python类resize()的实例源码

def initwithsize(self, curshape, dim):
        # DIM-dependent initialization
        if self.dim != dim:
            if self.zerox:
                self.xopt = zeros(dim)
            else:
                self.xopt = compute_xopt(self.rseed, dim)
            if hasattr(self, 'param') and self.param: # not self.param is None
                tmp = self.param
            else:
                tmp = self.condition
            self.scales = tmp ** linspace(0, 1, dim)

        # DIM- and POPSI-dependent initialisations of DIM*POPSI matrices
        if self.lastshape != curshape:
            self.dim = dim
            self.lastshape = curshape
            self.arrxopt = resize(self.xopt, curshape)

def initwithsize(self, curshape, dim):
        # DIM-dependent initialisation
        if self.dim != dim:
            if self.zerox:
                self.xopt = zeros(dim)
            else:
                self.xopt = compute_xopt(self.rseed, dim)
            self.scales = (self.condition ** .5) ** linspace(0, 1, dim)

        # DIM- and POPSI-dependent initialisations of DIM*POPSI matrices
        if self.lastshape != curshape:
            self.dim = dim
            self.lastshape = curshape
            self.arrxopt = resize(self.xopt, curshape)
            self.arrscales = resize(self.scales, curshape)
            self.arrexpo = resize(self.beta * linspace(0, 1, dim), curshape)

def initwithsize(self, curshape, dim):
        # DIM-dependent initialization
        if self.dim != dim:
            if self.zerox:
                self.xopt = zeros(dim)
            else:
                self.xopt = compute_xopt(self.rseed, dim)
            self.xopt[:min(dim, self.maxindex):2] = abs(self.xopt[:min(dim, self.maxindex):2])
            self.scales = (self.condition ** .5) ** linspace(0, 1, dim)

        # DIM- and POPSI-dependent initialisations of DIM*POPSI matrices
        if self.lastshape != curshape:
            self.dim = dim
            self.lastshape = curshape
            self.arrxopt = resize(self.xopt, curshape)
            self.arrscales = resize(self.scales, curshape)

def initwithsize(self, curshape, dim):
        # DIM-dependent initialization
        if self.dim != dim:
            if self.zerox:
                self.xopt = zeros(dim)
            else:
                self.xopt = compute_xopt(self.rseed, dim)
            self.rotation = compute_rotation(self.rseed + 1e6, dim)
            self.scales = self.condition ** linspace(0, 1, dim)
            self.linearTF = dot(compute_rotation(self.rseed, dim),
                                diag(((self.condition / 10.)**.5) ** linspace(0, 1, dim)))

        # DIM- and POPSI-dependent initialisations of DIM*POPSI matrices
        if self.lastshape != curshape:
            self.dim = dim
            self.lastshape = curshape
            self.arrxopt = resize(self.xopt, curshape)

def initwithsize(self, curshape, dim):
        # DIM-dependent initialization
        if self.dim != dim:
            if self.zerox:
                self.xopt = zeros(dim)
            else:
                self.xopt = compute_xopt(self.rseed, dim)
            scale = max(1, dim ** .5 / 8.) # nota: different from scales in F8
            self.linearTF = scale * compute_rotation(self.rseed, dim)
            self.xopt = np.hstack(dot(.5 * np.ones((1, dim)), self.linearTF.T)) / scale ** 2

        # DIM- and POPSI-dependent initialisations of DIM*POPSI matrices
        if self.lastshape != curshape:
            self.dim = dim
            self.lastshape = curshape
            self.arrxopt = resize(self.xopt, curshape)

def initwithsize(self, curshape, dim):
        # DIM-dependent initialization
        if self.dim != dim:
            if self.zerox:
                self.xopt = zeros(dim)
            else:
                self.xopt = compute_xopt(self.rseed, dim)
            self.rotation = compute_rotation(self.rseed + 1e6, dim)
            self.scales = (self.condition ** .5) ** linspace(0, 1, dim)
            self.linearTF = dot(compute_rotation(self.rseed, dim), diag(self.scales))
            self.linearTF = dot(self.linearTF, self.rotation)

