Python numpy.max() Examples

The following are 30 code examples for showing how to use numpy.max(). These examples are extracted from open source projects. You can vote up the ones you like or vote down the ones you don't like, and go to the original project or source file by following the links above each example.

You may check out the related API usage on the sidebar.

You may also want to check out all available functions/classes of the module numpy , or try the search function .

Example 1
Project: aospy   Author: spencerahill   File: vertcoord.py    License: Apache License 2.0 6 votes vote down vote up
def to_radians(arr, is_delta=False):
    """Force data with units either degrees or radians to be radians."""
    # Infer the units from embedded metadata, if it's there.
    try:
        units = arr.units
    except AttributeError:
        pass
    else:
        if units.lower().startswith('degrees'):
            warn_msg = ("Conversion applied: degrees -> radians to array: "
                        "{}".format(arr))
            logging.debug(warn_msg)
            return np.deg2rad(arr)
    # Otherwise, assume degrees if the values are sufficiently large.
    threshold = 0.1*np.pi if is_delta else 4*np.pi
    if np.max(np.abs(arr)) > threshold:
        warn_msg = ("Conversion applied: degrees -> radians to array: "
                    "{}".format(arr))
        logging.debug(warn_msg)
        return np.deg2rad(arr)
    return arr 
Example 2
Project: MPContribs   Author: materialsproject   File: pre_submission.py    License: MIT License 6 votes vote down vote up
def load_RSM(filename):
    om, tt, psd = xu.io.getxrdml_map(filename)
    om = np.deg2rad(om)
    tt = np.deg2rad(tt)
    wavelength = 1.54056

    q_y = (1 / wavelength) * (np.cos(tt) - np.cos(2 * om - tt))
    q_x = (1 / wavelength) * (np.sin(tt) - np.sin(2 * om - tt))

    xi = np.linspace(np.min(q_x), np.max(q_x), 100)
    yi = np.linspace(np.min(q_y), np.max(q_y), 100)
    psd[psd < 1] = 1
    data_grid = griddata(
        (q_x, q_y), psd, (xi[None, :], yi[:, None]), fill_value=1, method="cubic"
    )
    nx, ny = data_grid.shape

    range_values = [np.min(q_x), np.max(q_x), np.min(q_y), np.max(q_y)]
    output_data = (
        Panel(np.log(data_grid).reshape(nx, ny, 1), minor_axis=["RSM"])
        .transpose(2, 0, 1)
        .to_frame()
    )

    return range_values, output_data 
Example 3
Project: disentangling_conditional_gans   Author: zalandoresearch   File: dataset_tool.py    License: MIT License 6 votes vote down vote up
def create_mnist(tfrecord_dir, mnist_dir):
    print('Loading MNIST from "%s"' % mnist_dir)
    import gzip
    with gzip.open(os.path.join(mnist_dir, 'train-images-idx3-ubyte.gz'), 'rb') as file:
        images = np.frombuffer(file.read(), np.uint8, offset=16)
    with gzip.open(os.path.join(mnist_dir, 'train-labels-idx1-ubyte.gz'), 'rb') as file:
        labels = np.frombuffer(file.read(), np.uint8, offset=8)
    images = images.reshape(-1, 1, 28, 28)
    images = np.pad(images, [(0,0), (0,0), (2,2), (2,2)], 'constant', constant_values=0)
    assert images.shape == (60000, 1, 32, 32) and images.dtype == np.uint8
    assert labels.shape == (60000,) and labels.dtype == np.uint8
    assert np.min(images) == 0 and np.max(images) == 255
    assert np.min(labels) == 0 and np.max(labels) == 9
    onehot = np.zeros((labels.size, np.max(labels) + 1), dtype=np.float32)
    onehot[np.arange(labels.size), labels] = 1.0
    
    with TFRecordExporter(tfrecord_dir, images.shape[0]) as tfr:
        order = tfr.choose_shuffled_order()
        for idx in range(order.size):
            tfr.add_image(images[order[idx]])
        tfr.add_labels(onehot[order])

