Home
last modified time | relevance | path

Searched refs:logits (Results 1 – 25 of 68) sorted by relevance

123

/dports/math/py-keras/Keras-2.4.3/tests/keras/
H A Dlosses_test.py453 loss = bce_obj(y_true, logits)
478 loss = bce_obj(y_true, logits)
565 loss = bce_obj(y_true, logits)
589 loss = bce_obj(y_true, logits)
613 loss = cce_obj(y_true, logits)
627 loss = cce_obj(y_true, logits)
664 loss = cce_obj(y_true, logits)
685 loss = cce_obj(y_true, logits)
709 loss = cce_obj(y_true, logits)
723 loss = cce_obj(y_true, logits)
[all …]
H A Dmetrics_test.py906 logits = ((100., -100., -100.))
911 result = bce_obj(y_true, logits)
940 logits = np.asarray([[1, 9, 0], [1, 8, 1]], dtype=np.float32)
941 result = cce_obj(y_true, logits)
959 logits = np.asarray([[1, 9, 0], [1, 8, 1]], dtype=np.float32)
961 result = cce_obj(y_true, logits, sample_weight=sample_weight)
967 logits = np.asarray([[1, 9, 0], [1, 8, 1]], dtype=np.float32)
972 loss = cce_obj(y_true, logits)
997 logits = np.asarray([[1, 9, 0], [1, 8, 1]], dtype=np.float32)
998 result = scce_obj(y_true, logits)
[all …]
/dports/math/R-cran-LearnBayes/LearnBayes/man/
H A Dlogctablepost.Rd3 \title{Log posterior of difference and sum of logits in a 2x2 table}
5 Computes the log posterior density for the difference and sum of logits
7 prior placed on the logits
13 \item{theta}{vector of parameter values "difference of logits" and "sum of logits")}
/dports/math/mlpack/mlpack-3.4.2/src/mlpack/methods/ann/dists/
H A Dbernoulli_distribution_impl.hpp34 logits(param), in BernoulliDistribution()
40 LogisticFunction::Fn(logits, probability); in BernoulliDistribution()
44 probability = arma::mat(logits.memptr(), logits.n_rows, in BernoulliDistribution()
45 logits.n_cols, false, false); in BernoulliDistribution()
H A Dbernoulli_distribution.hpp108 const DataType& Logits() const { return logits; } in Logits()
111 DataType& Logits() { return logits; } in Logits()
121 ar & BOOST_SERIALIZATION_NVP(logits); in serialize()
132 DataType logits; member in mlpack::ann::BernoulliDistribution
/dports/misc/mmdnn/MMdnn-0.3.1/mmdnn/conversion/examples/tensorflow/models/
H A Dtest_rnn.py19 logits = tf.layers.dense(outputs[-1], 2, activation=None, name='output')
33 logits = tf.layers.dense(outputs[-1], 2, activation=None, name='output')
35 return logits, logits
H A Dmobilenet_v1.py346 logits = slim.conv2d(net, num_classes, [1, 1], activation_fn=None,
349 logits = tf.squeeze(logits, [1, 2], name='SpatialSqueeze')
350 end_points['Logits'] = logits
352 end_points['Predictions'] = prediction_fn(logits, scope='Predictions')
353 return logits, end_points
H A Dinception_resnet_v2.py359 logits = slim.fully_connected(net, num_classes, activation_fn=None,
361 end_points['Logits'] = logits
362 end_points['Predictions'] = tf.nn.softmax(logits, name='Predictions')
364 return logits, end_points
H A Dnasnet.py505 logits = slim.fully_connected(net, num_classes)
507 if add_and_check_endpoint('Logits', logits):
510 predictions = tf.nn.softmax(logits, name='predictions')
513 return logits, end_points
/dports/misc/mmdnn/MMdnn-0.3.1/mmdnn/conversion/examples/tensorflow/models/mobilenet/
H A Dmobilenet.py372 logits = slim.conv2d(
380 logits = tf.squeeze(logits, [1, 2])
382 logits = tf.identity(logits, name='output')
383 end_points['Logits'] = logits
385 end_points['Predictions'] = prediction_fn(logits, 'Predictions')
386 return logits, end_points
/dports/misc/mmdnn/MMdnn-0.3.1/mmdnn/conversion/examples/tensorflow/
H A Dextractor.py205 logits, endpoints = cls.architecture_map[architecture]['builder']()(
210 if logits.op.type == 'Squeeze':
211 labels = tf.identity(logits, name='MMdnn_Output')
213 labels = tf.squeeze(logits, name='MMdnn_Output')
303 logits, endpoints = cls.architecture_map[architecture]['builder']()(