        # DIM- and POPSI-dependent initialisations of DIM*POPSI matrices
        if self.lastshape != curshape:
            self.dim = dim
            self.lastshape = curshape
            self.arrxopt = resize(self.xopt, curshape)

def initwithsize(self, curshape, dim):
        # DIM-dependent initialization
        if self.dim != dim:
            if self.zerox:
                self.xopt = zeros(dim)
            else:
                self.xopt = compute_xopt(self.rseed, dim)
            self.rotation = compute_rotation(self.rseed + 1e6, dim)
            self.scales = (self.condition ** .5) ** linspace(0, 1, dim)
            self.linearTF = dot(compute_rotation(self.rseed, dim), diag(self.scales))
            # decouple scaling from function definition
            self.linearTF = dot(self.linearTF, self.rotation)

        # DIM- and POPSI-dependent initialisations of DIM*POPSI matrices
        if self.lastshape != curshape:
            self.dim = dim
            self.lastshape = curshape
            self.arrxopt = resize(self.xopt, curshape)
            self.arrexpo = resize(self.beta * linspace(0, 1, dim), curshape)

def initwithsize(self, curshape, dim):
        # DIM-dependent initialization
        if self.dim != dim:
            if self.zerox:
                self.xopt = zeros(dim)
            else:
                self.xopt = compute_xopt(self.rseed, dim)
            self.rotation = compute_rotation(self.rseed + 1e6, dim)
            self.scales = (1. / self.condition ** .5) ** linspace(0, 1, dim) # CAVE?
            self.linearTF = dot(compute_rotation(self.rseed, dim), diag(self.scales))
            # decouple scaling from function definition
            self.linearTF = dot(self.linearTF, self.rotation)
            K = np.arange(0, 12)
            self.aK = np.reshape(0.5 ** K, (1, 12))
            self.bK = np.reshape(3. ** K, (1, 12))
            self.f0 = np.sum(self.aK * np.cos(2 * np.pi * self.bK * 0.5)) # optimal value

        # DIM- and POPSI-dependent initialisations of DIM*POPSI matrices
        if self.lastshape != curshape:
            self.dim = dim
            self.lastshape = curshape
            self.arrxopt = resize(self.xopt, curshape)

def initwithsize(self, curshape, dim):
        # DIM-dependent initialization
        if self.dim != dim:
            if self.zerox:
                self.xopt = zeros(dim)
            else:
                self.xopt = compute_xopt(self.rseed, dim)
            self.rotation = compute_rotation(self.rseed + 1e6, dim)
            self.scales = (self.condition ** .5) ** linspace(0, 1 , dim)
            self.linearTF = dot(compute_rotation(self.rseed, dim), diag(self.scales))

        # DIM- and POPSI-dependent initialisations of DIM*POPSI matrices
        if self.lastshape != curshape:
            self.dim = dim
            self.lastshape = curshape
            self.arrxopt = resize(self.xopt, curshape)
            self.arrexpo = resize(self.beta * linspace(0, 1, dim), curshape)

def initwithsize(self, curshape, dim):
        # DIM-dependent initialization
        if self.dim != dim:
            if self.zerox:
                self.xopt = zeros(dim)
            else:
                self.xopt = 0.5 * sign(unif(dim, self.rseed) - 0.5) * 4.2096874633
            self.scales = (self.condition ** .5) ** np.linspace(0, 1, dim)

