer to output evidence for <span translate=no>_^_0_^_</span> classes. The ReLU or Softplus activation is applied to this outside the model to get the non-negative evidence </p>\n": "<p><span translate=no>_^_0_^_</span>\u30af\u30e9\u30b9\u306e\u30a8\u30d3\u30c7\u30f3\u30b9\u3092\u51fa\u529b\u3059\u308b\u305f\u3081\u306e\u6700\u5f8c\u306e\u5b8c\u5168\u63a5\u7d9a\u30ec\u30a4\u30e4\u30fc\u3002\u3053\u308c\u306bReLU\u307e\u305f\u306fSoftplus\u30a2\u30af\u30c6\u30a3\u30d9\u30fc\u30b7\u30e7\u30f3\u3092\u30e2\u30c7\u30eb\u5916\u3067\u9069\u7528\u3059\u308b\u3068\u3001\u975e\u9670\u6027\u30a8\u30d3\u30c7\u30f3\u30b9\u304c\u5f97\u3089\u308c\u307e\u3059</p>\u3002\n",
 "<p>First <span translate=no>_^_0_^_</span> convolution layer </p>\n": "<p><span translate=no>_^_0_^_</span>\u6700\u521d\u306e\u7573\u307f\u8fbc\u307f\u5c64</p>\n",
 "<p>First fully-connected layer that maps to <span translate=no>_^_0_^_</span> features </p>\n": "<p>\u30d5\u30a3\u30fc\u30c1\u30e3\u306b\u30de\u30c3\u30d4\u30f3\u30b0\u3055\u308c\u308b\u6700\u521d\u306e\u5b8c\u5168\u63a5\u7d9a\u30ec\u30a4\u30e4\u30fc <span translate=no>_^_0_^_</span></p>\n",
 "<p>Flatten the tensor to shape <span translate=no>_^_0_^_</span> </p>\n": "<p>\u30c6\u30f3\u30bd\u30eb\u3092\u5e73\u3089\u306b\u3057\u3066\u5f62\u3092\u6574\u3048\u308b <span translate=no>_^_0_^_</span></p>\n",
 "<p>Get evidences <span translate=no>_^_0_^_</span> </p>\n": "<p>\u8a3c\u62e0\u3092\u53d6\u5f97 <span translate=no>_^_0_^_</span></p>\n",
 "<p>Get model outputs </p>\n": "<p>\u30e2\u30c7\u30eb\u51fa\u529b\u3092\u53d6\u5f97</p>\n",
 "<p>KL Divergence loss coefficient <span translate=no>_^_0_^_</span> </p>\n": "<p>KL \u767a\u6563\u640d\u5931\u4fc2\u6570 <span translate=no>_^_0_^_</span></p>\n",
 "<p>KL Divergence regularization coefficient schedule </p>\n": "<p>KL \u30c0\u30a4\u30d0\u30fc\u30b8\u30a7\u30f3\u30b9\u6b63\u5247\u5316\u4fc2\u6570\u30b9\u30b1\u30b8\u30e5\u30fc\u30eb</p>\n",
 "<p>Load configurations </p>\n": "<p>\u69cb\u6210\u3092\u30ed\u30fc\u30c9</p>\n",
 "<p>Module to convert the model output to non-zero evidences </p>\n": "<p>\u30e2\u30c7\u30eb\u51fa\u529b\u3092\u30bc\u30ed\u4ee5\u5916\u306e\u30a8\u30d3\u30c7\u30f3\u30b9\u306b\u5909\u63db\u3059\u308b\u30e2\u30b8\u30e5\u30fc\u30eb</p>\n",
 "<p>Move data to the device </p>\n": "<p>\u30c7\u30fc\u30bf\u3092\u30c7\u30d0\u30a4\u30b9\u306b\u79fb\u52d5</p>\n",
 "<p>One-hot coded targets </p>\n": "<p>\u30ef\u30f3\u30db\u30c3\u30c8\u30b3\u30fc\u30c7\u30a3\u30f3\u30b0\u30bf\u30fc\u30b2\u30c3\u30c8</p>\n",