#---------------------------------------------------------------------------- 
Example 4
Project: disentangling_conditional_gans   Author: zalandoresearch   File: dataset_tool.py    License: MIT License 6 votes vote down vote up
def create_mnistrgb(tfrecord_dir, mnist_dir, num_images=1000000, random_seed=123):
    print('Loading MNIST from "%s"' % mnist_dir)
    import gzip
    with gzip.open(os.path.join(mnist_dir, 'train-images-idx3-ubyte.gz'), 'rb') as file:
        images = np.frombuffer(file.read(), np.uint8, offset=16)
    images = images.reshape(-1, 28, 28)
    images = np.pad(images, [(0,0), (2,2), (2,2)], 'constant', constant_values=0)
    assert images.shape == (60000, 32, 32) and images.dtype == np.uint8
    assert np.min(images) == 0 and np.max(images) == 255
    
    with TFRecordExporter(tfrecord_dir, num_images) as tfr:
        rnd = np.random.RandomState(random_seed)
        for idx in range(num_images):
            tfr.add_image(images[rnd.randint(images.shape[0], size=3)])

#---------------------------------------------------------------------------- 
Example 5
Project: disentangling_conditional_gans   Author: zalandoresearch   File: dataset_tool.py    License: MIT License 6 votes vote down vote up
def create_cifar100(tfrecord_dir, cifar100_dir):
    print('Loading CIFAR-100 from "%s"' % cifar100_dir)
    import pickle
    with open(os.path.join(cifar100_dir, 'train'), 'rb') as file:
        data = pickle.load(file, encoding='latin1')
    images = data['data'].reshape(-1, 3, 32, 32)
    labels = np.array(data['fine_labels'])
    assert images.shape == (50000, 3, 32, 32) and images.dtype == np.uint8
    assert labels.shape == (50000,) and labels.dtype == np.int32
    assert np.min(images) == 0 and np.max(images) == 255
    assert np.min(labels) == 0 and np.max(labels) == 99
    onehot = np.zeros((labels.size, np.max(labels) + 1), dtype=np.float32)
    onehot[np.arange(labels.size), labels] = 1.0

    with TFRecordExporter(tfrecord_dir, images.shape[0]) as tfr:
        order = tfr.choose_shuffled_order()
        for idx in range(order.size):
            tfr.add_image(images[order[idx]])
        tfr.add_labels(onehot[order])

#---------------------------------------------------------------------------- 
Example 6
Project: spectrum_painter   Author: polygon   File: spectrum_painter.py    License: MIT License 6 votes vote down vote up
def convert_image(self, filename):
        pic = img.imread(filename)
        # Set FFT size to be double the image size so that the edge of the spectrum stays clear
        # preventing some bandfilter artifacts
        self.NFFT = 2*pic.shape[1]

        # Repeat image lines until each one comes often enough to reach the desired line time
        ffts = (np.flipud(np.repeat(pic[:, :, 0], self.repetitions, axis=0) / 16.)**2.) / 256.

        # Embed image in center bins of the FFT
        fftall = np.zeros((ffts.shape[0], self.NFFT))
        startbin = int(self.NFFT/4)
        fftall[:, startbin:(startbin+pic.shape[1])] = ffts

        # Generate random phase vectors for the FFT bins, this is important to prevent high peaks in the output
        # The phases won't be visible in the spectrum
        phases = 2*np.pi*np.random.rand(*fftall.shape)
        rffts = fftall * np.exp(1j*phases)

        # Perform the FFT per image line, then concatenate them to form the final signal
        timedata = np.fft.ifft(np.fft.ifftshift(rffts, axes=1), axis=1) / np.sqrt(float(self.NFFT))
        linear = timedata.flatten()
        linear = linear / np.max(np.abs(linear))
        return linear 
Example 7
Project: Deep_VoiceChanger   Author: pstuvwx   File: dataset.py    License: MIT License 6 votes vote down vote up
def wave2input_image(wave, window, pos=0, pad=0):
    wave_image = np.hstack([wave[pos+i*sride:pos+(i+pad*2)*sride+dif].reshape(height+pad*2, sride) for i in range(256//sride)])[:,:254]
    wave_image *= window
    spectrum_image = np.fft.fft(wave_image, axis=1)
    input_image = np.abs(spectrum_image[:,:128].reshape(1, height+pad*2, 128), dtype=np.float32)