307 labels = tf.squeeze(logits)
314 predict = sess.run(logits, feed_dict = {data_input : input_data})
H A Dextract_model.py76 …logits, endpoints = networks_map[args.network]()(data_input, num_classes=num_classes, is_training=…
77 labels = tf.squeeze(logits)
95 predict = sess.run(logits, feed_dict = {data_input : img})
/dports/math/py-ssm/ssm-0.0.1/ssm/
H A Dstats.py561 def categorical_logpdf(data, logits, mask=None): argument
584 C = logits.shape[-1]
587 assert logits.shape[-2] == D
593 logits = logits - logsumexp(logits, axis=-1, keepdims=True) # (..., D, C)
595 lls = np.sum(x * logits, axis=-1) # (..., D)
/dports/math/R-cran-pbkrtest/pbkrtest/man/
H A Ddata-budworm.Rd34 ## function to caclulate the empirical logits
41 # plot the empirical logits against log-dose
46 title('budworm: emprirical logits of probability to die ')
/dports/misc/mxnet/incubator-mxnet-1.9.0/example/rnn/large_word_lm/
H A Dmodel.py126 logits = S.concat(p_target, p_sample, dim=1)
128 return logits, new_targets
165 logits, new_targets = sampled_softmax(ntokens, k, num_proj,
168 self.train_loss = cross_entropy_loss(logits, new_targets, rescale_loss=rescale_loss)
/dports/misc/py-mxnet/incubator-mxnet-1.9.0/example/rnn/large_word_lm/
H A Dmodel.py126 logits = S.concat(p_target, p_sample, dim=1)
128 return logits, new_targets
165 logits, new_targets = sampled_softmax(ntokens, k, num_proj,
168 self.train_loss = cross_entropy_loss(logits, new_targets, rescale_loss=rescale_loss)
/dports/multimedia/vmaf/vmaf-2.3.0/python/vmaf/core/
H A Dnn_train_test_model.py302 input_image_batch, logits, y_, y_p, W_conv0, W_conv1, loss, train_step \
372 input_image_batch, logits, y_, y_p, W_conv0, W_conv1, loss, train_step \
547 logits = tf.reduce_mean(h_conv1_elu_flat, 1)
548 logits_norm = tf.nn.softmax(logits)
551 loss = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=logits, labels=y_))
554 return input_image_batch, logits, y_, y_p, W_conv0, W_conv1, loss, train_step
/dports/misc/py-gluonnlp/gluon-nlp-0.10.0/scripts/tests/
H A Dtest_models.py87 logits, new_states = model(nd_indices, None)
88 npt.assert_allclose(logits.asnumpy(), gt_logits, 1E-5, 1E-5)
/dports/misc/mxnet/incubator-mxnet-1.9.0/example/rnn/word_lm/
H A Dmodel.py64 logits = mx.sym.log_softmax(pred, axis=-1)
65 loss = -mx.sym.pick(logits, label, axis=-1, keepdims=True)
/dports/misc/py-mxnet/incubator-mxnet-1.9.0/example/rnn/word_lm/
H A Dmodel.py64 logits = mx.sym.log_softmax(pred, axis=-1)
65 loss = -mx.sym.pick(logits, label, axis=-1, keepdims=True)
/dports/misc/py-gluoncv/gluon-cv-0.9.0/gluoncv/nn/
H A Dsampler.py59 def forward(self, x, logits, ious): argument
67 positive = logits.slice_axis(axis=2, begin=1, end=None)
68 background = logits.slice_axis(axis=2, begin=0, end=1).reshape((0, -1))
70 esum = F.exp(logits - maxval.reshape((0, 0, 1))).sum(axis=2)
/dports/misc/py-gluonnlp/gluon-nlp-0.10.0/src/gluonnlp/model/train/
H A Dcache.py185 logits = F.dot(valid_cache_history, encoder_h[idx])
186 cache_attn = F.softmax(self._theta * logits).reshape(-1, 1)
/dports/misc/py-gluonnlp/gluon-nlp-0.10.0/scripts/language_model/transformer/
H A Dsoftmax.py111 logits = F.FullyConnected(data=hidden, weight=params[name],
115 logprob = F.log_softmax(logits)
306 logits = F.FullyConnected(data=hidden, weight=params[name],
310 logprob = F.log_softmax(logits)
/dports/science/py-scikit-optimize/scikit-optimize-0.9.0/skopt/optimizer/
H A Doptimizer.py597 logits = np.array(self.gains_)
598 logits -= np.max(logits)
599 exp_logits = np.exp(self.eta * logits)
/dports/misc/mmdnn/MMdnn-0.3.1/mmdnn/conversion/tensorflow/
H A DREADME.md92 logits = your_own_network_builder(data_input)
93 if logits.op.type == 'Squeeze':
94 labels = tf.identity(logits, name='MMdnn_Output')
96 labels = tf.squeeze(logits, name='MMdnn_Output')

123