python类Print()的实例源码

TestUpd.py 文件源码 项目:How-to-Learn-from-Little-Data 作者: llSourcell 项目源码 文件源码 阅读 32 收藏 0 点赞 0 评论 0
def omniglot():

    sess = tf.InteractiveSession()

    """    def wrapper(v):
        return tf.Print(v, [v], message="Printing v")

    v = tf.Variable(initial_value=np.arange(0, 36).reshape((6, 6)), dtype=tf.float32, name='Matrix')

    sess.run(tf.global_variables_initializer())
    sess.run(tf.local_variables_initializer())

    temp = tf.Variable(initial_value=np.arange(0, 36).reshape((6, 6)), dtype=tf.float32, name='temp')
    temp = wrapper(v)
    #with tf.control_dependencies([temp]):
    temp.eval()
    print 'Hello'"""

    def update_tensor(V, dim2, val):  # Update tensor V, with index(:,dim2[:]) by val[:]
        val = tf.cast(val, V.dtype)
        def body(_, (v, d2, chg)):
            d2_int = tf.cast(d2, tf.int32)
            return tf.slice(tf.concat_v2([v[:d2_int],[chg] ,v[d2_int+1:]], axis=0), [0], [v.get_shape().as_list()[0]])
        Z = tf.scan(body, elems=(V, dim2, val), initializer=tf.constant(1, shape=V.get_shape().as_list()[1:], dtype=tf.float32), name="Scan_Update")
        return Z
preprocessing.py 文件源码 项目:benchmarks 作者: tensorflow 项目源码 文件源码 阅读 34 收藏 0 点赞 0 评论 0
def decode_jpeg(image_buffer, scope=None):  # , dtype=tf.float32):
  """Decode a JPEG string into one 3-D float image Tensor.

  Args:
    image_buffer: scalar string Tensor.
    scope: Optional scope for op_scope.
  Returns:
    3-D float Tensor with values ranging from [0, 1).
  """
  # with tf.op_scope([image_buffer], scope, 'decode_jpeg'):
  # with tf.name_scope(scope, 'decode_jpeg', [image_buffer]):
  with tf.name_scope(scope or 'decode_jpeg'):
    # Decode the string as an RGB JPEG.
    # Note that the resulting image contains an unknown height and width
    # that is set dynamically by decode_jpeg. In other words, the height
    # and width of image is unknown at compile-time.
    image = tf.image.decode_jpeg(image_buffer, channels=3,
                                 fancy_upscaling=False,
                                 dct_method='INTEGER_FAST')

    # image = tf.Print(image, [tf.shape(image)], 'Image shape: ')

    return image
rnd_trans.py 文件源码 项目:tfplus 作者: renmengye 项目源码 文件源码 阅读 36 收藏 0 点赞 0 评论 0
def init_var(self):
        self.rand_h = tf.random_uniform([1], 1.0 - float(self.rnd_hflip), 1.0)
        self.rand_v = tf.random_uniform([1], 1.0 - float(self.rnd_vflip), 1.0)
        self.rand_t = tf.random_uniform(
            [1], 1.0 - float(self.rnd_transpose), 1.0)
        self.offset = tf.random_uniform(
            [2], dtype='int32', maxval=self.padding * 2 + self.shrink)
        if self._debug:
            self.offset = tf.Print(self.offset,
                                   ['Forward RND module', self.offset])
        if self.rnd_size:
            self.space = 2 * self.padding - self.offset
            self.offset20 = tf.random_uniform(
                [], dtype='int32', maxval=self.space[0] * 2) - self.space[0]
            self.offset21 = tf.random_uniform(
                [], dtype='int32', maxval=self.space[1] * 2) - self.space[1]
            self.offset2 = tf.pack([self.offset20, self.offset21])
        else:
            self.offset2 = tf.zeros([2], dtype='int32')
        pass
test_feature.py 文件源码 项目:tf-image-interpreter 作者: ThoughtWorksInc 项目源码 文件源码 阅读 39 收藏 0 点赞 0 评论 0
def test_vgg():
  vgg = Vgg16()
  image_tensor = tf.placeholder(tf.float32)
  with tf.Session() as sess:
    vgg.build(image_tensor)
    init = tf.initialize_all_variables()
    sess.run(init)

    load_feature_layer_params('/Users/dtong/code/data/tf-image-interpreter/pretrain/vgg16_weights.npz', sess)

    for v in tf.get_collection(tf.GraphKeys.VARIABLES):
      print_op = tf.Print(v, [v], message=v.name, first_n=10)
      sess.run(print_op)