 "<p>ReLU activation </p>\n": "<p>ReLU \u30a2\u30af\u30c6\u30a3\u30d9\u30fc\u30b7\u30e7\u30f3</p>\n",
 "<p>ReLU to calculate evidence </p>\n": "<p>\u30a8\u30d3\u30c7\u30f3\u30b9\u306e\u8a08\u7b97\u306b\u306f ReLU</p>\n",
 "<p>Save the tracked metrics </p>\n": "<p>\u8ffd\u8de1\u3057\u305f\u30e1\u30c8\u30ea\u30af\u30b9\u3092\u4fdd\u5b58\u3059\u308b</p>\n",
 "<p>Second <span translate=no>_^_0_^_</span> convolution layer </p>\n": "<p>2 <span translate=no>_^_0_^_</span> \u756a\u76ee\u306e\u7573\u307f\u8fbc\u307f\u5c64</p>\n",
 "<p>Set tracker configurations </p>\n": "<p>\u30c8\u30e9\u30c3\u30ab\u30fc\u69cb\u6210\u3092\u8a2d\u5b9a</p>\n",
 "<p>Softplus to calculate evidence </p>\n": "<p>\u8a3c\u62e0\u8a08\u7b97\u7528\u30bd\u30d5\u30c8\u30d7\u30e9\u30b9</p>\n",
 "<p>Start the experiment and run the training loop </p>\n": "<p>\u5b9f\u9a13\u3092\u958b\u59cb\u3057\u3001\u30c8\u30ec\u30fc\u30cb\u30f3\u30b0\u30eb\u30fc\u30d7\u3092\u5b9f\u884c\u3057\u307e\u3059</p>\n",
 "<p>Take optimizer step </p>\n": "<p>\u6700\u9069\u5316\u306e\u4e00\u6b69\u3092\u8e0f\u307f\u51fa\u3059</p>\n",
 "<p>Total loss </p>\n": "<p>\u7dcf\u640d\u5931</p>\n",
 "<p>Track statistics </p>\n": "<p>\u30c8\u30e9\u30c3\u30af\u7d71\u8a08</p>\n",
 "<p>Train the model </p>\n": "<p>\u30e2\u30c7\u30eb\u306e\u30c8\u30ec\u30fc\u30cb\u30f3\u30b0</p>\n",
 "<p>Training/Evaluation mode </p>\n": "<p>\u30c8\u30ec\u30fc\u30cb\u30f3\u30b0/\u8a55\u4fa1\u30e2\u30fc\u30c9</p>\n",
 "<p>Update global step (number of samples processed) when in training mode </p>\n": "<p>\u30c8\u30ec\u30fc\u30cb\u30f3\u30b0\u30e2\u30fc\u30c9\u6642\u306b\u30b0\u30ed\u30fc\u30d0\u30eb\u30b9\u30c6\u30c3\u30d7 (\u51e6\u7406\u3055\u308c\u305f\u30b5\u30f3\u30d7\u30eb\u6570) \u3092\u66f4\u65b0</p>\n",
 "<ul><li><span translate=no>_^_0_^_</span> is the batch of MNIST images of shape <span translate=no>_^_1_^_</span></li></ul>\n": "<ul><li><span translate=no>_^_0_^_</span>\u5f62\u72b6\u306eMNIST\u753b\u50cf\u306e\u30d0\u30c3\u30c1\u3067\u3059 <span translate=no>_^_1_^_</span></li></ul>\n",
 "Evidential Deep Learning to Quantify Classification Uncertainty Experiment": "\u5206\u985e\u4e0d\u78ba\u5b9a\u6027\u5b9f\u9a13\u3092\u5b9a\u91cf\u5316\u3059\u308b\u305f\u3081\u306e\u30a8\u30d3\u30c7\u30f3\u30b7\u30e3\u30eb\u30c7\u30a3\u30fc\u30d7\u30e9\u30fc\u30cb\u30f3\u30b0",
 "This trains is EDL model on MNIST": "\u3053\u306e\u5217\u8eca\u306fMNIST\u306eEDL\u30e2\u30c7\u30eb\u3067\u3059"
}