| /external/tensorflow/tensorflow/python/keras/tests/ |
| D | model_subclassing_compiled_test.py | 42 num_classes = 2
47 num_hidden=32, num_classes=num_classes, use_dp=True, use_bn=True)
55 y = np.zeros((num_samples, num_classes))
61 num_classes = (2, 3)
66 num_classes=num_classes, use_dp=True, use_bn=True)
75 y1 = np.zeros((num_samples, num_classes[0]))
76 y2 = np.zeros((num_samples, num_classes[1]))
82 num_classes = 2
88 num_hidden=32, num_classes=num_classes, use_dp=True, use_bn=True)
95 y = np.zeros((num_samples, num_classes), dtype=np.float32)
[all …]
|
| D | model_subclassing_test_util.py | 28 def __init__(self, num_classes=10): argument
30 self.num_classes = num_classes
34 self.dense1 = keras.layers.Dense(num_classes, activation='softmax')
42 def get_multi_io_subclass_model(use_bn=False, use_dp=False, num_classes=(2, 3)): argument
48 branch_a.append(keras.layers.Dense(num_classes[0], activation='softmax'))
53 branch_b.append(keras.layers.Dense(num_classes[1], activation='softmax'))
65 def __init__(self, num_classes=2): argument
67 self.num_classes = num_classes
69 self.dense2 = keras.layers.Dense(num_classes, activation='relu')
72 num_hidden=32, num_classes=4, use_bn=True, use_dp=True)
[all …]
|
| D | model_subclassing_test.py | 134 num_classes = 2
138 num_hidden=32, num_classes=num_classes, use_dp=True, use_bn=True)
210 num_classes = 2
215 num_hidden=32, num_classes=num_classes, use_dp=True, use_bn=True)
227 num_classes = 2
232 num_hidden=32, num_classes=num_classes, use_dp=True, use_bn=True)
244 num_classes = 10
249 model = model_util.SimpleConvTestModel(num_classes)
262 num_classes = 10
267 model = model_util.SimpleConvTestModel(num_classes)
[all …]
|
| /external/google-fruit/extras/benchmark/tables/ |
| D | fruit_wiki.yml | 10 dimension: "num_classes"
81 num_classes: 100
107 num_classes: 250
133 num_classes: 1000
159 num_classes: 100
185 num_classes: 250
211 num_classes: 1000
237 num_classes: 100
263 num_classes: 250
289 num_classes: 1000
[all …]
|
| /external/google-fruit/extras/benchmark/suites/ |
| D | fruit_full.yml | 24 num_classes: &num_classes
51 num_classes: *num_classes
62 num_classes: *num_classes
79 num_classes: *num_classes
91 num_classes: *num_classes
|
| D | debug.yml | 64 num_classes:
78 num_classes:
96 num_classes:
110 num_classes:
130 num_classes:
142 num_classes:
159 num_classes:
171 num_classes:
|
| D | fruit_mostly_full.yml | 24 num_classes: &num_classes
48 num_classes: *num_classes
59 num_classes: *num_classes
|
| D | simple_di_full.yml | 27 num_classes: &num_classes
54 num_classes: *num_classes
67 num_classes: *num_classes
|
| /external/tensorflow/tensorflow/python/keras/utils/ |
| D | np_utils_test.py | 30 num_classes = 5
32 expected_shapes = [(1, num_classes), (3, num_classes), (4, 3, num_classes),
33 (5, 4, 3, num_classes), (3, num_classes),
34 (3, 2, num_classes)]
35 labels = [np.random.randint(0, num_classes, shape) for shape in shapes]
37 np_utils.to_categorical(label, num_classes) for label in labels]
|
| D | np_utils.py | 25 def to_categorical(y, num_classes=None, dtype='float32'): argument
32 (integers from 0 to num_classes).