    roidb = RoiDb('val.txt', 2007)
    batch_gen = BatchGenerator(roidb)

    for i in range(10):
      image, scale, bboxes = batch_gen.next_batch()

      print(sess.run(vgg.conv5_3, feed_dict={image_tensor: image}))
test_minibatch.py 文件源码 项目:tf-image-interpreter 作者: ThoughtWorksInc 项目源码 文件源码 阅读 31 收藏 0 点赞 0 评论 0
def main():
  roidb = RoiDb('val.txt', 2007)
  batch_gen = BatchGenerator(roidb)

  image_tensor = tf.placeholder(dtype=tf.float32)
  scale_tensor = tf.placeholder(dtype=tf.float32)
  bboxes_tensor = tf.placeholder(dtype=tf.float32)
  p_op = tf.Print(image_tensor, [tf.shape(image_tensor), scale_tensor, bboxes_tensor])

  sess = tf.Session()
  init = tf.initialize_all_variables()
  sess.run(init)

  coord = tf.train.Coordinator()
  queue_threads = queue_runner.start_queue_runners(sess, coord=coord)

  for i in range(10):
    if coord.should_stop():
      break
    image, scale, bboxes = batch_gen.next_batch()

    sess.run([p_op], feed_dict={image_tensor: image, scale_tensor: scale, bboxes_tensor:bboxes})

  coord.request_stop()
  coord.join(queue_threads)
rpn_data.py 文件源码 项目:tf-image-interpreter 作者: ThoughtWorksInc 项目源码 文件源码 阅读 35 收藏 0 点赞 0 评论 0
def generate(self, image, scale, bboxes):
    shape = tf.shape(image)
    # TODO: NotImplementedError: Negative start indices are not currently supported
    # height, width = shape[-2:]
    # height, width = shape[-2:]
    height = shape[1]
    width = shape[2]

    if self._debug:
      height = tf.Print(height, [height], message='image height: ')
      width = tf.Print(width, [width], message='image width: ')

    anchors = self._generate_valid_anchors(width, height)
    overlaps = self._calculate_overlaps(tf.cast(anchors, dtype=tf.float32), tf.cast(bboxes, dtype=tf.float32))

    labels = self._generate_labels(overlaps)

    labels = self._subsample_positive(labels)
    labels = self._subsample_negative(labels)

    return labels
rpn_data.py 文件源码 项目:tf-image-interpreter 作者: ThoughtWorksInc 项目源码 文件源码 阅读 30 收藏 0 点赞 0 评论 0
def _generate_labels(self, overlaps):
    labels = tf.Variable(tf.ones(shape=(tf.shape(overlaps)[0],), dtype=tf.float32) * -1, trainable=False,
                         validate_shape=False)
    gt_max_overlaps = tf.arg_max(overlaps, dimension=0)
    anchor_max_overlaps = tf.arg_max(overlaps, dimension=1)
    mask = tf.one_hot(anchor_max_overlaps, tf.shape(overlaps)[1], on_value=True, off_value=False)
    max_overlaps = tf.boolean_mask(overlaps, mask)
    if self._debug:
      max_overlaps = tf.Print(max_overlaps, [max_overlaps])
    labels = tf.scatter_update(labels, gt_max_overlaps, tf.ones((tf.shape(gt_max_overlaps)[0],)))
    # TODO: extract config object
    over_threshold_mask = tf.reshape(tf.where(max_overlaps > 0.5), (-1,))
    if self._debug:
      over_threshold_mask = tf.Print(over_threshold_mask, [over_threshold_mask], message='over threshold index : ')
    labels = tf.scatter_update(labels, over_threshold_mask, tf.ones((tf.shape(over_threshold_mask)[0],)))
    # TODO: support clobber positive in the origin implement
    below_threshold_mask = tf.reshape(tf.where(max_overlaps < 0.3), (-1,))
    if self._debug:
      below_threshold_mask = tf.Print(below_threshold_mask, [below_threshold_mask], message='below threshold index : ')
    labels = tf.scatter_update(labels, below_threshold_mask, tf.zeros((tf.shape(below_threshold_mask)[0],)))
    return labels
model_group.py 文件源码 项目:answer-triggering 作者: jiez-osu 项目源码 文件源码 阅读 27 收藏 0 点赞 0 评论 0
def bag_hinge_loss(config, preds, sent_mask, flip_sent_mask, hete_mask,
                   sent_trgt, sent_num):
  """ HINGE LOSS:
      DEFINED AS: MAX(0, M - MIN(SENT+) - MAX(SENT-))
      THIS ONLY APPLIES TO HETE BAGS.
  """
  flip_sent_trgt = \
      tf.constant(1, shape=[config.batch_size,sent_num], dtype=config.data_type) - \
      sent_trgt
  pos_preds = preds + flip_sent_trgt + flip_sent_mask # [batch_size, sent_num]
  neg_preds = preds * flip_sent_trgt * sent_mask # [batch_size, sent_num]
  min_pos_pred = tf.reduce_min(pos_preds, 1)
  # min_pos_pred = tf.Print(min_pos_pred, [min_pos_pred], message='min_pos_pred')
  max_neg_pred = tf.reduce_max(neg_preds, 1)
  # max_neg_pred = tf.Print(max_neg_pred, [max_neg_pred], message='max_neg_pred')

