Python tensorflow.logical_not函数代码示例

  def get_scheduled_sample_inputs(self,
                                  done_warm_start,
                                  groundtruth_items,
                                  generated_items,
                                  scheduled_sampling_func):
    """Scheduled sampling.

    Args:
      done_warm_start: whether we are done with warm start or not.
      groundtruth_items: list of ground truth items.
      generated_items: list of generated items.
      scheduled_sampling_func: scheduled sampling function to choose between
        groundtruth items and generated items.

    Returns:
      A mix list of ground truth and generated items.
    """
    def sample():
      """Calculate the scheduled sampling params based on iteration number."""
      with tf.variable_scope("scheduled_sampling", reuse=tf.AUTO_REUSE):
        output_items = []
        for item_gt, item_gen in zip(groundtruth_items, generated_items):
          output_items.append(scheduled_sampling_func(item_gt, item_gen))
        return output_items

    cases = [
        (tf.logical_not(done_warm_start), lambda: groundtruth_items),
        (tf.logical_not(self.is_training), lambda: generated_items),
    ]
    output_items = tf.case(cases, default=sample, strict=True)

    return output_items

  def train(self, sentences):
    token_ids, token_values, token_dense_shape = self._tokenize(sentences)
    tokens_sparse = tf.sparse.SparseTensor(
        indices=token_ids, values=token_values, dense_shape=token_dense_shape)
    tokens = tf.sparse.to_dense(tokens_sparse, default_value="")

    sparse_lookup_ids = tf.sparse.SparseTensor(
        indices=tokens_sparse.indices,
        values=self._words_to_indices(tokens_sparse.values),
        dense_shape=tokens_sparse.dense_shape)
    lookup_ids = tf.sparse.to_dense(sparse_lookup_ids, default_value=0)

    # Targets are the next word for each word of the sentence.
    tokens_ids_seq = lookup_ids[:, 0:-1]
    tokens_ids_target = lookup_ids[:, 1:]

    tokens_prefix = tokens[:, 0:-1]

    # Mask determining which positions we care about for a loss: all positions
    # that have a valid non-terminal token.
    mask = tf.logical_and(
        tf.logical_not(tf.equal(tokens_prefix, "")),
        tf.logical_not(tf.equal(tokens_prefix, "<E>")))

    input_mask = tf.cast(mask, tf.int32)

    with tf.GradientTape() as t:
      sentence_embeddings = tf.nn.embedding_lookup(self._embeddings,
                                                   tokens_ids_seq)

      lstm_initial_state = self._lstm_cell.get_initial_state(
          sentence_embeddings)

      lstm_output = self._rnn_layer(
          inputs=sentence_embeddings, initial_state=lstm_initial_state)

      # Stack LSTM outputs into a batch instead of a 2D array.
      lstm_output = tf.reshape(lstm_output, [-1, self._lstm_cell.output_size])

      logits = self._logit_layer(lstm_output)

      targets = tf.reshape(tokens_ids_target, [-1])
      weights = tf.cast(tf.reshape(input_mask, [-1]), tf.float32)

      losses = tf.nn.sparse_softmax_cross_entropy_with_logits(
          labels=targets, logits=logits)

      # Final loss is the mean loss for all token losses.
      final_loss = tf.math.divide(
          tf.reduce_sum(tf.multiply(losses, weights)),
          tf.reduce_sum(weights),
          name="final_loss")

    watched = t.watched_variables()
    gradients = t.gradient(final_loss, watched)

    for w, g in zip(watched, gradients):
      w.assign_sub(g)

    return final_loss

    def getRpRnTpTnForTrain0OrVal1(self, y, training0OrValidation1):
        # The returned list has (numberOfClasses)x4 integers: >numberOfRealPositives, numberOfRealNegatives, numberOfTruePredictedPositives, numberOfTruePredictedNegatives< for each class (incl background).
        # Order in the list is the natural order of the classes (ie class-0 RP,RN,TPP,TPN, class-1 RP,RN,TPP,TPN, class-2 RP,RN,TPP,TPN ...)
        # param y: y = T.itensor4('y'). Dimensions [batchSize, r, c, z]
        
        yPredToUse = self.y_pred_train if  training0OrValidation1 == 0 else self.y_pred_val
        
        returnedListWithNumberOfRpRnTpTnForEachClass = []
        