        # DIM- and POPSI-dependent initialisations of DIM*POPSI matrices
        if self.lastshape != curshape:
            self.dim = dim
            self.lastshape = curshape
            self.arrxopt = resize(2 * np.abs(self.xopt), curshape)
            self.arrscales = resize(self.scales, curshape)
            self.arrsigns = resize(sign(self.xopt), curshape)

def initwithsize(self, curshape, dim):
        # DIM-dependent initialization
        if self.dim != dim:
            if self.zerox:
                self.xopt = zeros(dim)
            else:
                self.xopt = compute_xopt(self.rseed, dim)
            self.rotation = compute_rotation(self.rseed + 1e6, dim)
            self.scales = (self.condition ** .5) ** linspace(0, 1, dim)
            self.linearTF = dot(compute_rotation(self.rseed, dim), diag(self.scales))
            # decouple scaling from function definition
            self.linearTF = dot(self.linearTF, self.rotation)

        # DIM- and POPSI-dependent initialisations of DIM*POPSI matrices
        if self.lastshape != curshape:
            self.dim = dim
            self.lastshape = curshape
            self.arrxopt = resize(self.xopt, curshape)

def initwithsize(self, curshape, dim):
        # DIM-dependent initialization
        if self.dim != dim:
            if self.zerox:
                self.xopt = zeros(dim)
            else:
                self.xopt = .5 * self._mu1 * sign(gauss(dim, self.rseed))
            self.rotation = compute_rotation(self.rseed + 1e6, dim)
            self.scales = (self.condition ** .5) ** linspace(0, 1, dim)
            self.linearTF = dot(compute_rotation(self.rseed, dim), diag(self.scales))
            # decouple scaling from function definition
            self.linearTF = dot(self.linearTF, self.rotation)

        # DIM- and POPSI-dependent initialisations of DIM*POPSI matrices
        if self.lastshape != curshape:
            self.dim = dim
            self.lastshape = curshape
            # self.arrxopt = resize(self.xopt, curshape)
            self.arrscales = resize(2. * sign(self.xopt), curshape) # makes up for xopt

def initwithsize(self, curshape, dim):
        # DIM-dependent initialization
        if self.dim != dim:
            if self.zerox:
                self.xopt = zeros(dim)
            else:
                self.xopt = compute_xopt(self.rseed, dim)

        # DIM- and POPSI-dependent initialisations of DIM*POPSI matrices
        if self.lastshape != curshape:
            self.dim = dim
            self.lastshape = curshape
            self.arrxopt = resize(self.xopt, curshape)

        self.linearTf = None
        self.rotation = None

def __call__(self, ts=None, constrains=False):

        if ts is None:
            if constrains:
                if self.J.constrains.size:
                    A = np.resize(self, (self.shape[0] + self.J.constrains.shape[0], self.shape[1]))
                    A[-self.J.constrains.shape[0] - 1:-1,self.L.params:self.L.params + self.J.params] = self.J.constrains
                    return A

                else:
                    return self

            else:
                return self

        else:
            Al = self.L.GetDesignTs(ts)
            Aj = self.J.GetDesignTs(ts)
            Ap = self.P.GetDesignTs(ts)

            As = np.column_stack((Al, Aj)) if Aj.size else Al
            As = np.column_stack((As, Ap)) if Ap.size else As

            return As

def apply_motion_blur(image, kernel_size, strength = 1.0):
    """Applies motion blur on image 
    """
    # generating the kernel
    kernel_motion_blur = np.zeros((kernel_size, kernel_size))
    kernel_motion_blur[int((kernel_size - 1) / 2), :] = np.ones(kernel_size)
    kernel_motion_blur = kernel_motion_blur / kernel_size

    rotation_kernel = np.random.uniform(0, 360)
    kernel_motion_blur = rotate(kernel_motion_blur, rotation_kernel)
    #cv2.imshow("kernel", cv2.resize(kernel_motion_blur, (100, 100)))
    kernel_motion_blur *= strength