  hinge_loss = hete_mask * tf.reduce_max(tf.pack(
      [tf.constant(0, shape=[config.batch_size], dtype=config.data_type),
       (0.20 - min_pos_pred + max_neg_pred)], axis=1), 1) # [batch_size]
  # hinge_loss = tf.Print(hinge_loss, [hinge_loss], message='hinge_loss', summarize=20)

  avg_hinge_loss = tf.reduce_sum(hinge_loss) / (tf.reduce_sum(hete_mask) + 1e-12)
  return avg_hinge_loss
TestUpd.py 文件源码 项目:NTM-One-Shot-TF 作者: hmishra2250 项目源码 文件源码 阅读 29 收藏 0 点赞 0 评论 0
def omniglot():

    sess = tf.InteractiveSession()

    """    def wrapper(v):
        return tf.Print(v, [v], message="Printing v")

    v = tf.Variable(initial_value=np.arange(0, 36).reshape((6, 6)), dtype=tf.float32, name='Matrix')

    sess.run(tf.global_variables_initializer())
    sess.run(tf.local_variables_initializer())

    temp = tf.Variable(initial_value=np.arange(0, 36).reshape((6, 6)), dtype=tf.float32, name='temp')
    temp = wrapper(v)
    #with tf.control_dependencies([temp]):
    temp.eval()
    print 'Hello'"""

    def update_tensor(V, dim2, val):  # Update tensor V, with index(:,dim2[:]) by val[:]
        val = tf.cast(val, V.dtype)
        def body(_, (v, d2, chg)):
            d2_int = tf.cast(d2, tf.int32)
            return tf.slice(tf.concat_v2([v[:d2_int],[chg] ,v[d2_int+1:]], axis=0), [0], [v.get_shape().as_list()[0]])
        Z = tf.scan(body, elems=(V, dim2, val), initializer=tf.constant(1, shape=V.get_shape().as_list()[1:], dtype=tf.float32), name="Scan_Update")
        return Z
ocr.py 文件源码 项目:tf-cnn-lstm-ocr-captcha 作者: Luonic 项目源码 文件源码 阅读 34 收藏 0 点赞 0 评论 0
def distorted_inputs():
  """Construct distorted input for CIFAR training using the Reader ops.

  Returns:
    images: Images. 4D tensor of [batch_size, IMAGE_SIZE, IMAGE_SIZE, 3] size.
    labels: Labels. 1D tensor of [batch_size] size.

  Raises:
    ValueError: If no data_dir
  """
  with tf.variable_scope('distorted_inputs'):
    if not FLAGS.train_data_dir:
      raise ValueError('Please supply a data_dir')
    data_dir = FLAGS.train_data_dir
    images, labels, seq_lengths = ocr_input.distorted_inputs(data_dir=data_dir,
                                                    batch_size=FLAGS.batch_size)  
    # seq_lengths = tf.Print(seq_lengths, [seq_lengths], "seq_lengths")
    return images, labels, seq_lengths
ocr.py 文件源码 项目:tf-cnn-lstm-ocr-captcha 作者: Luonic 项目源码 文件源码 阅读 37 收藏 0 点赞 0 评论 0
def create_ctc_loss(logits, labels, timesteps, label_seq_lengths):
  with tf.variable_scope('CTC_Loss'):
    print()
    print("Labels shape")
    print(labels)
    print()
    print("Logits shape")
    print(logits)
    print()
    print("Labels len  shape")
    print(label_seq_lengths)

    # logits = tf.Print(logits, [logits], "Logits")
    ctc_loss = tf.nn.ctc_loss(labels, 
                   logits, 
                   timesteps)

    cost = tf.reduce_mean(ctc_loss, name='ctc')