        for class_i in range(0, self._numberOfOutputClasses) :
            #Number of Real Positive, Real Negatives, True Predicted Positives and True Predicted Negatives are reported PER CLASS (first for WHOLE).
            tensorOneAtRealPos = tf.equal(y, class_i)
            tensorOneAtRealNeg = tf.logical_not(tensorOneAtRealPos)

            tensorOneAtPredictedPos = tf.equal(yPredToUse, class_i)
            tensorOneAtPredictedNeg = tf.logical_not(tensorOneAtPredictedPos)
            tensorOneAtTruePos = tf.logical_and(tensorOneAtRealPos,tensorOneAtPredictedPos)
            tensorOneAtTrueNeg = tf.logical_and(tensorOneAtRealNeg,tensorOneAtPredictedNeg)
                    
            returnedListWithNumberOfRpRnTpTnForEachClass.append( tf.reduce_sum( tf.cast(tensorOneAtRealPos, dtype="int32")) )
            returnedListWithNumberOfRpRnTpTnForEachClass.append( tf.reduce_sum( tf.cast(tensorOneAtRealNeg, dtype="int32")) )
            returnedListWithNumberOfRpRnTpTnForEachClass.append( tf.reduce_sum( tf.cast(tensorOneAtTruePos, dtype="int32")) )
            returnedListWithNumberOfRpRnTpTnForEachClass.append( tf.reduce_sum( tf.cast(tensorOneAtTrueNeg, dtype="int32")) )
            
        return returnedListWithNumberOfRpRnTpTnForEachClass

        def m_body(i, ta_tp, ta_fp, gmatch):
            # Jaccard score with groundtruth bboxes.
            rbbox = bboxes[i]
            jaccard = bboxes_jaccard(rbbox, gbboxes)
            jaccard = jaccard * tf.cast(tf.equal(glabels, rlabel), dtype=jaccard.dtype)

            # Best fit, checking it's above threshold.
            idxmax = tf.cast(tf.argmax(jaccard, axis=0), tf.int32)
            jcdmax = jaccard[idxmax]
            match = jcdmax > matching_threshold
            existing_match = gmatch[idxmax]
            not_difficult = tf.logical_not(gdifficults[idxmax])

            # TP: match & no previous match and FP: previous match | no match.
            # If difficult: no record, i.e FP=False and TP=False.
            tp = tf.logical_and(not_difficult,
                                tf.logical_and(match, tf.logical_not(existing_match)))
            ta_tp = ta_tp.write(i, tp)
            fp = tf.logical_and(not_difficult,
                                tf.logical_or(existing_match, tf.logical_not(match)))
            ta_fp = ta_fp.write(i, fp)
            # Update grountruth match.
            mask = tf.logical_and(tf.equal(grange, idxmax),
                                  tf.logical_and(not_difficult, match))
            gmatch = tf.logical_or(gmatch, mask)

            return [i+1, ta_tp, ta_fp, gmatch]

        def m_body(i, ta_tp, ta_fp, gmatch, n_ignored_det):
            # Jaccard score with groundtruth bboxes.
            rbbox = bboxes[i, :]
#             rbbox = tf.Print(rbbox, [rbbox])
            jaccard = bboxes_jaccard(rbbox, gxs, gys)

            # Best fit, checking it's above threshold.
            idxmax = tf.cast(tf.argmax(jaccard, axis=0), dtype = tf.int32)
            
            jcdmax = jaccard[idxmax]
            match = jcdmax > matching_threshold
            existing_match = gmatch[idxmax]
            not_ignored = tf.logical_not(gignored[idxmax])

            n_ignored_det = n_ignored_det + tf.cast(gignored[idxmax], tf.int32)
            # TP: match & no previous match and FP: previous match | no match.
            # If ignored: no record, i.e FP=False and TP=False.
            tp = tf.logical_and(not_ignored, tf.logical_and(match, tf.logical_not(existing_match)))
            ta_tp = ta_tp.write(i, tp)
            
            fp = tf.logical_and(not_ignored, tf.logical_or(existing_match, tf.logical_not(match)))
            ta_fp = ta_fp.write(i, fp)
            