    np.clip(input_image, 1000, None, out=input_image)
    np.log(input_image, out=input_image)
    input_image += bias
    input_image /= scale

    if np.max(input_image) > 0.95:
        print('input image max bigger than 0.95', np.max(input_image))
    if np.min(input_image) < 0.05:
        print('input image min smaller than 0.05', np.min(input_image))

    return input_image 
Example 8
Project: deep-learning-note   Author: wdxtub   File: layers.py    License: MIT License 6 votes vote down vote up
def forward(self, x):
        N, C, H, W = x.shape
        out_h = int(1 + (H - self.pool_h) / self.stride)
        out_w = int(1 + (W - self.pool_w) / self.stride)

        col = im2col(x, self.pool_h, self.pool_w, self.stride, self.pad)
        col = col.reshape(-1, self.pool_h * self.pool_w)

        arg_max = np.argmax(col, axis=1)
        out = np.max(col, axis=1)
        out = out.reshape(N, out_h, out_w, C).transpose(0, 3, 1, 2)

        self.x = x
        self.arg_max = arg_max

        return out 
Example 9
Project: Sound-Recognition-Tutorial   Author: JasonZhang156   File: feature_extraction.py    License: Apache License 2.0 6 votes vote down vote up
def extract_logmel(y, sr, size=3):
    """
    extract log mel spectrogram feature
    :param y: the input signal (audio time series)
    :param sr: sample rate of 'y'
    :param size: the length (seconds) of random crop from original audio, default as 3 seconds
    :return: log-mel spectrogram feature
    """
    # normalization
    y = y.astype(np.float32)
    normalization_factor = 1 / np.max(np.abs(y))
    y = y * normalization_factor

    # random crop
    start = random.randint(0, len(y) - size * sr)
    y = y[start: start + size * sr]

    # extract log mel spectrogram #####
    melspectrogram = librosa.feature.melspectrogram(y=y, sr=sr, n_fft=2048, hop_length=1024, n_mels=60)
    logmelspec = librosa.power_to_db(melspectrogram)

    return logmelspec 
Example 10
Project: Sound-Recognition-Tutorial   Author: JasonZhang156   File: feature_extraction.py    License: Apache License 2.0 6 votes vote down vote up
def extract_mfcc(y, sr, size=3):
    """
    extract MFCC feature
    :param y: np.ndarray [shape=(n,)], real-valued the input signal (audio time series)
    :param sr: sample rate of 'y'
    :param size: the length (seconds) of random crop from original audio, default as 3 seconds
    :return: MFCC feature
    """
    # normalization
    y = y.astype(np.float32)
    normalization_factor = 1 / np.max(np.abs(y))
    y = y * normalization_factor

    # random crop
    start = random.randint(0, len(y) - size * sr)
    y = y[start: start + size * sr]

    # extract log mel spectrogram #####
    melspectrogram = librosa.feature.melspectrogram(y=y, sr=sr, n_fft=2048, hop_length=1024)
    mfcc = librosa.feature.mfcc(S=librosa.power_to_db(melspectrogram), n_mfcc=20)
    mfcc_delta = librosa.feature.delta(mfcc)
    mfcc_delta_delta = librosa.feature.delta(mfcc_delta)
    mfcc_comb = np.concatenate([mfcc, mfcc_delta, mfcc_delta_delta], axis=0)

    return mfcc_comb 
Example 11
Project: neuropythy   Author: noahbenson   File: core.py    License: GNU Affero General Public License v3.0 6 votes vote down vote up
def cortex_cmap_plot_2D(the_map, zs, cmap, vmin=None, vmax=None, axes=None, triangulation=None):
    '''
    cortex_cmap_plot_2D(map, zs, cmap, axes) plots the given cortical map values zs on the given
      axes using the given given color map and yields the resulting polygon collection object.
    cortex_cmap_plot_2D(map, zs, cmap) uses matplotlib.pyplot.gca() for the axes.