    # The total loss is defined as the cross entropy loss plus all of the weight
    # decay terms (L2 loss).
    return cost
mnist.py 文件源码 项目:mnist 作者: tensorport 项目源码 文件源码 阅读 44 收藏 0 点赞 0 评论 0
def main(unused_argv):
  if FLAGS.log_dir is None or FLAGS.log_dir == "":
    raise ValueError("Must specify an explicit `log_dir`")
  if FLAGS.data_dir is None or FLAGS.data_dir == "":
    raise ValueError("Must specify an explicit `data_dir`")

  device, target = device_and_target()
  with tf.device(device):
    images = tf.placeholder(tf.float32, [None, 784], name='image_input')
    labels = tf.placeholder(tf.float32, [None], name='label_input')
    data = read_data_sets(FLAGS.data_dir,
            one_hot=False,
            fake_data=False)
    logits = mnist.inference(images, FLAGS.hidden1, FLAGS.hidden2)
    loss = mnist.loss(logits, labels)
    loss = tf.Print(loss, [loss], message="Loss = ")
    train_op = mnist.training(loss, FLAGS.learning_rate)

  with tf.train.MonitoredTrainingSession(
      master=target,
      is_chief=(FLAGS.task_index == 0),
      checkpoint_dir=FLAGS.log_dir) as sess:
    while not sess.should_stop():
      xs, ys = data.train.next_batch(FLAGS.batch_size, fake_data=False)
      sess.run(train_op, feed_dict={images:xs, labels:ys})
tf_addons.py 文件源码 项目:factorix 作者: gbouchar 项目源码 文件源码 阅读 30 收藏 0 点赞 0 评论 0
def tf_debug_gradient(x, y, verbose=True):
    """
    Print the theoretical and numeric gradients, and the absolute difference between the two
    Args:
        x (tf.Variable): input variable
        y (tf.Variable): output variable
        verbose: switch display of information

    Returns:
        the theoretical and numeric gradient
    """
    with tf.Session() as sess:
        sess.run(tf.initialize_all_variables())
        if verbose:
            print(y.eval())
        gt, gn = tf.test.compute_gradient(
                x, [d.value for d in x.get_shape()], y, [d.value for d in y.get_shape()], delta=1e-2)
        if verbose:
            print(np.concatenate((gt, gn, np.round(np.abs(gt-gn),2)), len(gt.shape) - 1))
            print(y.eval())
    return gt, gn
ssd.py 文件源码 项目:SSD_tensorflow_VOC 作者: LevinJ 项目源码 文件源码 阅读 33 收藏 0 点赞 0 评论 0
def __match_with_labels(self,gt_anchor_labels,gt_anchor_bboxes,gt_anchor_scores,jaccard,matching_threshold,gt_labels,gt_bboxes,num_anchors):
        #debugging info
        #jaccard = tf.Print(jaccard, [gt_labels], "gt_labels")
        #match default boxes to any ground truth with jaccard overlap higher than a threshold (0.5).
        mask = tf.reduce_max (jaccard, axis = 0) > matching_threshold
        mask_inds = tf.argmax(jaccard, axis = 0)
        matched_labels = tf.gather(gt_labels, mask_inds)
        gt_anchor_labels = tf.where(mask, matched_labels, gt_anchor_labels)
        gt_anchor_bboxes = tf.where(mask, tf.gather(gt_bboxes, mask_inds),gt_anchor_bboxes)
        gt_anchor_scores = tf.reduce_max(jaccard, axis= 0)



        #matching each ground truth box to the default box with the best jaccard overlap
        use_no_miss = True
        if use_no_miss:
            gt_anchor_labels,gt_anchor_bboxes,gt_anchor_scores = self.__match_no_miss(gt_anchor_labels, \
                                                                                      gt_anchor_bboxes, gt_anchor_scores, jaccard, \
                                                                                      gt_labels, gt_bboxes, num_anchors)

        return gt_anchor_labels,gt_anchor_bboxes,gt_anchor_scores
model.py 文件源码 项目:location_tracking_ml 作者: cybercom-finland 项目源码 文件源码 阅读 28 收藏 0 点赞 0 评论 0
def mixture_loss(pred, y, n_mixtures, batch_size):
    pred = tf.verify_tensor_all_finite(pred, "Pred not finite!")
    out_pi, out_sigma, out_mu, out_rho = splitMix(pred, n_mixtures, batch_size)
    result_binorm, result_delta = tf_bivariate_normal(y, out_mu, out_sigma, out_rho, n_mixtures, batch_size)