            # Update grountruth match.
            mask = tf.logical_and(tf.equal(grange, idxmax), tf.logical_and(not_ignored, match))
            gmatch = tf.logical_or(gmatch, mask)
            return [i+1, ta_tp, ta_fp, gmatch,n_ignored_det]

    def build_graph(self, nn_im_w, nn_im_h, num_colour_channels=3, weights=None, biases=None):
        num_outputs = 1 #ofc
        self.nn_im_w = nn_im_w
        self.nn_im_h = nn_im_h

        if weights is None:
            weights = [None, None, None, None, None]
        if biases is None:
            biases = [None, None, None, None, None]

        with tf.device('/cpu:0'):
            # Placeholder variables for the input image and output images
            self.x = tf.placeholder(tf.float32, shape=[None, nn_im_w*nn_im_h*3])
            self.y_ = tf.placeholder(tf.float32, shape=[None, num_outputs])
            self.threshold = tf.placeholder(tf.float32)

            # Build the convolutional and pooling layers
            conv1_output_channels = 32
            conv2_output_channels = 16
            conv3_output_channels = 8

            conv_layer_1_input = tf.reshape(self.x, [-1, nn_im_h, nn_im_w, num_colour_channels]) #The resized input image
            self.build_conv_layer(conv_layer_1_input, num_colour_channels, conv1_output_channels, initial_weights=weights[0], initial_biases=biases[0]) # layer 1
            self.build_conv_layer(self.layers[0][0], conv1_output_channels, conv2_output_channels, initial_weights=weights[1], initial_biases=biases[1])# layer 2
            self.build_conv_layer(self.layers[1][0], conv2_output_channels, conv3_output_channels, initial_weights=weights[2], initial_biases=biases[2])# layer 3

            # Build the fully connected layer
            convnet_output_w = nn_im_w//8
            convnet_output_h = nn_im_h//8

            fully_connected_layer_input = tf.reshape(self.layers[2][0], [-1, convnet_output_w * convnet_output_h * conv3_output_channels])
            self.build_fully_connected_layer(fully_connected_layer_input, convnet_output_w, convnet_output_h, conv3_output_channels, initial_weights=weights[3], initial_biases=biases[3])

            # The dropout stage and readout layer
            self.keep_prob, self.h_drop = self.dropout(self.layers[3][0])
            self.y_conv,_,_ = self.build_readout_layer(self.h_drop, num_outputs, initial_weights=weights[4], initial_biases=biases[4])

            self.mean_error =  tf.sqrt(tf.reduce_mean(tf.square(self.y_ - self.y_conv)))
            self.train_step = tf.train.AdamOptimizer(1e-4).minimize(self.mean_error)

            self.accuracy = (1.0 - tf.reduce_mean(tf.abs(self.y_ - tf.round(self.y_conv))))


            positive_examples = tf.greater_equal(self.y_, 0.5)
            negative_examples = tf.logical_not(positive_examples)
            positive_classifications = tf.greater_equal(self.y_conv, self.threshold)
            negative_classifications = tf.logical_not(positive_classifications)

            self.true_positive = tf.reduce_sum(tf.cast(tf.logical_and(positive_examples, positive_classifications),tf.int32)) # count the examples that are positive and classified as positive
            self.false_positive = tf.reduce_sum(tf.cast(tf.logical_and(negative_examples, positive_classifications),tf.int32)) # count the examples that are negative but classified as positive

            self.true_negative = tf.reduce_sum(tf.cast(tf.logical_and(negative_examples, negative_classifications),tf.int32)) # count the examples that are negative and classified as negative
            self.false_negative = tf.reduce_sum(tf.cast(tf.logical_and(positive_examples, negative_classifications),tf.int32)) # count the examples that are positive but classified as negative

            self.positive_count = tf.reduce_sum(tf.cast(positive_examples, tf.int32)) # count the examples that are positive
            self.negative_count = tf.reduce_sum(tf.cast(negative_examples, tf.int32)) # count the examples that are negative

            self.confusion_matrix = tf.reshape(tf.pack([self.true_positive, self.false_positive, self.false_negative, self.true_negative]), [2,2])

        self.sess.run(tf.initialize_all_variables())