    The following options may be passed:
      * triangulation (None) may specify the triangularion object for the mesh if it has already
        been created; otherwise it is generated fresh.
      * axes (None) specify the axes on which to plot; if None, then matplotlib.pyplot.gca() is
        used. If Ellipsis, then a tuple (triangulation, z, cmap) is returned; to recreate the plot,
        one would call:
          axes.tripcolor(triangulation, z, cmap, shading='gouraud', vmin=vmin, vmax=vmax)
      * vmin (default: None) specifies the minimum value for scaling the property when one is passed
        as the color option. None means to use the min value of the property.
      * vmax (default: None) specifies the maximum value for scaling the property when one is passed
        as the color option. None means to use the max value of the property.
    '''
    if triangulation is None:
        triangulation = matplotlib.tri.Triangulation(the_map.coordinates[0], the_map.coordinates[1],
                                                     triangles=the_map.tess.indexed_faces.T)
    if axes is Ellipsis: return (triangulation, zs, cmap)
    return axes.tripcolor(triangulation, zs, cmap=cmap, shading='gouraud', vmin=vmin, vmax=vmax) 
Example 12
Project: Black-Box-Audio   Author: rtaori   File: run_audio_attack.py    License: MIT License 5 votes vote down vote up
def db(audio):
    if len(audio.shape) > 1:
        maxx = np.max(np.abs(audio), axis=1)
        return 20 * np.log10(maxx) if np.any(maxx != 0) else np.array([0])
    maxx = np.max(np.abs(audio))
    return 20 * np.log10(maxx) if maxx != 0 else np.array([0]) 
Example 13
Project: Black-Box-Audio   Author: rtaori   File: run_audio_attack.py    License: MIT License 5 votes vote down vote up
def get_new_pop(elite_pop, elite_pop_scores, pop_size):
    scores_logits = np.exp(elite_pop_scores - elite_pop_scores.max()) 
    elite_pop_probs = scores_logits / scores_logits.sum()
    cand1 = elite_pop[np.random.choice(len(elite_pop), p=elite_pop_probs, size=pop_size)]
    cand2 = elite_pop[np.random.choice(len(elite_pop), p=elite_pop_probs, size=pop_size)]
    mask = np.random.rand(pop_size, elite_pop.shape[1]) < 0.5 
    next_pop = mask * cand1 + (1 - mask) * cand2
    return next_pop 
Example 14
Project: libTLDA   Author: wmkouw   File: rba.py    License: MIT License 5 votes vote down vote up
def posterior(self, psi):
        """
        Class-posterior estimation.

        Parameters
        ----------
        psi : array
            weighted data-classifier output (N samples by K classes)

        Returns
        -------
        pyx : array
            class-posterior estimation (N samples by K classes)

        """
        # Data shape
        N, K = psi.shape

        # Preallocate array
        pyx = np.zeros((N, K))

        # Subtract maximum value for numerical stability
        psi = (psi.T - np.max(psi, axis=1).T).T

        # Loop over classes
        for k in range(K):

            # Estimate posterior p^(Y=y | x_i)
            pyx[:, k] = np.exp(psi[:, k]) / np.sum(np.exp(psi), axis=1)

        return pyx 
Example 15
Project: libTLDA   Author: wmkouw   File: rba.py    License: MIT License 5 votes vote down vote up
def predict(self, Z):
        """
        Make predictions on new dataset.

        Parameters
        ----------
        Z : array
            new data set (M samples by D features)

        Returns
        -------
        preds : array
            label predictions (M samples by 1)

        """
        # Data shape
        M, D = Z.shape

        # If classifier is trained, check for same dimensionality
        if self.is_trained:
            if not self.train_data_dim == D:
                raise ValueError('''Test data is of different dimensionality
                                 than training data.''')

        # Compute posteriors
        post = self.predict_proba(Z)

        # Predictions through max-posteriors
        preds = np.argmax(post, axis=1)

        # Map predictions back to original labels
        return self.classes[preds] 
Example 16
Project: dkt   Author: mmkhajah   File: dkt.py    License: MIT License 5 votes vote down vote up
def pad_sequences(sequences, maxlen=None, dim=1, dtype='int32',
    padding='pre', truncating='pre', value=0.):
    '''
        Override keras method to allow multiple feature dimensions.