33 num_classes: total number of classes. If `None`, this would be inferred
43 >>> a = tf.keras.utils.to_categorical([0, 1, 2, 3], num_classes=4)
74 if not num_classes:
75 num_classes = np.max(y) + 1
77 categorical = np.zeros((n, num_classes), dtype=dtype)
79 output_shape = input_shape + (num_classes,)
|
| /external/tensorflow/tensorflow/python/ops/ |
| D | confusion_matrix.py | 98 num_classes=None, argument
110 If `num_classes` is `None`, then `num_classes` will be set to one plus the
112 start at 0. For example, if `num_classes` is 3, then the possible labels
135 num_classes: The possible number of labels the classification task can
153 (predictions, labels, num_classes, weights)) as name:
171 if num_classes is None:
172 num_classes = math_ops.maximum(math_ops.reduce_max(predictions),
175 num_classes_int64 = math_ops.cast(num_classes, dtypes.int64)
191 shape = array_ops.stack([num_classes, num_classes])
206 num_classes=None, argument
[all …]
|
| /external/tensorflow/tensorflow/core/kernels/ |
| D | in_topk_op_gpu.cu.cc | 40 const T* __restrict__ predictions, // dims: [ num_targets x num_classes ] in ComputePredictionMaskKernel()
42 int64* __restrict__ mask, // dims: [ num_targets x num_classes ] in ComputePredictionMaskKernel()
43 int num_targets, int num_classes) { in ComputePredictionMaskKernel() argument
44 GPU_1D_KERNEL_LOOP(i, num_targets * num_classes) { in ComputePredictionMaskKernel()
45 const int batch_index = i / num_classes; in ComputePredictionMaskKernel()
48 if (!FastBoundsCheck(target_idx, num_classes)) { in ComputePredictionMaskKernel()
55 ldg(predictions + batch_index * num_classes + target_idx); in ComputePredictionMaskKernel()
96 const Eigen::Index num_classes = predictions.dimension(1); in operator ()() local
99 context, num_targets * num_classes < std::numeric_limits<int>::max(), in operator ()()
103 if (num_targets == 0 || num_classes == 0) { in operator ()()
[all …]
|
| D | multinomial_op_gpu.cu.cc | 42 __global__ void MultinomialKernel(int32 nthreads, const int32 num_classes, in MultinomialKernel() argument
48 const int maxima_idx = index / num_classes; in MultinomialKernel()
52 static_cast<UnsignedOutputType>(index % num_classes)); in MultinomialKernel()
64 int num_classes, int num_samples, in operator ()()
77 bsc.set(2, num_classes); in operator ()()
81 boc.set(2, num_classes); in operator ()()
86 Eigen::array<int, 3> bsc{batch_size, num_samples, num_classes}; in operator ()()
87 Eigen::array<int, 3> boc{batch_size, 1, num_classes}; in operator ()()
110 /*in_dim1=*/num_classes, /*in_dim2=*/1, /*out_rank=*/1, in operator ()()
116 const int32 work_items = batch_size * num_samples * num_classes; in operator ()()
[all …]
|
| D | multinomial_op.cc | 51 int num_classes, int num_samples,
77 int num_classes, int num_samples, in operator ()()
86 auto DoWork = [ctx, num_samples, num_classes, &gen, &output, &logits]( in operator ()()
99 ctx->allocate_temp(DT_DOUBLE, TensorShape({num_classes}), in operator ()()
107 for (int64 j = 0; j < num_classes; ++j) { in operator ()()
119 for (int64 j = 0; j < num_classes; ++j) { in operator ()()
127 const double* cdf_end = cdf.data() + num_classes; in operator ()()
137 50 * (num_samples * std::log(num_classes) / std::log(2) + num_classes); in operator ()()
176 const int num_classes = static_cast<int>(logits_t.dim_size(1)); in DoCompute() local
177 OP_REQUIRES(ctx, num_classes > 0, in DoCompute()
[all …]
|
| D | ctc_decoder_ops.cc | 208 errors::InvalidArgument("num_classes cannot exceed max int")); in Compute()
209 const int num_classes = static_cast<const int>(num_classes_raw); in Compute() local
215 input_list_t.emplace_back(inputs_t.data() + t * batch_size * num_classes, in Compute()
216 batch_size, num_classes); in Compute()
223 // Assumption: the blank index is num_classes - 1 in Compute()
224 int blank_index = num_classes - 1; in Compute()
246 const int64 kCostPerUnit = 50 * max_time * num_classes; in Compute()
309 errors::InvalidArgument("num_classes cannot exceed max int")); in Compute()
310 const int num_classes = static_cast<const int>(num_classes_raw); in Compute() local
318 input_list_t.emplace_back(inputs_t.data() + t * batch_size * num_classes, in Compute()
[all …]
|
| /external/tensorflow/tensorflow/python/kernel_tests/random/ |
| D | multinomial_op_test.py | 154 logits: Numpy ndarray of shape [batch_size, num_classes].
156 sampler: A sampler function that takes (1) a [batch_size, num_classes]
160 Frequencies from sampled classes; shape [batch_size, num_classes].
167 batch_size, num_classes = logits.shape
173 self.assertLess(max(cnts.keys()), num_classes)
177 for k in range(num_classes)]
203 with self.assertRaisesOpError("num_classes should be positive"):
216 def native_op_vs_composed_ops(batch_size, num_classes, num_samples, num_iters): argument
218 shape = [batch_size, num_classes]
247 for num_classes in [10000, 100000]:
[all …]
|
| /external/tensorflow/tensorflow/python/keras/ |
| D | callbacks_v1_test.py | 45 NUM_CLASSES = 2 variable
63 num_classes=NUM_CLASSES)
91 model.add(layers.Dense(NUM_CLASSES, activation='softmax'))
171 num_classes=NUM_CLASSES)
197 output1 = layers.Dense(NUM_CLASSES, activation='softmax')(hidden)
198 output2 = layers.Dense(NUM_CLASSES, activation='softmax')(hidden)
274 num_classes=NUM_CLASSES)
285 model.add(layers.Dense(NUM_CLASSES, activation='softmax'))
324 num_hidden=10, num_classes=10, input_dim=100)
369 num_classes=NUM_CLASSES)
[all …]
|
| D | regularizers_test.py | 35 NUM_CLASSES = 2 variable
43 model.add(keras.layers.Dense(NUM_CLASSES,
54 num_classes=NUM_CLASSES)
55 y_train = np_utils.to_categorical(y_train, NUM_CLASSES)
56 y_test = np_utils.to_categorical(y_test, NUM_CLASSES)
137 NUM_CLASSES,
155 NUM_CLASSES,
177 NUM_CLASSES,
184 NUM_CLASSES, kernel_regularizer=regularizer)
|
| D | testing_utils.py | 65 num_classes, argument
73 num_classes: Integer, number of classes for the data and targets.
