experiment.zh.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>\u57fa\u4e8e<a href=\"index.html\">\u8bc1\u636e\u7684\u6df1\u5ea6\u5b66\u4e60\u91cf\u5316\u5206\u7c7b\u4e0d\u786e\u5b9a\u6027</a>\u5b9e\u9a8c</h1>\n<p>\u8fd9\u5c06\u8bad\u7ec3\u4e00\u4e2a\u57fa\u4e8e<a href=\"index.html\">\u8bc1\u636e\u6df1\u5ea6\u5b66\u4e60\u7684\u6a21\u578b\uff0c\u4ee5\u91cf\u5316MNIST\u6570\u636e\u96c6\u4e0a\u7684\u5206\u7c7b\u4e0d\u786e\u5b9a\u6027</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>\u914d\u7f6e</h2>\n<p>\u6211\u4eec\u4f7f\u7528<a href=\"../../experiments/mnist.html#MNISTConfigs\"><span translate=no>_^_0_^_</span></a>\u914d\u7f6e\u3002</p>\n",
 "<h2>LeNet based model fro MNIST classification</h2>\n": "<h2>\u57fa\u4e8e LeNET \u7684 MINST \u5206\u7c7b\u6a21\u578b</h2>\n",
 "<h3>Create model</h3>\n": "<h3>\u521b\u5efa\u6a21\u578b</h3>\n",
 "<h3>Initialization</h3>\n": "<h3>\u521d\u59cb\u5316</h3>\n",
 "<h3>KL Divergence Loss Coefficient Schedule</h3>\n": "<h3>KL \u80cc\u79bb\u635f\u5931\u7cfb\u6570\u65f6\u95f4\u8868</h3>\n",
 "<h3>Training or validation step</h3>\n": "<h3>\u57f9\u8bad\u6216\u9a8c\u8bc1\u6b65\u9aa4</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'\uff1a'max_imilihood_loss'\uff0c'loss_func'\uff1a'cross_entropy_bayes_risk '\uff0c</p>\n",
 "<p><a href=\"index.html#CrossEntropyBayesRisk\">Cross Entropy Bayes Risk</a> </p>\n": "<p><a href=\"index.html#CrossEntropyBayesRisk\">\u4ea4\u53c9\u71b5\u8d1d\u53f6\u65af\u98ce\u9669</a></p>\n",
 "<p><a href=\"index.html#KLDivergenceLoss\">KL Divergence regularization</a> </p>\n": "<p><a href=\"index.html#KLDivergenceLoss\">KL \u5206\u6b67\u6b63\u5219\u5316</a></p>\n",
 "<p><a href=\"index.html#MaximumLikelihoodLoss\">Maximum Likelihood Loss</a> </p>\n": "<p><a href=\"index.html#MaximumLikelihoodLoss\">\u6700\u5927\u4f3c\u7136\u635f\u5931</a></p>\n",
 "<p><a href=\"index.html#SquaredErrorBayesRisk\">Squared Error Bayes Risk</a> </p>\n": "<p><a href=\"index.html#SquaredErrorBayesRisk\">\u5e73\u65b9\u8bef\u5dee\u8d1d\u53f6\u65af\u98ce\u9669</a></p>\n",
 "<p><a href=\"index.html#TrackStatistics\">Stats module</a> for tracking </p>\n": "<p>\u7528\u4e8e\u8ddf\u8e2a\u7684<a href=\"index.html#TrackStatistics\">\u7edf\u8ba1\u6a21\u5757</a></p>\n",
 "<p><span translate=no>_^_0_^_</span> max-pooling </p>\n": "<p><span translate=no>_^_0_^_</span>max-pooling</p>\n",
 "<p>Apply dropout </p>\n": "<p>\u7533\u8bf7\u9000\u5b66</p>\n",
 "<p>Apply final layer and return </p>\n": "<p>\u5e94\u7528\u6700\u540e\u4e00\u5c42\u7136\u540e\u8fd4\u56de</p>\n",