        @dim: input feature dimension (number of features per timestep)
    '''
    lengths = [len(s) for s in sequences]

    nb_samples = len(sequences)
    if maxlen is None:
        maxlen = np.max(lengths)

    x = (np.ones((nb_samples, maxlen, dim)) * value).astype(dtype)
    for idx, s in enumerate(sequences):
        if truncating == 'pre':
            trunc = s[-maxlen:]
        elif truncating == 'post':
            trunc = s[:maxlen]
        else:
            raise ValueError("Truncating type '%s' not understood" % padding)

        if padding == 'post':
            x[idx, :len(trunc)] = trunc
        elif padding == 'pre':
            x[idx, -len(trunc):] = trunc
        else:
            raise ValueError("Padding type '%s' not understood" % padding)
    return x 
Example 17
Project: cat-bbs   Author: aleju   File: plotting.py    License: MIT License 5 votes vote down vote up
def get_max_x(self):
        return max([group.get_max_x() for group in self.line_groups.itervalues()]) 
Example 18
Project: cat-bbs   Author: aleju   File: plotting.py    License: MIT License 5 votes vote down vote up
def get_max_x(self):
        return max([max(line.xs) if len(line.xs) > 0 else 0 for line in self.lines.itervalues()]) 
Example 19
Project: cat-bbs   Author: aleju   File: plotting.py    License: MIT License 5 votes vote down vote up
def __init__(self, titles, increasing, save_to_fp):
        assert len(titles) == len(increasing)
        n_plots = len(titles)
        self.titles = titles
        self.increasing = dict([(title, incr) for title, incr in zip(titles, increasing)])
        self.colors = ["red", "blue", "cyan", "magenta", "orange", "black"]

        self.nb_points_max = 500
        self.save_to_fp = save_to_fp
        self.start_batch_idx = 0
        self.autolimit_y = False
        self.autolimit_y_multiplier = 5

        #self.fig, self.axes = plt.subplots(nrows=2, ncols=2, figsize=(20, 20))
        nrows = max(1, int(math.sqrt(n_plots)))
        ncols = int(math.ceil(n_plots / nrows))
        width = ncols * 10
        height = nrows * 10

        self.fig, self.axes = plt.subplots(nrows=nrows, ncols=ncols, figsize=(width, height))

        if nrows == 1 and ncols == 1:
            self.axes = [self.axes]
        else:
            self.axes = self.axes.flat

        title_to_ax = dict()
        for idx, (title, ax) in enumerate(zip(self.titles, self.axes)):
            title_to_ax[title] = ax
        self.title_to_ax = title_to_ax

        self.fig.tight_layout()
        self.fig.subplots_adjust(left=0.05) 
Example 20
Project: cat-bbs   Author: aleju   File: plotting.py    License: MIT License 5 votes vote down vote up
def _line_to_xy(self, line_x, line_y, limit_y_min=None, limit_y_max=None):
        point_every = max(1, int(len(line_x) / self.nb_points_max))
        points_x = []
        points_y = []
        curr_sum = 0
        counter = 0
        last_idx = len(line_x) - 1
        for i in range(len(line_x)):
            batch_idx = line_x[i]
            if batch_idx > self.start_batch_idx:
                curr_sum += line_y[i]
                counter += 1
                if counter >= point_every or i == last_idx:
                    points_x.append(batch_idx)
                    y = curr_sum / counter
                    if limit_y_min is not None and limit_y_max is not None:
                        y = np.clip(y, limit_y_min, limit_y_max)
                    elif limit_y_min is not None:
                        y = max(y, limit_y_min)
                    elif limit_y_max is not None:
                        y = min(y, limit_y_max)
                    points_y.append(y)
                    counter = 0
                    curr_sum = 0

        return points_x, points_y 
Example 21
Project: aospy   Author: spencerahill   File: vertcoord.py    License: Apache License 2.0 5 votes vote down vote up
def to_pascal(arr, is_dp=False):
    """Force data with units either hPa or Pa to be in Pa."""
    threshold = 400 if is_dp else 1200
    if np.max(np.abs(arr)) < threshold:
        warn_msg = "Conversion applied: hPa -> Pa to array: {}".format(arr)
        logging.debug(warn_msg)
        return arr*100.
    return arr 
Example 22
Project: aospy   Author: spencerahill   File: vertcoord.py    License: Apache License 2.0 5 votes vote down vote up
def to_hpa(arr):
    """Convert pressure array from Pa to hPa (if needed)."""
    if np.max(np.abs(arr)) > 1200.:
        warn_msg = "Conversion applied: Pa -> hPa to array: {}".format(arr)
        logging.debug(warn_msg)
        return arr / 100.
    return arr 
Example 23
Project: aospy   Author: spencerahill   File: var.py    License: Apache License 2.0 5 votes vote down vote up
def mask_unphysical(self, data):
        """Mask data array where values are outside physically valid range."""
        if not self.valid_range:
            return data
        else:
            return np.ma.masked_outside(data, np.min(self.valid_range),
                                        np.max(self.valid_range)) 
Example 24
Project: RF-Monitor   Author: EarToEarOak   File: gui.py    License: GNU General Public License v2.0 5 votes vote down vote up
def __on_scan_data(self, event):
        levels = numpy.log10(event['l'])
        levels *= 10
        self._levels = levels