82 templates = 2 * num_classes * np.random.random((num_classes,) + input_shape)
83 y = np.random.randint(0, num_classes, size=(num_sample,))
450 def get_small_sequential_mlp(num_hidden, num_classes, input_dim=None): argument
456 activation = 'sigmoid' if num_classes == 1 else 'softmax'
457 model.add(layers.Dense(num_classes, activation=activation))
461 def get_small_functional_mlp(num_hidden, num_classes, input_dim): argument
464 activation = 'sigmoid' if num_classes == 1 else 'softmax'
465 outputs = layers.Dense(num_classes, activation=activation)(outputs)
[all …]
|
| /external/tensorflow/tensorflow/python/keras/preprocessing/ |
| D | image_dataset_test.py | 56 num_classes=2, argument
68 for class_index in range(num_classes):
101 directory = self._prepare_directory(count=7, num_classes=2)
125 directory = self._prepare_directory(num_classes=2)
157 directory = self._prepare_directory(num_classes=2)
173 directory = self._prepare_directory(num_classes=4, count=15)
185 directory = self._prepare_directory(num_classes=4, count=15)
222 directory = self._prepare_directory(num_classes=4, color_mode='rgba')
230 directory = self._prepare_directory(num_classes=4, color_mode='grayscale')
242 directory = self._prepare_directory(num_classes=2, count=10)
[all …]
|
| D | text_dataset_test.py | 35 num_classes=2, argument
46 for class_index in range(num_classes):
72 directory = self._prepare_directory(count=7, num_classes=2)
96 directory = self._prepare_directory(num_classes=2)
126 directory = self._prepare_directory(num_classes=4, count=15)
135 directory = self._prepare_directory(num_classes=4, count=15)
169 directory = self._prepare_directory(num_classes=2, count=10)
184 directory = self._prepare_directory(num_classes=2, count=2)
192 directory = self._prepare_directory(num_classes=2, count=25,
202 directory = self._prepare_directory(num_classes=2, count=0)
[all …]
|
| /external/tensorflow/tensorflow/python/keras/wrappers/ |
| D | scikit_learn_test.py | 32 NUM_CLASSES = 2 variable
43 model.add(keras.layers.Dense(NUM_CLASSES))
56 num_classes=NUM_CLASSES)
66 assert prediction in range(NUM_CLASSES)
69 assert proba.shape == (TEST_SAMPLES, NUM_CLASSES)
92 num_classes=NUM_CLASSES)
|
| /external/tensorflow/tensorflow/core/util/ctc/ |
| D | ctc_loss_calculator.h | 99 int num_classes, const Vector& seq_len,
131 auto num_classes = inputs[0].cols(); in CalculateLoss() local
144 if (inputs[t].cols() != num_classes) { in CalculateLoss()
146 " to be: ", num_classes, in CalculateLoss()
169 batch_size, num_classes, seq_len, labels, &max_u_prime, &l_primes); in CalculateLoss()
175 auto ComputeLossAndGradients = [this, num_classes, &labels, &l_primes, in CalculateLoss()
204 Matrix y(num_classes, seq_len(b)); in CalculateLoss()
214 // y, prob are in num_classes x seq_len(b) in CalculateLoss()
270 max_seq_len * num_classes * in CalculateLoss()
272 max_seq_len * 2 * (2 * num_classes + 1) * in CalculateLoss()
[all …]
|
| /external/tensorflow/tensorflow/python/data/experimental/ops/ |
| D | resampling.py | 45 `tf.int32` tensor. Values should be in `[0, num_classes)`.
46 target_dist: A floating point type tensor, shaped `[num_classes]`.
48 `[num_classes]`. If not provided, the true class distribution is
141 `tf.int32` tensor. Values should be in `[0, num_classes)`.
180 num_classes = (target_dist_t.shape[0] or array_ops.shape(target_dist_t)[0])
182 [num_classes], np.int64(smoothing_constant))
210 num_examples_per_class_seen: Type `int64`, shape `[num_classes]`,
215 `[num_classes]`.
216 dist: The updated distribution. Type `float32`, shape `[num_classes]`.
218 num_classes = num_examples_per_class_seen.get_shape()[0]
[all …]
|
| /external/tensorflow/tensorflow/python/ops/numpy_ops/integration_test/benchmarks/ |
| D | numpy_mlp.py | 22 NUM_CLASSES = 3 variable
34 def __init__(self, num_classes=NUM_CLASSES, input_size=INPUT_SIZE, argument
38 self.w2 = np.random.uniform(size=[hidden_units, num_classes]).astype(
42 self.b2 = np.random.uniform(size=[1, num_classes]).astype(
|