    result_binorm = tf.verify_tensor_all_finite(result_binorm, "Result not finite1!")
    result_weighted = tf.mul(result_binorm, out_pi)
    result_weighted = tf.verify_tensor_all_finite(result_weighted, "Result not finite2!")
    result_raw = tf.reduce_sum(result_weighted + epsilon, 1, keep_dims=True)
    result_raw = tf.Print(result_raw, [tf.reduce_sum(result_raw)], "Sum of weighted density. If zero, sigma is too small: ")
    result_raw = tf.Print(result_raw, [tf.reduce_max(result_raw)], "Max of weighted density. If zero, sigma is too small: ")
    result_raw = tf.verify_tensor_all_finite(result_raw, "Result not finite3!")
    result = -tf.log(result_raw + e)
    result = tf.verify_tensor_all_finite(result, "Result not finite4!")
    result = tf.reduce_sum(result)
    result = tf.verify_tensor_all_finite(result, "Result not finite5!")
    return result

# Returns the LSTM stack created based on the parameters.
# Processes several batches at once.
# Input shape is: (parameters['batch_size'], parameters['n_steps'], parameters['n_input'])
test_capacities.py 文件源码 项目:openai-rl 作者: morgangiraud 项目源码 文件源码 阅读 25 收藏 0 点赞 0 评论 0
def test_tabular_UCB(self):
        nb_states = 3
        nb_actions = 2

        with tf.Graph().as_default():
            tf.set_random_seed(1)

            inputs_t = tf.random_uniform(shape=[1], minval=0, maxval=3, dtype=tf.int32)
            # inputs_t = tf.Print(inputs_t, data=[inputs_t], message='inputs_t')

            Qs = tf.ones([nb_states, nb_actions], dtype=tf.float32)
            # Qs = tf.Print(Qs, data=[Qs], message='Qs', summarize=12)

            actions_t, probs = capacities.tabular_UCB(Qs, inputs_t)
            # actions_t = tf.Print(actions_t, data=[timestep, actions_t], message='actions_t')

            with tf.Session() as sess:
                sess.run(tf.global_variables_initializer())