    # applying the kernel to the input image
    output = cv2.filter2D(image, -1, kernel_motion_blur)
    return output

def train(self, tran, selected):
        self.targetNet.blobs['frames'].data[...] \
            = tran.frames[selected + 1].copy()
        netOut = self.targetNet.forward()

        target = np.tile(tran.reward[selected]
                         + pms.discount
                         * tran.n_last[selected]
                         * np.resize(netOut['value_q'].max(1),
                                     (pms.batchSize, 1)),
                         (pms.actionSize,)
                         ) * tran.action[selected]

        self.solver.net.blobs['target'].data[...] = target
        self.solver.net.blobs['frames'].data[...] = tran.frames[selected].copy()
        self.solver.net.blobs['filter'].data[...] = tran.action[selected].copy()
        self.solver.step(1)

def read_data(dataFile,size,Transpose=False,resize=False):
    f             =      h5py.File(dataFile,'r')
    result_data   =      np.zeros(size)
    result_label  =      np.zeros(size)
    if Transpose == True:
        data      =      np.transpose(np.array(f['data']),(3,2,1,0))
        label     =      np.transpose(np.array(f['label']),(3,2,1,0))
    else:
        data      =      np.array(f['data'])
        label     =      np.array(f['label'])
    [d1,d2,d3,d4] =      data.shape
    if resize == True:
        for p in range(d1):
            for d in range(d2):
                result_data[p,d,:,:]     =      np.resize(data[p,d,:,:],(size[2],size[3]))
                result_label[p,d,:,:]    =      np.resize(label[p,d,:,:],(size[2],size[3]))
        data      =      result_data
        label     =      result_label
    return data, label

def run_test_r2c_dtype(self, shape, axes, dtype=np.float32, scale=1., misalign=0):
        known_data = np.random.normal(size=shape).astype(np.float32)
        known_data = (known_data * scale).astype(dtype)

        # Force misaligned data
        padded_shape = shape[:-1] + (shape[-1] + misalign,)
        known_data = np.resize(known_data, padded_shape)
        idata = bf.ndarray(known_data, space='cuda')
        known_data = known_data[..., misalign:]
        idata = idata[..., misalign:]

        oshape = list(shape)
        oshape[axes[-1]] = shape[axes[-1]] // 2 + 1
        odata = bf.ndarray(shape=oshape, dtype='cf32', space='cuda')
        fft = Fft()
        fft.init(idata, odata, axes=axes)
        fft.execute(idata, odata)
        known_result = gold_rfftn(known_data.astype(np.float32) / scale, axes=axes)
        compare(odata.copy('system'), known_result)

def resize(vec, size):
   """
   Resizes a vector such that it has the right size. This is done by repeating the vector
   in each dimension until the required size is reached. Note an error is thrown if 'size'
   is not a multiple of the size of vec.

   vec      A 1D or 2D numpy array
   size     A list of dimension sizes (e.g. [2,3])
   """
   if not isinstance(vec, (np.ndarray)):
      vec_resized = vec * np.ones(size)
   elif vec.shape[0] == size[0] and len(vec.shape) == 1:
      vec_resized = np.reshape(np.repeat(vec, size[1]), size)
   elif vec.shape[0] == 1 and len(vec.shape) == 1:
      vec_resized = vec*np.ones(size)
   else:
      # Check that the output dims are multiples of input dims
      assert(size[0] % vec.shape[0] == 0)
      assert(size[1] % vec.shape[1] == 0)
      vec_resized = np.tile(vec, (size[0] // vec.shape[0], size[1] // vec.shape[1]))
   return vec_resized

def _read_particle_coords(self, chunks, ptf):
        # This will read chunks and yield the results.
        chunks = list(chunks)
        data_files = set([])
        for chunk in chunks:
            for obj in chunk.objs:
                data_files.update(obj.data_files)
        for data_file in sorted(data_files):
            with h5py.File(data_file.filename, "r") as f:
                for ptype, field_list in sorted(ptf.items()):
                    pcount = data_file.total_particles[ptype]
                    coords = f[ptype]["%sPos" % ptype].value.astype("float64")
                    coords = np.resize(coords, (pcount, 3))
                    x = coords[:, 0]
                    y = coords[:, 1]
                    z = coords[:, 2]
                    yield ptype, (x, y, z)

