HomeSort by relevance Sort by last modified time
    Searched full:weights (Results 401 - 425 of 1517) sorted by null

<<11121314151617181920>>

  /external/apache-commons-math/src/main/java/org/apache/commons/math/ode/nonstiff/
EmbeddedRungeKuttaIntegrator.java 74 /** Internal weights from Butcher array (without the first empty row). */
77 /** External weights for the high order method from Butcher array. */
99 * @param a internal weights from Butcher array (without the first empty row)
100 * @param b propagation weights for the high order method from Butcher array
137 * @param a internal weights from Butcher array (without the first empty row)
138 * @param b propagation weights for the high order method from Butcher array
  /external/tensorflow/tensorflow/docs_src/performance/
quantization.md 24 Training neural networks is done by applying many tiny nudges to the weights,
42 is taken up with the weights for the neural connections, since there are often
46 weights tend to be normally distributed within a certain range, for example -3.0
107 with eight bit calculations internally, and all weights quantized as well. If
165 representations as a compression problem. We know that the weights and
168 +15 for weights, -500 to 1000 for activations on an image model, though the
  /external/tensorflow/tensorflow/python/estimator/canned/
parsing_utils.py 40 * Users need to combine parsing spec of features with labels and weights
81 # * weights are retrieved with key 'example-weight'
122 weights. It is used to down weight or boost examples during training. It
181 * Users need to combine parsing spec of features with labels and weights
221 # * weights are retrieved with key 'example-weight'
258 weights. It is used to down weight or boost examples during training. It
  /external/tensorflow/tensorflow/python/kernel_tests/
confusion_matrix_test.py 49 def _testConfMatrix(self, labels, predictions, truth, weights=None,
54 labels, predictions, dtype=dtype, weights=weights,
170 weights = constant_op.constant(np.arange(5, dtype=np.int32))
181 labels=labels, predictions=predictions, weights=weights, truth=truth)
  /prebuilts/python/linux-x86/2.7.5/lib/python2.7/site-packages/setools/
permmap.py 253 Exclude all permissions in an object class for calculating rule weights.
266 Exclude a permission for calculating rule weights.
280 Include all permissions in an object class for calculating rule weights.
294 Include a permission for calculating rule weights.
331 Get the type enforcement rule's information flow read and write weights.
404 raise ValueError("Permission weights must be 1-10: {0}".format(weight))
  /external/apache-commons-math/src/main/java/org/apache/commons/math/optimization/
MultiStartDifferentiableMultivariateVectorialOptimizer.java 177 final double[] target, final double[] weights,
192 optima[i] = optimizer.optimize(f, target, weights,
221 sum += weights[i] * ri * ri;
  /external/llvm/docs/
BlockFrequencyTerminology.rst 26 Weights are relative to the other edges of a given predecessor block. The
28 the sum of the weights on the predecessor's outgoing edges.
75 distributed to successors according to branch weights. Block Mass uses a
  /external/tensorflow/tensorflow/contrib/boosted_trees/lib/learner/batch/
categorical_split_handler.py 57 min_node_weight: Minimum sum of weights of examples in each partition to
85 hessians, empty_gradients, empty_hessians, weights,
99 weights: A dense float32 tensor with a weight for each example.
  /external/tensorflow/tensorflow/contrib/learn/python/learn/estimators/
linear.py 122 * joint_weights: If True, the weights for all columns will be stored in a
206 None if there are no weights.
208 model weights.
284 """SessionRunHook to update and shrink SDCA model weights."""
416 weights. It is used to down weight or boost examples during training. It
427 _joint_weight: If True, the weights for all columns will be stored in a
472 # the hook to update weights and shrink step only on the chief.
688 weights. It is used to down weight or boost examples during training. It
702 store the weights. It's faster, but requires all feature columns are
739 # the hook to update weights and shrink step only on the chief
    [all...]
  /external/tensorflow/tensorflow/contrib/linear_optimizer/python/
sdca_optimizer.py 116 # very sparse features with weights and not weights.
131 # and sparse features as well as dense and sparse weights (variables) for
  /external/tensorflow/tensorflow/contrib/lite/models/smartreply/g3doc/
README.md 124 integers. Longer skip-grams are allocated higher weights.
135 appropriate response labels along with weights for the projected features,
136 and aggregates the response labels and weights together.
  /external/tensorflow/tensorflow/contrib/lite/models/smartreply/ops/
predict.cc 17 // output predicted labels and weights in decreasing order.
23 // Input[3]: Weights in the model. float[keys of model, item per entry]
27 // Output[1]: Predicted weights. float[num of output]
  /external/tensorflow/tensorflow/contrib/model_pruning/
README.md 11 weight tensor and determines which of the weights participate in the forward
18 conv = tf.nn.conv2d(images, pruning.apply_mask(weights), stride, padding)
71 such masking all the weights below this threshold achieves the sparsity level
  /external/tensorflow/tensorflow/core/kernels/
range_sampler.h 210 // distribution by applying a distortion power to the weights.
230 // Weights for individual samples. The probability of a sample i is defined
233 // The total weights of all samples.
  /external/tensorflow/tensorflow/python/keras/_impl/keras/layers/
gru_test.py 98 units, return_sequences=False, stateful=True, weights=None)
151 weights=None,
174 weights=None,
simplernn_test.py 98 units, return_sequences=False, stateful=True, weights=None)
151 weights=None,
174 weights=None,
  /external/tensorflow/tensorflow/python/keras/_impl/keras/utils/
training_utils.py 84 # so that the model's weights are hosted on CPU memory.
88 model = Xception(weights=None,
106 # Save model via the template model (which shares the same weights):
  /external/clang/test/Profile/
c-counter-overflows.c 1 // Test that big branch weights get scaled down to 32-bits, rather than just
  /external/curl/docs/libcurl/opts/
CURLOPT_STREAM_WEIGHT.3 35 stream used by the easy \fIhandle\fP. Setting and using weights only makes
  /external/deqp/external/openglcts/docs/specs/
CTS_ARB_texture_filter_minmax.txt 72 weights, so it cannot be tested.
  /external/glide/library/src/main/java/com/bumptech/glide/load/model/
ModelLoader.java 16 * view on devices with different densities, but also allows you to use layout weights or otherwise
  /external/libopus/src/
mlp_train.h 80 double **weights; member in struct:__anon25625
  /external/opencv/ml/include/
ml.h 562 start_step(0/*CvEM::START_AUTO_STEP*/), probs(0), weights(0), means(0), covs(0)
572 probs(_probs), weights(_weights), means(_means), covs(_covs), term_crit(_term_crit)
579 const CvMat* weights; member in struct:CvEMParams
630 CvMat* weights; member in class:CvEM
1135 CvMat* weights; member in class:CvBoost
1235 double** weights; member in class:CvANN_MLP
    [all...]
  /external/skia/src/effects/
GrCircleBlurFragmentProcessor.fp 132 uint8_t* weights = new uint8_t[numSteps];
153 weights[i] = eval_at(evalX, circleR, halfKernel, halfKernelSize, yEvals + i);
156 weights[numSteps - 1] = 0;
157 return weights;
  /external/skia/src/gpu/effects/
GrGaussianConvolutionFragmentProcessor.h 16 * A 1D Gaussian convolution effect. The kernel is computed as an array of 2 * half-width weights.

Completed in 375 milliseconds

<<11121314151617181920>>