        noise = numpy.percentile(levels,
                                 self._toolbar.get_dynamic_percentile())

        updated = False
        for monitor in self._monitors:
            freq = monitor.get_frequency()
            if monitor.get_enabled():
                monitor.set_noise(noise)
                index = numpy.where(freq == event['f'])[0]
                signal = monitor.set_level(levels[index][0],
                                           event['timestamp'],
                                           self._location)
                if signal is not None:
                    updated = True
                    if signal.end is not None:
                        recording = format_recording(freq, signal)
                        if self._settings.get_push_enable():
                            self._push.send(self._settings.get_push_uri(),
                                            recording)
                        if self._server is not None:
                            self._server.send(recording)

        if updated:
            if self._isSaved:
                self._isSaved = False
                self.__set_title()
                self.__set_timeline()

        self.__set_spectrum(noise)
        self._rssi.set_noise(numpy.mean(levels))
        self._rssi.set_level(numpy.max(levels)) 
Example 25
def im_list_to_blob(ims):
  """Convert a list of images into a network input.

  Assumes images are already prepared (means subtracted, BGR order, ...).
  """
  max_shape = np.array([im.shape for im in ims]).max(axis=0)
  num_images = len(ims)
  blob = np.zeros((num_images, max_shape[0], max_shape[1], 3),
                  dtype=np.float32)
  for i in range(num_images):
    im = ims[i]
    blob[i, 0:im.shape[0], 0:im.shape[1], :] = im

  return blob 
Example 26
def prep_im_for_blob(im, pixel_means, target_size, max_size):
  """Mean subtract and scale an image for use in a blob."""
  im = im.astype(np.float32, copy=False)
  im -= pixel_means
  im_shape = im.shape
  im_size_min = np.min(im_shape[0:2])
  im_size_max = np.max(im_shape[0:2])
  im_scale = float(target_size) / float(im_size_min)
  # Prevent the biggest axis from being more than MAX_SIZE
  if np.round(im_scale * im_size_max) > max_size:
    im_scale = float(max_size) / float(im_size_max)
  im = cv2.resize(im, None, None, fx=im_scale, fy=im_scale,
                  interpolation=cv2.INTER_LINEAR)

  return im, im_scale 
Example 27
def _get_image_blob(im):
  """Converts an image into a network input.
  Arguments:
    im (ndarray): a color image in BGR order
  Returns:
    blob (ndarray): a data blob holding an image pyramid
    im_scale_factors (list): list of image scales (relative to im) used
      in the image pyramid
  """
  im_orig = im.astype(np.float32, copy=True)
  im_orig -= cfg.PIXEL_MEANS

  im_shape = im_orig.shape
  im_size_min = np.min(im_shape[0:2])
  im_size_max = np.max(im_shape[0:2])

  processed_ims = []
  im_scale_factors = []

  for target_size in cfg.TEST.SCALES:
    im_scale = float(target_size) / float(im_size_min)
    # Prevent the biggest axis from being more than MAX_SIZE
    if np.round(im_scale * im_size_max) > cfg.TEST.MAX_SIZE:
      im_scale = float(cfg.TEST.MAX_SIZE) / float(im_size_max)
    im = cv2.resize(im_orig, None, None, fx=im_scale, fy=im_scale,
            interpolation=cv2.INTER_LINEAR)
    im_scale_factors.append(im_scale)
    processed_ims.append(im)