                inputs, actions = sess.run([inputs_t, actions_t])
                inputs, actions = sess.run([inputs_t, actions_t])
                inputs, actions = sess.run([inputs_t, actions_t])
                self.assertEqual(np.array_equal(inputs, [ 0 ]), True)
                self.assertEqual(np.array_equal(actions, [ 0 ]), True)
model.py 文件源码 项目:streetview 作者: ydnaandy123 项目源码 文件源码 阅读 32 收藏 0 点赞 0 评论 0
def _normalize(self, x, mean, mean_sq, message):
        # make sure this is called with a variable scope
        shape = x.get_shape().as_list()
        assert len(shape) == 4
        self.gamma_driver = tf.get_variable("gamma_driver", [shape[-1]],
                                initializer=tf.random_normal_initializer(0., 0.02))
        gamma = tf.exp(self.gamma_driver)
        gamma = tf.reshape(gamma, [1, 1, 1, -1])
        self.beta = tf.get_variable("beta", [shape[-1]],
                                initializer=tf.constant_initializer(0.))
        beta = tf.reshape(self.beta, [1, 1, 1, -1])
        assert self.epsilon is not None
        assert mean_sq is not None
        assert mean is not None
        std = tf.sqrt(self.epsilon + mean_sq - tf.square(mean))
        out = x - mean
        out = out / std
        # out = tf.Print(out, [tf.reduce_mean(out, [0, 1, 2]),
        #    tf.reduce_mean(tf.square(out - tf.reduce_mean(out, [0, 1, 2], keep_dims=True)), [0, 1, 2])],
        #    message, first_n=-1)
        out = out * gamma
        out = out + beta
        return out
model.py 文件源码 项目:streetview 作者: ydnaandy123 项目源码 文件源码 阅读 31 收藏 0 点赞 0 评论 0
def _normalize(self, x, mean, mean_sq, message):
        # make sure this is called with a variable scope
        shape = x.get_shape().as_list()
        assert len(shape) == 4
        self.gamma_driver = tf.get_variable("gamma_driver", shape[1:],
                                initializer=tf.random_normal_initializer(0., 0.02))
        gamma = tf.exp(self.gamma_driver)
        gamma = tf.expand_dims(gamma, 0)
        self.beta = tf.get_variable("beta", shape[1:],
                                initializer=tf.constant_initializer(0.))
        beta = tf.expand_dims(self.beta, 0)
        assert self.epsilon is not None
        assert mean_sq is not None
        assert mean is not None
        std = tf.sqrt(self.epsilon + mean_sq - tf.square(mean))
        out = x - mean
        out = out / std
        # out = tf.Print(out, [tf.reduce_mean(out, [0, 1, 2]),
        #    tf.reduce_mean(tf.square(out - tf.reduce_mean(out, [0, 1, 2], keep_dims=True)), [0, 1, 2])],
        #    message, first_n=-1)
        out = out * gamma
        out = out + beta
        return out
model.py 文件源码 项目:streetview 作者: ydnaandy123 项目源码 文件源码 阅读 26 收藏 0 点赞 0 评论 0
def _normalize(self, x, mean, mean_sq, message):
        # make sure this is called with a variable scope
        shape = x.get_shape().as_list()
        assert len(shape) == 4
        self.gamma = tf.get_variable("gamma", [shape[-1]],
                                initializer=tf.random_normal_initializer(1., 0.02))
        gamma = tf.reshape(self.gamma, [1, 1, 1, -1])
        self.beta = tf.get_variable("beta", [shape[-1]],
                                initializer=tf.constant_initializer(0.))
        beta = tf.reshape(self.beta, [1, 1, 1, -1])
        assert self.epsilon is not None
        assert mean_sq is not None
        assert mean is not None
        std = tf.sqrt(self.epsilon + mean_sq - tf.square(mean))
        out = x - mean
        out = out / std
        # out = tf.Print(out, [tf.reduce_mean(out, [0, 1, 2]),
        #    tf.reduce_mean(tf.square(out - tf.reduce_mean(out, [0, 1, 2], keep_dims=True)), [0, 1, 2])],
        #    message, first_n=-1)
        out = out * gamma
        out = out + beta
        return out
ntm.py 文件源码 项目:ntm_keras 作者: flomlo 项目源码 文件源码 阅读 25 收藏 0 点赞 0 评论 0
def _get_weight_vector(self, M, w_tm1, k, beta, g, s, gamma):
#        M = tf.Print(M, [M, w_tm1, k], message='get weights beg1: ')
#        M = tf.Print(M, [beta, g, s, gamma], message='get weights beg2: ')
        # Content adressing, see Chapter 3.3.1:
        num = beta * _cosine_distance(M, k)
        w_c  = K.softmax(num) # It turns out that equation (5) is just softmax.
        # Location adressing, see Chapter 3.3.2:
        # Equation 7:
        w_g = (g * w_c) + (1-g)*w_tm1
        # C_s is the circular convolution
        #C_w = K.sum((self.C[None, :, :, :] * w_g[:, None, None, :]),axis=3)
        # Equation 8:
        # TODO: Explain
        C_s = K.sum(K.repeat_elements(self.C[None, :, :, :], self.batch_size, axis=0) * s[:,:,None,None], axis=1)
        w_tilda = K.batch_dot(C_s, w_g)
        # Equation 9:
        w_out = _renorm(w_tilda ** gamma)

        return w_out
preprocessing.py 文件源码 项目:stuff 作者: yaroslavvb 项目源码 文件源码 阅读 45 收藏 0 点赞 0 评论 0
def decode_jpeg(image_buffer, scope=None):  # , dtype=tf.float32):
  """Decode a JPEG string into one 3-D float image Tensor.

  Args:
    image_buffer: scalar string Tensor.
    scope: Optional scope for op_scope.
  Returns:
    3-D float Tensor with values ranging from [0, 1).
  """
  # with tf.op_scope([image_buffer], scope, 'decode_jpeg'):
  # with tf.name_scope(scope, 'decode_jpeg', [image_buffer]):
  with tf.name_scope(scope or 'decode_jpeg'):
    # Decode the string as an RGB JPEG.
    # Note that the resulting image contains an unknown height and width
    # that is set dynamically by decode_jpeg. In other words, the height
    # and width of image is unknown at compile-time.
    image = tf.image.decode_jpeg(image_buffer, channels=3,
                                 fancy_upscaling=False,
                                 dct_method='INTEGER_FAST')