 "<p>Apply first convolution and max pooling. The result has shape <span translate=no>_^_0_^_</span> </p>\n": "<p>\u5e94\u7528\u7b2c\u4e00\u4e2a\u5377\u79ef\u548c\u6700\u5927\u6c60\u3002\u7ed3\u679c\u6709\u5f62\u72b6<span translate=no>_^_0_^_</span></p>\n",
 "<p>Apply hidden layer </p>\n": "<p>\u5e94\u7528\u9690\u85cf\u5c42</p>\n",
 "<p>Apply second convolution and max pooling. The result has shape <span translate=no>_^_0_^_</span> </p>\n": "<p>\u5e94\u7528\u7b2c\u4e8c\u4e2a\u5377\u79ef\u548c\u6700\u5927\u6c60\u3002\u7ed3\u679c\u6709\u5f62\u72b6<span translate=no>_^_0_^_</span></p>\n",
 "<p>Calculate KL Divergence regularization loss </p>\n": "<p>\u8ba1\u7b97 KL \u80cc\u79bb\u6b63\u5219\u5316\u635f\u5931</p>\n",
 "<p>Calculate gradients </p>\n": "<p>\u8ba1\u7b97\u68af\u5ea6</p>\n",
 "<p>Calculate loss </p>\n": "<p>\u8ba1\u7b97\u635f\u5931</p>\n",
 "<p>Clear the gradients </p>\n": "<p>\u6e05\u9664\u6e10\u53d8</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>\u521b\u5efa<a href=\"https://docs.labml.ai/api/helpers.html#labml_helpers.schedule.Piecewise\">\u76f8\u5bf9\u7684\u5206\u6bb5\u65f6\u95f4\u8868</a></p>\n",
 "<p>Create configurations </p>\n": "<p>\u521b\u5efa\u914d\u7f6e</p>\n",
 "<p>Create experiment </p>\n": "<p>\u521b\u5efa\u5b9e\u9a8c</p>\n",
 "<p>Dropout </p>\n": "<p>\u8f8d\u5b66</p>\n",
 "<p>Dropout for the hidden layer </p>\n": "<p>\u9690\u85cf\u56fe\u5c42\u7684\u9000\u51fa</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>\u6700\u540e\u4e00\u4e2a\u5b8c\u5168\u8fde\u63a5\u7684\u5c42\uff0c\u7528\u4e8e\u8f93\u51fa<span translate=no>_^_0_^_</span>\u8bfe\u5802\u8bc1\u636e\u3002RelU \u6216 Softplus \u6fc0\u6d3b\u5728\u6a21\u578b\u4e4b\u5916\u5e94\u7528\u4e8e\u6b64\uff0c\u4ee5\u83b7\u5f97\u975e\u8d1f\u9762\u8bc1\u636e</p>\n",
 "<p>First <span translate=no>_^_0_^_</span> convolution layer </p>\n": "<p>\u7b2c\u4e00\u4e2a<span translate=no>_^_0_^_</span>\u5377\u79ef\u5c42</p>\n",
 "<p>First fully-connected layer that maps to <span translate=no>_^_0_^_</span> features </p>\n": "<p>\u7b2c\u4e00\u4e2a\u6620\u5c04\u5230\u8981\u7d20\u7684\u5b8c\u5168\u8fde\u63a5\u7684<span translate=no>_^_0_^_</span>\u56fe\u5c42</p>\n",
 "<p>Flatten the tensor to shape <span translate=no>_^_0_^_</span> </p>\n": "<p>\u5c06\u5f20\u91cf\u5c55\u5e73\u6210\u5f62\u72b6<span translate=no>_^_0_^_</span></p>\n",
 "<p>Get evidences <span translate=no>_^_0_^_</span> </p>\n": "<p>\u83b7\u53d6\u8bc1\u636e<span translate=no>_^_0_^_</span></p>\n",
 "<p>Get model outputs </p>\n": "<p>\u83b7\u53d6\u6a21\u578b\u8f93\u51fa</p>\n",