def _read_particle_coords(self, chunks, ptf):
        # This will read chunks and yield the results.
        chunks = list(chunks)
        data_files = set([])
        for chunk in chunks:
            for obj in chunk.objs:
                data_files.update(obj.data_files)
        for data_file in sorted(data_files, key=lambda f: f.filename):
            with h5py.File(data_file.filename, "r") as f:
                for ptype, field_list in sorted(ptf.items()):
                    pcount = data_file.total_particles[ptype]
                    coords = f[ptype]["CenterOfMass"].value.astype("float64")
                    coords = np.resize(coords, (pcount, 3))
                    x = coords[:, 0]
                    y = coords[:, 1]
                    z = coords[:, 2]
                    yield ptype, (x, y, z)

def get_cloud_colors(data):
        """ Get colors from the cloud """
        dtype = np.dtype('float32')
        dtype = dtype.newbyteorder('<')
        buf = np.frombuffer(data.data, dtype)
        buf = np.resize(buf, (data.width * data.height, 8))
        buf = np.compress([True, True, True, False, True, False, False,
                           False], buf, axis=1)
        cond = np.isnan(buf).any(1)
        buf[cond] = [0.0, 0.0, 0.0, 0.0]
        buf = np.compress([False, False, False, True], buf, axis=1)
        nstr = buf.tostring()
        rgb = np.fromstring(nstr, dtype='uint8')
        rgb.resize((data.height * data.width), 4)
        rgb = np.compress([True, True, True, False], rgb, axis=1)
        return np.array([rgb])

def plot_RF(rf, sample_shape):
    norm = matplotlib.colors.Normalize()
    norm.autoscale(rf)
    rf = np.resize(rf, np.prod(sample_shape)).reshape(sample_shape)
    norm_zero = min(max(norm(0.0), 0.0+1e-6), 1.0-1e-6)
    cdict = {
             'red'  :  ((0., 0., 0.), (norm_zero, 0.5, 0.5), (1., 1., 1.)),
             'green':  ((0., 0., 0.), (norm_zero, 0.5, 0.5), (1., 1., 1.)),
             'blue' :  ((0., 0., 0.), (norm_zero, 0.5, 0.5), (1., 1., 1.))
             }
    #generate the colormap with 1024 interpolated values
    my_cmap = matplotlib.colors.LinearSegmentedColormap('my_colormap', cdict, 1024)                
    plt.imshow(rf, interpolation='nearest', origin='upper', cmap=my_cmap)   
    ax = plt.gca()
    ax.xaxis.set_visible(False)
    ax.yaxis.set_visible(False)

def plot_examples(nade, dataset, shape, name, rows=5, cols=10):    
    #Show some samples
    images = list()
    for row in xrange(rows):                     
        for i in xrange(cols):
            nade.setup_n_orderings(n=1)
            sample = dataset.sample_data(1)[0].T
            dens = nade.logdensity(sample)
            images.append((sample, dens))
    images.sort(key=lambda x: -x[1])

    plt.figure(figsize=(0.5*cols,0.5*rows), dpi=100)
    plt.gray()            
    for row in xrange(rows):                     
        for col in xrange(cols):
            i = row*cols+col
            sample, dens = images[i]
            plt.subplot(rows, cols, i+1)
            plot_sample(np.resize(sample, np.prod(shape)).reshape(shape), shape, origin="upper")
    plt.subplots_adjust(left=0.01, right=0.99, top=0.99, bottom=0.01, hspace=0.04, wspace=0.04)
    type_1_font()
    plt.savefig(os.path.join(DESTINATION_PATH, name))

def plot_samples(nade, shape, name, rows=5, cols=10):    
    #Show some samples
    images = list()
    for row in xrange(rows):                     
        for i in xrange(cols):
            nade.setup_n_orderings(n=1)
            sample = nade.sample(1)[:,0]
            dens = nade.logdensity(sample[:, np.newaxis])
            images.append((sample, dens))
    images.sort(key=lambda x: -x[1])