    # image = tf.Print(image, [tf.shape(image)], 'Image shape: ')

    return image
goturn_net.py 文件源码 项目:GOTURN-Tensorflow 作者: tangyuhao 项目源码 文件源码 阅读 27 收藏 0 点赞 0 评论 0
def _fc_relu_layers(self, bottom, dim, name = None):
        with tf.name_scope(name) as scope:
            shape = int(np.prod(bottom.get_shape()[1:]))
            weights = tf.Variable(tf.truncated_normal([shape, dim],
                                    dtype=tf.float32, stddev=0.005), name='weights')
            bias = tf.Variable(tf.constant(1.0, shape=[dim], dtype=tf.float32), name='biases')
            bottom_flat = tf.reshape(bottom, [-1, shape])
            fc_weights = tf.nn.bias_add(tf.matmul(bottom_flat, weights), bias)
            self.parameters[name] = [weights, bias]


            if not tf.get_variable_scope().reuse:
                weight_decay = tf.multiply(tf.nn.l2_loss(weights), self.wd,
                                       name='fc_relu_weight_loss')
                tf.add_to_collection(tf.GraphKeys.REGULARIZATION_LOSSES,
                                 weight_decay)



            top = tf.nn.relu(fc_weights, name=scope)
            _activation_summary(top)
            top = tf.Print(top, [tf.shape(top)], message='Shape of %s' % name, first_n = 1, summarize=4)
            return top
goturn_net.py 文件源码 项目:GOTURN-Tensorflow 作者: tangyuhao 项目源码 文件源码 阅读 34 收藏 0 点赞 0 评论 0
def _fc_layers(self, bottom, dim, name = None):
        with tf.name_scope(name) as scope:
            shape = int(np.prod(bottom.get_shape()[1:]))
            weights = tf.Variable(tf.truncated_normal([shape, dim],
                                    dtype=tf.float32, stddev=0.005), name='weights')
            bias = tf.Variable(tf.constant(1.0, shape=[dim], dtype=tf.float32), name='biases')
            bottom_flat = tf.reshape(bottom, [-1, shape])
            top = tf.nn.bias_add(tf.matmul(bottom_flat, weights), bias, name=scope)
            self.parameters[name] = [weights, bias]

            if not tf.get_variable_scope().reuse:
                weight_decay = tf.multiply(tf.nn.l2_loss(weights), self.wd,
                                       name='fc_weight_loss')
                tf.add_to_collection(tf.GraphKeys.REGULARIZATION_LOSSES,
                                 weight_decay)

            _activation_summary(top)
            top = tf.Print(top, [tf.shape(top)], message='Shape of %s' % name, first_n = 1, summarize=4)
            return top
utils.py 文件源码 项目:lda2vec-tf 作者: meereeum 项目源码 文件源码 阅读 34 收藏 0 点赞 0 评论 0
def print_(var, name: str, first_n=10, summarize=5):
    """Util for debugging, by printing values of tf.Variable `var` during training"""

    # name = (next(k for k, v in globals().items() if v == var) # get name automagically
    #       if name is None else name) # TODO make work for list ?

    # name = (next(k for k, v in globals().items() if id(v) == id(var))
    #       if name is None else name)
    # print(name)
    # return ([k for k, v in globals().items() if id(v) == id(var)]
    #       if name is None else name)

    try:
        return tf.Print(var, [var], '{}: '.format(name), first_n=first_n,
                        summarize=summarize)

    except(TypeError): # variables are already in a list
        return tf.Print(var, var, '{}: '.format(name), first_n=first_n,
                        summarize=summarize)
kfac.py 文件源码 项目:acktr 作者: emansim 项目源码 文件源码 阅读 26 收藏 0 点赞 0 评论 0
def apply_gradients(self, grads):
        coldOptim = tf.train.MomentumOptimizer(
            self._cold_lr * (1. - self._momentum), self._momentum)

        def coldSGDstart():
            sgd_step_op = tf.assign_add(self.sgd_step, 1)
            coldOptim_op = coldOptim.apply_gradients(grads)
            if KFAC_DEBUG:
                with tf.control_dependencies([sgd_step_op, coldOptim_op]):
                    sgd_step_op = tf.Print(
                        sgd_step_op, [self.sgd_step, tf.convert_to_tensor('doing cold sgd step')])
            return tf.group(*[sgd_step_op, coldOptim_op])

        kfacOptim_op, qr = self.apply_gradients_kfac(grads)

        def warmKFACstart():
            return kfacOptim_op

        return tf.cond(tf.greater(self.sgd_step, self._cold_iter), warmKFACstart, coldSGDstart), qr
tf_tree_lstm.py 文件源码 项目:RecursiveNN 作者: sapruash 项目源码 文件源码 阅读 26 收藏 0 点赞 0 评论 0
def add_training_op(self):
        loss=self.total_loss
        opt1=tf.train.AdagradOptimizer(self.config.lr)
        opt2=tf.train.AdagradOptimizer(self.config.emb_lr)

        ts=tf.trainable_variables()
        gs=tf.gradients(loss,ts)
        gs_ts=zip(gs,ts)