 "<p>KL Divergence loss coefficient <span translate=no>_^_0_^_</span> </p>\n": "<p>KL \u80cc\u79bb\u635f\u5931\u7cfb\u6570<span translate=no>_^_0_^_</span></p>\n",
 "<p>KL Divergence regularization coefficient schedule </p>\n": "<p>KL \u53d1\u6563\u6b63\u5219\u5316\u7cfb\u6570\u65f6\u95f4\u8868</p>\n",
 "<p>Load configurations </p>\n": "<p>\u88c5\u8f7d\u914d\u7f6e</p>\n",
 "<p>Module to convert the model output to non-zero evidences </p>\n": "<p>\u7528\u4e8e\u5c06\u6a21\u578b\u8f93\u51fa\u8f6c\u6362\u4e3a\u975e\u96f6\u8bc1\u636e\u7684\u6a21\u5757</p>\n",
 "<p>Move data to the device </p>\n": "<p>\u5c06\u6570\u636e\u79fb\u52a8\u5230\u8bbe\u5907</p>\n",
 "<p>One-hot coded targets </p>\n": "<p>\u4e00\u70ed\u7f16\u7801\u76ee\u6807</p>\n",
 "<p>ReLU activation </p>\n": "<p>\u6fc0\u6d3b ReLU</p>\n",
 "<p>ReLU to calculate evidence </p>\n": "<p>RelU \u6765\u8ba1\u7b97\u8bc1\u636e</p>\n",
 "<p>Save the tracked metrics </p>\n": "<p>\u4fdd\u5b58\u8ddf\u8e2a\u7684\u6307\u6807</p>\n",
 "<p>Second <span translate=no>_^_0_^_</span> convolution layer </p>\n": "<p>\u7b2c\u4e8c\u4e2a<span translate=no>_^_0_^_</span>\u5377\u79ef\u5c42</p>\n",
 "<p>Set tracker configurations </p>\n": "<p>\u8bbe\u7f6e\u8ddf\u8e2a\u5668\u914d\u7f6e</p>\n",
 "<p>Softplus to calculate evidence </p>\n": "<p>Softplus \u7528\u4e8e\u8ba1\u7b97\u8bc1\u636e</p>\n",
 "<p>Start the experiment and run the training loop </p>\n": "<p>\u5f00\u59cb\u5b9e\u9a8c\u5e76\u8fd0\u884c\u8bad\u7ec3\u5faa\u73af</p>\n",
 "<p>Take optimizer step </p>\n": "<p>\u91c7\u53d6\u4f18\u5316\u5668\u6b65\u9aa4</p>\n",
 "<p>Total loss </p>\n": "<p>\u603b\u4e8f\u635f</p>\n",
 "<p>Track statistics </p>\n": "<p>\u8ffd\u8e2a\u7edf\u8ba1\u6570\u636e</p>\n",
 "<p>Train the model </p>\n": "<p>\u8bad\u7ec3\u6a21\u578b</p>\n",
 "<p>Training/Evaluation mode </p>\n": "<p>\u8bad\u7ec3/\u8bc4\u4f30\u6a21\u5f0f</p>\n",
 "<p>Update global step (number of samples processed) when in training mode </p>\n": "<p>\u5728\u8bad\u7ec3\u6a21\u5f0f\u4e0b\u66f4\u65b0\u5168\u5c40\u6b65\u957f\uff08\u5904\u7406\u7684\u6837\u672c\u6570\uff09</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>\u662f\u4e00\u6279 MNIST \u5f62\u72b6\u7684\u56fe\u50cf<span translate=no>_^_1_^_</span></li></ul>\n",
 "Evidential Deep Learning to Quantify Classification Uncertainty Experiment": "\u57fa\u4e8e\u8bc1\u636e\u7684\u6df1\u5ea6\u5b66\u4e60\u91cf\u5316\u5206\u7c7b\u4e0d\u786e\u5b9a\u6027\u5b9e\u9a8c",
 "This trains is EDL model on MNIST": "\u8fd9\u5217\u706b\u8f66\u662f MNIST \u4e0a\u7684 EDL \u578b\u53f7"
}