  # Create a blob to hold the input images
  blob = im_list_to_blob(processed_ims)

  return blob, np.array(im_scale_factors) 
Example 28
def _get_image_blob(im):
  """Converts an image into a network input.
  Arguments:
    im (ndarray): a color image in BGR order
  Returns:
    blob (ndarray): a data blob holding an image pyramid
    im_scale_factors (list): list of image scales (relative to im) used
      in the image pyramid
  """
  im_orig = im.astype(np.float32, copy=True)
  im_orig -= cfg.PIXEL_MEANS

  im_shape = im_orig.shape
  im_size_min = np.min(im_shape[0:2])
  im_size_max = np.max(im_shape[0:2])

  processed_ims = []
  im_scale_factors = []

  for target_size in cfg.TEST.SCALES:
    im_scale = float(target_size) / float(im_size_min)
    # Prevent the biggest axis from being more than MAX_SIZE
    if np.round(im_scale * im_size_max) > cfg.TEST.MAX_SIZE:
      im_scale = float(cfg.TEST.MAX_SIZE) / float(im_size_max)
    im = cv2.resize(im_orig, None, None, fx=im_scale, fy=im_scale,
            interpolation=cv2.INTER_LINEAR)
    im_scale_factors.append(im_scale)
    processed_ims.append(im)

  # Create a blob to hold the input images
  blob = im_list_to_blob(processed_ims)

  return blob, np.array(im_scale_factors) 
Example 29
def voc_ap(rec, prec, use_07_metric=False):
  """ ap = voc_ap(rec, prec, [use_07_metric])
  Compute VOC AP given precision and recall.
  If use_07_metric is true, uses the
  VOC 07 11 point method (default:False).
  """
  if use_07_metric:
    # 11 point metric
    ap = 0.
    for t in np.arange(0., 1.1, 0.1):
      if np.sum(rec >= t) == 0:
        p = 0
      else:
        p = np.max(prec[rec >= t])
      ap = ap + p / 11.
  else:
    # correct AP calculation
    # first append sentinel values at the end
    mrec = np.concatenate(([0.], rec, [1.]))
    mpre = np.concatenate(([0.], prec, [0.]))

    # compute the precision envelope
    for i in range(mpre.size - 1, 0, -1):
      mpre[i - 1] = np.maximum(mpre[i - 1], mpre[i])

    # to calculate area under PR curve, look for points
    # where X axis (recall) changes value
    i = np.where(mrec[1:] != mrec[:-1])[0]

    # and sum (\Delta recall) * prec
    ap = np.sum((mrec[i + 1] - mrec[i]) * mpre[i + 1])
  return ap 
Example 30
def _print_detection_eval_metrics(self, coco_eval):
    IoU_lo_thresh = 0.5
    IoU_hi_thresh = 0.95

    def _get_thr_ind(coco_eval, thr):
      ind = np.where((coco_eval.params.iouThrs > thr - 1e-5) &
                     (coco_eval.params.iouThrs < thr + 1e-5))[0][0]
      iou_thr = coco_eval.params.iouThrs[ind]
      assert np.isclose(iou_thr, thr)
      return ind

    ind_lo = _get_thr_ind(coco_eval, IoU_lo_thresh)
    ind_hi = _get_thr_ind(coco_eval, IoU_hi_thresh)
    # precision has dims (iou, recall, cls, area range, max dets)
    # area range index 0: all area ranges
    # max dets index 2: 100 per image
    precision = \
      coco_eval.eval['precision'][ind_lo:(ind_hi + 1), :, :, 0, 2]
    ap_default = np.mean(precision[precision > -1])
    print(('~~~~ Mean and per-category AP @ IoU=[{:.2f},{:.2f}] '
           '~~~~').format(IoU_lo_thresh, IoU_hi_thresh))
    print('{:.1f}'.format(100 * ap_default))
    for cls_ind, cls in enumerate(self.classes):
      if cls == '__background__':
        continue
      # minus 1 because of __background__
      precision = coco_eval.eval['precision'][ind_lo:(ind_hi + 1), :, cls_ind - 1, 0, 2]
      ap = np.mean(precision[precision > -1])
      print('{:.1f}'.format(100 * ap))

    print('~~~~ Summary metrics ~~~~')
    coco_eval.summarize()