 def compute_error(self):
   #Sets mask variables and performs batch processing
   self.batch_gold_select = self.batch_print_answer > 0.0
   self.full_column_mask = tf.concat(
       axis=1, values=[self.batch_number_column_mask, self.batch_word_column_mask])
   self.full_processed_column = tf.concat(
       axis=1,
       values=[self.batch_processed_number_column, self.batch_processed_word_column])
   self.full_processed_sorted_index_column = tf.concat(axis=1, values=[
       self.batch_processed_sorted_index_number_column,
       self.batch_processed_sorted_index_word_column
   ])
   self.select_bad_number_mask = tf.cast(
       tf.logical_and(
           tf.not_equal(self.full_processed_column,
                        self.utility.FLAGS.pad_int),
           tf.not_equal(self.full_processed_column,
                        self.utility.FLAGS.bad_number_pre_process)),
       self.data_type)
   self.select_mask = tf.cast(
       tf.logical_not(
           tf.equal(self.batch_number_column, self.utility.FLAGS.pad_int)),
       self.data_type)
   self.select_word_mask = tf.cast(
       tf.logical_not(
           tf.equal(self.batch_word_column_entry_mask,
                    self.utility.dummy_token_id)), self.data_type)
   self.select_full_mask = tf.concat(
       axis=1, values=[self.select_mask, self.select_word_mask])
   self.select_whole_mask = tf.maximum(
       tf.reshape(
           tf.slice(self.select_mask, [0, 0, 0],
                    [self.batch_size, 1, self.max_elements]),
           [self.batch_size, self.max_elements]),
       tf.reshape(
           tf.slice(self.select_word_mask, [0, 0, 0],
                    [self.batch_size, 1, self.max_elements]),
           [self.batch_size, self.max_elements]))
   self.invert_select_full_mask = tf.cast(
       tf.concat(axis=1, values=[
           tf.equal(self.batch_number_column, self.utility.FLAGS.pad_int),
           tf.equal(self.batch_word_column_entry_mask,
                    self.utility.dummy_token_id)
       ]), self.data_type)
   self.batch_lookup_answer = tf.zeros(tf.shape(self.batch_gold_select))
   self.reset_select = self.select_whole_mask
   self.rows = tf.reduce_sum(self.select_whole_mask, 1)
   self.num_entries = tf.reshape(
       tf.reduce_sum(tf.reduce_sum(self.select_full_mask, 1), 1),
       [self.batch_size])
   self.final_error, self.final_correct = self.batch_process()
   return self.final_error

 def recall(self, y_):
     y_true = tf.cast(tf.argmin(y_, 1), tf.bool)
     y_pred = tf.cast(tf.argmin(self.y, 1), tf.bool)
     # 1 stands for positive, 0 stands for negative
     tp = tf.reduce_sum(tf.cast(tf.logical_and(y_true, y_pred), tf.float32))
     tn = tf.reduce_sum(tf.cast(tf.logical_not(tf.logical_or(y_true, y_pred)), tf.float32))
     p = tf.reduce_sum(tf.cast(y_true, tf.float32))
     n = tf.reduce_sum(tf.cast(tf.logical_not(y_true), tf.float32))
     fp = p - tp
     fn = n - tn
     # t = tf.add(tp, tn)
     # f = tf.add(fp, fn)
     relevant = tf.add(tp, fn)
     recall = tf.div(tp, relevant)
     return recall

def _has_foreground_and_background_in_first_frame_2(label,
                                                    decoder_output_stride):
  """Checks if the labels have foreground and background in the first frame.

  Second attempt, this time we use the actual output dimension for resizing.

  Args:
    label: Label tensor of shape [num_frames, height, width, 1].
    decoder_output_stride: Integer, the stride of the decoder output.

  Returns:
    Boolean, whether the labels have foreground and background in the first
      frame.
  """
  h, w = train_utils.resolve_shape(label)[1:3]
  h_sub = model.scale_dimension(h, 1.0 / decoder_output_stride)
  w_sub = model.scale_dimension(w, 1.0 / decoder_output_stride)
  label_downscaled = tf.squeeze(
      tf.image.resize_nearest_neighbor(label[0, tf.newaxis], [h_sub, w_sub],
                                       align_corners=True), axis=0)
  is_bg = tf.equal(label_downscaled, 0)
  is_fg = tf.logical_not(is_bg)
  # Just using reduce_any was not robust enough, so lets make sure the count
  # is above MIN_LABEL_COUNT.
  fg_count = tf.reduce_sum(tf.cast(is_fg, tf.int32))
  bg_count = tf.reduce_sum(tf.cast(is_bg, tf.int32))
  has_bg = tf.greater_equal(fg_count, MIN_LABEL_COUNT)
  has_fg = tf.greater_equal(bg_count, MIN_LABEL_COUNT)
  return tf.logical_and(has_bg, has_fg)