    plt.figure(figsize=(0.5*cols,0.5*rows), dpi=100)
    plt.gray()            
    for row in xrange(rows):                     
        for col in xrange(cols):
            i = row*cols+col
            sample, dens = images[i]
            plt.subplot(rows, cols, i+1)
            plot_sample(np.resize(sample, np.prod(shape)).reshape(shape), shape, origin="upper")
    plt.subplots_adjust(left=0.01, right=0.99, top=0.99, bottom=0.01, hspace=0.04, wspace=0.04)
    type_1_font()
    plt.savefig(os.path.join(DESTINATION_PATH, name))                
    #plt.show()

def _create_batches(self, X, batch_size, shuffle_data=False):
        """
        Create batches out of a sequence of data.

        This function will append zeros to the end of your data to ensure that
        all batches are even-sized. These are masked out during training.
        """
        if shuffle_data:
            X = shuffle(X)

        if batch_size > X.shape[0]:
            batch_size = X.shape[0]

        max_x = int(np.ceil(X.shape[0] / batch_size))
        # This line first resizes the data to
        X = np.resize(X, (batch_size, max_x, X.shape[1]))
        # Transposes it to (len(X) / batch_size, batch_size, data_dim)

        return X.transpose((1, 0, 2))

def _create_batches(self, X, batch_size, shuffle_data=True):
        """
        Create batches out of a sequence of data.

        This function will append zeros to the end of your data to ensure that
        all batches are even-sized. These are masked out during training.
        """
        if shuffle_data:
            X = shuffle(X)

        if batch_size > X.shape[0]:
            batch_size = X.shape[0]

        max_x = int(np.ceil(X.shape[0] / batch_size))
        X = np.resize(X, (max_x, batch_size, X.shape[-1]))

        return X

def predict():
    logger.info('/predict, hostname: ' + str(socket.gethostname()))

    if 'image' not in request.files:
        logger.info('Missing image parameter')
        return Response('Missing image parameter', 400)

    # Write image to disk
    with open('request.png', 'wb') as f:
        f.write(request.files['image'].read())

    img = cv2.imread('request.png', 0)
    img = np.resize(img, (28, 28, 1))

    ''' Return value will be None if model not running on host '''
    prediction = mnist_client.predict(np.array([img]))

    logger.info('Prediction of length: ' + str(len(prediction)))

    ''' Convert the dict to json and return response '''
    return jsonify(
        prediction=prediction,
        prediction_length=len(prediction),
        hostname=str(socket.gethostname())
    )

def predict():
    logger.info('/predict, hostname: ' + str(socket.gethostname()))

    if 'image' not in request.files:
        logger.info('Missing image parameter')
        return Response('Missing image parameter', 400)

    # Write image to disk
    with open('request.png', 'wb') as f:
        f.write(request.files['image'].read())

    img = cv2.imread('request.png', 0)
    img = np.resize(img, (28, 28, 1))
    prediction = mnist_client.predict(np.array([img]))

    logger.info('Prediction of length:' + str(len(prediction)))

    ''' Convert the dict to json and return response '''
    return jsonify(
        prediction=prediction,
        prediction_length=len(prediction),
        hostname=str(socket.gethostname())
    )

def readFlow(fn):
    """ Read .flo file in Middlebury format"""
    # Code adapted from:
    # http://stackoverflow.com/questions/28013200/reading-middlebury-flow-files-with-python-bytes-array-numpy

    # WARNING: this will work on little-endian architectures (eg Intel x86) only!
    with open(fn, 'rb') as f:
        magic = np.fromfile(f, np.float32, count=1)
        if 202021.25 != magic:
            print 'Magic number incorrect. Invalid .flo file'
            return None
        else:
            w = np.fromfile(f, np.int32, count=1)
            h = np.fromfile(f, np.int32, count=1)
            #print 'Reading %d x %d flo file' % (w, h)
            data = np.fromfile(f, np.float32, count=2*w*h)
            # Reshape data into 3D array (columns, rows, bands)
            return np.resize(data, (h, w, 2))