        gt_emb,gt_nn=[],[]
        for g,t in gs_ts:
            #print t.name,g.name
            if "Embed/embedding:0" in t.name:
                #g=tf.Print(g,[g.get_shape(),t.get_shape()])
                gt_emb.append((g,t))
                #print t.name
            else:
                gt_nn.append((g,t))
                #print t.name

        train_op1=opt1.apply_gradients(gt_nn)
        train_op2=opt2.apply_gradients(gt_emb)
        train_op=[train_op1,train_op2]

        return train_op
copy_task.py 文件源码 项目:Neural-Turing-Machine 作者: yeoedward 项目源码 文件源码 阅读 25 收藏 0 点赞 0 评论 0
def bits_err_per_seq(out, expected, nsteps):
  rel_pred = predict(out, nsteps)
  rel_pred = tf.Print(
    rel_pred,
    [tf.slice(rel_pred, [0, 0, 0], [1, -1, 1])],
    "predicted",
    summarize=20,
  )
  expected = tf.Print(
    expected,
    [tf.slice(expected, [0, 0, 0], [1, -1, 1])],
    "expected",
    summarize=20,
  )
  diff = rel_pred - expected
  return tf.reduce_mean(tf.reduce_sum(tf.abs(diff), [1, 2]))
unet.py 文件源码 项目:lung-cancer-detector 作者: YichenGong 项目源码 文件源码 阅读 31 收藏 0 点赞 0 评论 0
def _get_optimizer(self, training_iters, global_step):
        if self.optimizer == "momentum":
            learning_rate = self.opt_kwargs.pop("learning_rate", 0.2)
            decay_rate = self.opt_kwargs.pop("decay_rate", 0.95)

            self.learning_rate_node = tf.train.exponential_decay(learning_rate=learning_rate, 
                                                        global_step=global_step, 
                                                        decay_steps=training_iters,  
                                                        decay_rate=decay_rate, 
                                                        staircase=True)

            optimizer = tf.train.MomentumOptimizer(learning_rate=self.learning_rate_node, momentum=0.9,
                                                   **self.opt_kwargs).minimize(self.net.cost, 
                                                                                global_step=global_step)
            # optimizer = tf.train.MomentumOptimizer(learning_rate=self.learning_rate_node, momentum=0.9,
            #                                        **self.opt_kwargs)
            # gvs = optimizer.compute_gradients(self.net.cost)
            # # [print(grad) for grad, var in gvs]
            # tf.Print(self.net.cost,self.net.cost)
            # capped_gvs = [(tf.clip_by_value(grad, -1., 1.), var) for grad, var in gvs]
            # train_op = optimizer.apply_gradients(capped_gvs, global_step=global_step)
        elif self.optimizer == "adam":
            learning_rate = self.opt_kwargs.pop("learning_rate", 0.001)
            self.learning_rate_node = tf.Variable(learning_rate)

            optimizer = tf.train.AdamOptimizer(learning_rate=self.learning_rate_node,  
                                               **self.opt_kwargs).minimize(self.net.cost,
                                                                     global_step=global_step)

        return optimizer
rpn_data.py 文件源码 项目:tf-image-interpreter 作者: ThoughtWorksInc 项目源码 文件源码 阅读 33 收藏 0 点赞 0 评论 0
def _filter_inside_anchors(self, all_anchors, height, width):
    # filter anchors
    inds_inside = tf.where(
      (all_anchors[:, 0] > 0) &
      (all_anchors[:, 1] > 0) &
      (all_anchors[:, 2] < width) &
      (all_anchors[:, 3] < height)
    )
    if self._debug:
      inds_inside = tf.Print(inds_inside, [tf.shape(inds_inside)], message='inside anchors: ')
    anchors = tf.gather(all_anchors, inds_inside)
    return anchors
common.py 文件源码 项目:tf-image-interpreter 作者: ThoughtWorksInc 项目源码 文件源码 阅读 26 收藏 0 点赞 0 评论 0
def _generate_all_anchors(self, shifts):
    num_anchors = self._anchors.shape[0]
    num_shifts = tf.shape(shifts)[0]
    all_anchors = (self._anchors.reshape(1, num_anchors, 4) +
                   tf.transpose(tf.reshape(shifts, (1, num_shifts, 4)), perm=(1, 0, 2)))
    all_anchors = tf.reshape(all_anchors, (num_shifts * num_anchors, 4))

    if self._debug:
      num_all_anchors = num_shifts * num_anchors
      tf.Print(num_all_anchors, [num_all_anchors], message='all anchor: ')
    return all_anchors


问题


面经


文章

微信
公众号

扫码关注公众号