def read_record(filename_queue):
    class FCNRecord(object):
        pass
    result = FCNRecord()
    result.mask_height = int(420/DOWNSAMPLE_FACTOR)
    result.mask_width = int(580/DOWNSAMPLE_FACTOR)
    result.mask_depth = 1
    result.img_depth = 1
    img_len = result.mask_height*result.mask_width*result.img_depth
    mask_len = result.mask_height*result.mask_width*result.mask_depth
    record_len = img_len + mask_len

    reader = tf.FixedLengthRecordReader(record_bytes=record_len)
    result.key, value = reader.read(filename_queue)
    record_bytes = tf.decode_raw(value, tf.uint8)
    #print(record_bytes.get_shape())
    int_image = tf.reshape(tf.slice(record_bytes, [0], [img_len]),[result.mask_height, result.mask_width])
    rgb_image = tf.pack([int_image,int_image,int_image])
    rgb_img = tf.transpose(rgb_image,(1,2,0))
    result.image = tf.cast(rgb_img,tf.float32)
    bool_mask = tf.cast( tf.reshape(tf.slice(record_bytes, [img_len], [mask_len]),[result.mask_height, result.mask_width]), tf.bool)
    hot_mask= tf.pack( [bool_mask, tf.logical_not(bool_mask)])
    h_mask = tf.transpose(hot_mask,(1,2,0))
    result.mask = tf.cast(h_mask, tf.float32)
    return result

def aggregate_single_gradient(grad_and_vars, use_mean, check_inf_nan):
    """Calculate the average gradient for a shared variable across all towers.

  Note that this function provides a synchronization point across all towers.

  Args:
    grad_and_vars: A list or tuple of (gradient, variable) tuples. Each
      (gradient, variable) pair within the outer list represents the gradient
      of the variable calculated for a single tower, and the number of pairs
      equals the number of towers.
    use_mean: if True, mean is taken, else sum of gradients is taken.
    check_inf_nan: check grads for nans and infs.

  Returns:
    The tuple ([(average_gradient, variable),], has_nan_or_inf) where the
      gradient has been averaged across all towers. The variable is chosen from
      the first tower. The has_nan_or_inf indicates the grads has nan or inf.
  """
    grads = [g for g, _ in grad_and_vars]
    grad = tf.add_n(grads)

    if use_mean and len(grads) > 1:
        grad = tf.multiply(grad, 1.0 / len(grads))

    v = grad_and_vars[0][1]
    if check_inf_nan:
        has_nan_or_inf = tf.logical_not(tf.reduce_all(tf.is_finite(grads)))
        return (grad, v), has_nan_or_inf
    else:
        return (grad, v), None

  def _inverse_log_det_jacobian(self, y, use_saved_statistics=False):
    if not self.batchnorm.built:
      # Create variables.
      self.batchnorm.build(y.shape)

    event_dims = self.batchnorm.axis
    reduction_axes = [i for i in range(len(y.shape)) if i not in event_dims]

    # At training-time, ildj is computed from the mean and log-variance across
    # the current minibatch.
    # We use multiplication instead of tf.where() to get easier broadcasting.
    use_saved_statistics = tf.cast(
        tf.logical_or(use_saved_statistics, tf.logical_not(self._training)),
        tf.float32)
    log_variance = tf.log(
        (1 - use_saved_statistics) * tf.nn.moments(y, axes=reduction_axes,
                                                   keep_dims=True)[1]
        + use_saved_statistics * self.batchnorm.moving_variance
        + self.batchnorm.epsilon)

    # `gamma` and `log Var(y)` reductions over event_dims.
    # Log(total change in area from gamma term).
    log_total_gamma = tf.reduce_sum(tf.log(self.batchnorm.gamma))

