我们从Python开源项目中，提取了以下17个代码示例，用于说明如何使用tensorflow.int8()。
def create_torch_variable(self, value, gpu=False): """Convenience method that produces a tensor given the value of the defined type. Returns: a torch tensor of same type. """ if isinstance(value, torch.autograd.Variable): if gpu: value = value.cuda() return value if not torch.is_tensor(value): if not isinstance(value, np.ndarray): value = np.array(value, dtype=self.dtype.as_numpy_dtype) else: value = value.astype(self.dtype.as_numpy_dtype) if value.size == 0: return value allowed = [tf.int16, tf.int32, tf.int64, tf.float16, tf.float32, tf.float64, tf.int8] if self.dtype in allowed: value = torch.autograd.Variable(torch.from_numpy(value)) else: value = torch.autograd.Variable(value) if gpu and isinstance(value, torch.autograd.Variable): value = value.cuda() return value
def _convert_string_dtype(dtype): if dtype == 'float16': return tf.float16 if dtype == 'float32': return tf.float32 elif dtype == 'float64': return tf.float64 elif dtype == 'int16': return tf.int16 elif dtype == 'int32': return tf.int32 elif dtype == 'int64': return tf.int64 elif dtype == 'uint8': return tf.int8 elif dtype == 'uint16': return tf.uint16 else: raise ValueError('Unsupported dtype:', dtype)
def mu_law(x, mu=255, int8=False): """A TF implementation of Mu-Law encoding. Args: x: The audio samples to encode. mu: The Mu to use in our Mu-Law. int8: Use int8 encoding. Returns: out: The Mu-Law encoded int8 data. """ out = tf.sign(x) * tf.log(1 + mu * tf.abs(x)) / np.log(1 + mu) out = tf.floor(out * 128) if int8: out = tf.cast(out, tf.int8) return out
def unwrap_output_sparse(self, final_state, include_stop_tokens=True): """ Retreive the beam search output from the final state. Returns a sparse tensor with underlying dimensions of [batch_size, max_len] """ output_dense = final_state[0] mask = tf.not_equal(output_dense, self.stop_token) if include_stop_tokens: output_dense = tf.concat(1, [output_dense[:, 1:], tf.ones_like(output_dense[:, 0:1]) * self.stop_token]) mask = tf.concat(1, [mask[:, 1:], tf.cast(tf.ones_like(mask[:, 0:1], dtype=tf.int8), tf.bool)]) return sparse_boolean_mask(output_dense, mask)
def test_embedding_int8(self): weights = np.array([[1, 2], [3, 4]], dtype='float32') embedding = tdl.Embedding(2, 2, initializer=weights) with self.test_session() as sess: embeddings = [embedding(tf.constant([x], dtype=tf.int8)) for x in [0, 1, 7, -5]] sess.run(tf.global_variables_initializer()) self.assertAllEqual([[[1, 2]], [[3, 4]], [[3, 4]], [[3, 4]]], sess.run(embeddings))
def mu_law_encode(audio, quantization_channels=256): """Quantizes waveform amplitudes.""" with tf.name_scope('encode'): mu = quantization_channels - 1 out = tf.sign(audio) * tf.log(1 + mu * tf.abs(audio)) / np.log(1 + mu) out = tf.cast(tf.floor(out * 128), tf.int8) return out # tensorflow/magenta/blob/master/magenta/models/nsynth/utils.py#L79
def read(filename_queue): class CAM17Record(object): pass result = CAM17Record() result.height = IMAGE_SIZE result.width = IMAGE_SIZE result.depth = CHANNELS reader = tf.TFRecordReader() result.key, value = reader.read(filename_queue) feature_map = { 'image/encoded': tf.FixedLenFeature([], dtype=tf.string, default_value=''), 'image/class/label': tf.FixedLenFeature([1], dtype=tf.int64, default_value=-1) } features = tf.parse_single_example(value, feature_map) result.label = tf.cast(features['image/class/label'], dtype=tf.int8) image_buffer = features['image/encoded'] image = tf.image.decode_jpeg(image_buffer, channels=CHANNELS) depth_major = tf.reshape(image, [result.width, result.height, result.depth]) result.uint8image = tf.transpose(depth_major, [1, 0, 2]) return result
def test_input_int8(self): self._assert_dtype( np.int8, tf.int8, np.matrix([[1, 2], [3, 4]], dtype=np.int8))
def runSum(): a=tf.constant(12,dtype=tf.int8) b=tf.constant(10,dtype=tf.int8) sv=tf.train.Supervisor(logdir="./test1") with sv.managed_session() as sess: for i in range(10): if sv.should_stop(): return print(sess.run([a,b]))
def testDNN(): # copied from quick start sample code https://www.tensorflow.org/get_started/tflearn # Load datasets. training_set = tf.contrib.learn.datasets.base.load_csv_with_header( filename='training.csv', target_dtype=np.int8, features_dtype=np.int8) test_set = tf.contrib.learn.datasets.base.load_csv_with_header( filename='testset.csv', target_dtype=np.int8, features_dtype=np.int8) feature_columns = [tf.contrib.layers.real_valued_column("", dtype=tf.int8, dimension=1000)] classifier = tf.contrib.learn.DNNClassifier(feature_columns=feature_columns, hidden_units=[10], n_classes=2, model_dir="/tmp/spammodel3") # Define the training inputs def get_train_inputs(): x = tf.constant(training_set.data) y = tf.constant(training_set.target) return x, y # Fit model. classifier.fit(input_fn=get_train_inputs, steps=2000) # Define the test inputs def get_test_inputs(): x = tf.constant(test_set.data) y = tf.constant(test_set.target) return x, y # Evaluate accuracy. score = classifier.evaluate(input_fn=get_test_inputs, steps=1) print("\nTest Accuracy: {0:f}\n".format(score["accuracy"])) for key in score: print(key, score[key]) # Test Accuracy: 0.981333 # accuracy/baseline_label_mean 0.0233333 # loss 0.0698425 # auc 0.892803 # global_step 4000 # accuracy/threshold_0.500000_mean 0.981333 # recall/positive_threshold_0.500000_mean 0.257143 # labels/prediction_mean 0.0196873 # accuracy 0.981333 # precision/positive_threshold_0.500000_mean 0.818182 # labels/actual_label_mean 0.0233333