    # Log(total change in area from log-variance term).
    log_total_variance = tf.reduce_sum(log_variance)
    # The ildj is scalar, as it does not depend on the values of x and are
    # constant across minibatch elements.
    return log_total_gamma - 0.5 * log_total_variance

def loss_estimate(batch_size,old_state,data,total_data,model_params,base_mean,base_log_var):
    clipped_log_vals, nan_mask, reset_rows = data


    zeros = tf.zeros_like(clipped_log_vals)
    state_init = model_params.init_state(batch_size)
    data_count = tf.reduce_sum(tf.to_float(tf.logical_not(nan_mask)),name='data_count')
    
    model_input = tf.select(nan_mask,zeros,clipped_log_vals)
    target_outputs = model_input

    sample_params = model_params.sample_vals(batch_size)

    #TODO verify significance of old_state
    filtered_state = tf.select(reset_rows,old_state,state_init)

    new_state,delta_mean = sample_inference(filtered_state,model_input,sample_params)
    variance = tf.exp(base_log_var)
    mean = base_mean + delta_mean * variance

    raw_losses = gaussian_neg_log_likelyhood(target_outputs,mean,variance)
    clean_raw_losses = tf.select(nan_mask,zeros,raw_losses)
    raw_loss = tf.reduce_sum(clean_raw_losses)

    kl_divergence = model_params.get_divergence()

    loss_estimate = raw_loss * (total_data / data_count) + kl_divergence

    return loss_estimate,new_state,kl_divergence

def IoU(bbox, gt):

    # bbox = [ x , y , w , h ] ( x , y  left up)

    shape = [-1, 1]

    x1 = tf.maximum(tf.cast(bbox[0], tf.float32), tf.reshape(tf.cast(gt[:,0], tf.float32), shape))
    y1 = tf.maximum(tf.cast(bbox[1], tf.float32), tf.reshape(tf.cast(gt[:,1], tf.float32), shape))
    x2 = tf.minimum(tf.cast(bbox[2] + bbox[0], tf.float32), tf.reshape(tf.cast(gt[:,2] + gt[:,0], tf.float32), shape))
    y2 = tf.minimum(tf.cast(bbox[3] + bbox[1], tf.float32), tf.reshape(tf.cast(gt[:,3] + gt[:,1], tf.float32), shape))


    inter_w = tf.sub(x2,x1)

    inter_h = tf.sub(y2,y1)

    inter = tf.cast(inter_w * inter_h, tf.float32)

    bounding_box = tf.cast(tf.mul(bbox[2],bbox[3]), tf.float32)

    ground_truth = tf.reshape(tf.cast(tf.mul(gt[:,2],gt[:,3]), tf.float32), shape)

    #iou = tf.div(inter,tf.sub(tf.add(bounding_box,tf.reshape(ground_truth,shape)),inter))

    iou = inter / (bounding_box + ground_truth - inter)

    # limit the iou range between 0 and 1
    
    mask_less = tf.cast(tf.logical_not(tf.less(iou, tf.zeros_like(iou))), tf.float32)
    #mask_great = tf.cast(tf.logical_not(tf.greater(iou, tf.ones_like(iou))), tf.float32)
    
    iou = tf.mul(iou, mask_less)
    #iou = tf.mul(iou, positive_mask)
    
    return iou

def filter_groundtruth_with_nan_box_coordinates(tensor_dict):
  """Filters out groundtruth with no bounding boxes.

  Args:
    tensor_dict: a dictionary of following groundtruth tensors -
      fields.InputDataFields.groundtruth_boxes
      fields.InputDataFields.groundtruth_classes
      fields.InputDataFields.groundtruth_confidences
      fields.InputDataFields.groundtruth_keypoints
      fields.InputDataFields.groundtruth_instance_masks
      fields.InputDataFields.groundtruth_is_crowd
      fields.InputDataFields.groundtruth_area
      fields.InputDataFields.groundtruth_label_types

  Returns:
    a dictionary of tensors containing only the groundtruth that have bounding
    boxes.
  """
  groundtruth_boxes = tensor_dict[fields.InputDataFields.groundtruth_boxes]
  nan_indicator_vector = tf.greater(tf.reduce_sum(tf.to_int32(
      tf.is_nan(groundtruth_boxes)), reduction_indices=[1]), 0)
  valid_indicator_vector = tf.logical_not(nan_indicator_vector)
  valid_indices = tf.where(valid_indicator_vector)

  return retain_groundtruth(tensor_dict, valid_indices)