python类title()的实例源码

doscalars.py 文件源码 项目:pysynphot 作者: spacetelescope 项目源码 文件源码 阅读 30 收藏 0 点赞 0 评论 0
def plotdata(obsmode,spectrum,val,odict,sdict,
             instr,fieldname,outdir,outname):
    isetting=P.isinteractive()
    P.ioff()

    P.clf()
    P.plot(obsmode,val,'.')
    P.ylabel('(pysyn-syn)/syn')
    P.xlabel('obsmode')
    P.title("%s: %s"%(instr,fieldname))
    P.savefig(os.path.join(outdir,outname+'_obsmode.ps'))

    P.clf()
    P.plot(spectrum,val,'.')
    P.ylabel('(pysyn-syn)/syn')
    P.xlabel('spectrum')
    P.title("%s: %s"%(instr,fieldname))
    P.savefig(os.path.join(outdir,outname+'_spectrum.ps'))

    matplotlib.interactive(isetting)
diagnostic_plots.py 文件源码 项目:ugali 作者: DarkEnergySurvey 项目源码 文件源码 阅读 24 收藏 0 点赞 0 评论 0
def starPlot(targ_ra, targ_dec, data, iso, g_radius, nbhd):
    """Star bin plot"""

    mag_g = data[mag_g_dred_flag]
    mag_r = data[mag_r_dred_flag]

    filter = star_filter(data)

    iso_filter = (iso.separation(mag_g, mag_r) < 0.1)

    # projection of image
    proj = ugali.utils.projector.Projector(targ_ra, targ_dec)
    x, y = proj.sphereToImage(data[filter & iso_filter]['RA'], data[filter & iso_filter]['DEC'])

    plt.scatter(x, y, edgecolor='none', s=3, c='black')
    plt.xlim(0.2, -0.2)
    plt.ylim(-0.2, 0.2)
    plt.gca().set_aspect('equal')
    plt.xlabel(r'$\Delta \alpha$ (deg)')
    plt.ylabel(r'$\Delta \delta$ (deg)')

    plt.title('Stars')
rbm_vis.py 文件源码 项目:fang 作者: rgrosse 项目源码 文件源码 阅读 18 收藏 0 点赞 0 评论 0
def show_particles(rbm, state, dataset, display=True, figname='PCD particles', figtitle='PCD particles',
                   size=None):
    try:
        fantasy_vis = rbm.vis_expectations(state.h)
    except:
        fantasy_vis = state

    if size is None:
        size = (dataset.num_rows, dataset.num_cols)
    imgs = [fantasy_vis[j, :np.prod(size)].reshape(size).as_numpy_array()
            for j in range(fantasy_vis.shape[0])]
    visual = misc.norm01(misc.pack(imgs))
    if display:
        pylab.figure(figname)
        pylab.matshow(visual, cmap='gray', fignum=False)
        pylab.title(figtitle)
    return visual
diagnostics.py 文件源码 项目:fang 作者: rgrosse 项目源码 文件源码 阅读 30 收藏 0 点赞 0 评论 0
def show_chains(rbm, state, dataset, num_particles=20, num_samples=20, show_every=10, display=True,
                figname='Gibbs chains', figtitle='Gibbs chains'):
    samples = gnp.zeros((num_particles, num_samples, state.v.shape[1]))
    state = state[:num_particles, :, :]

    for i in range(num_samples):
        samples[:, i, :] = rbm.vis_expectations(state.h)

        for j in range(show_every):
            state = rbm.step(state)

    npix = dataset.num_rows * dataset.num_cols
    rows = [vm.hjoin([samples[i, j, :npix].reshape((dataset.num_rows, dataset.num_cols)).as_numpy_array()
                      for j in range(num_samples)],
                     normalize=False)
            for i in range(num_particles)]
    grid = vm.vjoin(rows, normalize=False)

    if display:
        pylab.figure(figname)
        pylab.matshow(grid, cmap='gray', fignum=False)
        pylab.title(figtitle)
        pylab.gcf().canvas.draw()

    return grid
TargetImage.py 文件源码 项目:hco-experiments 作者: zooniverse 项目源码 文件源码 阅读 19 收藏 0 点赞 0 评论 0
def visualiseNormObject(self):
        shape = (2*self.extent, 2*self.extent)
        pylab.ion()
        pylab.clf()
        #pylab.set_cmap("bone")
        pylab.hot()
        pylab.title("image: %s" % self.fitsFile)
        pylab.imshow(np.reshape(self.signPreserveNorm(), shape, order="F"), interpolation="nearest")
        pylab.plot(np.arange(0,2*self.extent), self.extent*np.ones((2*self.extent,)), "r--")
        pylab.plot(self.extent*np.ones((2*self.extent,)), np.arange(0,2*self.extent), "r--")
        pylab.colorbar()
        pylab.ylim(-1, 2*self.extent)
        pylab.xlim(-1, 2*self.extent)
        pylab.xlabel("Pixels")
        pylab.ylabel("Pixels")
        pylab.show()
TargetImage.py 文件源码 项目:hco-experiments 作者: zooniverse 项目源码 文件源码 阅读 26 收藏 0 点赞 0 评论 0
def visualiseNormObject(self):
        shape = (2*self.extent, 2*self.extent)
        pylab.ion()
        pylab.clf()
        #pylab.set_cmap("bone")
        pylab.hot()
        pylab.title("image: %s" % self.fitsFile)
        pylab.imshow(np.reshape(self.signPreserveNorm(), shape, order="F"), interpolation="nearest")
        pylab.plot(np.arange(0,2*self.extent), self.extent*np.ones((2*self.extent,)), "r--")
        pylab.plot(self.extent*np.ones((2*self.extent,)), np.arange(0,2*self.extent), "r--")
        pylab.colorbar()
        pylab.ylim(-1, 2*self.extent)
        pylab.xlim(-1, 2*self.extent)
        pylab.xlabel("Pixels")
        pylab.ylabel("Pixels")
        pylab.show()
active_inference_naoqi.py 文件源码 项目:actinf 作者: x75 项目源码 文件源码 阅读 22 收藏 0 点赞 0 评论 0
def plotstuff():
    X__ = np.load("tm_X.npy")
    S_pred = np.load("tm_S_pred.npy")
    E_pred = np.load("tm_E_pred.npy")
    M = np.load("tm_M.npy")

    pl.ioff()
    pl.suptitle("mode: %s (X: FM input, state pred: FM output)" % ("bluib"))
    pl.subplot(511)
    pl.title("X[goals]")
    pl.plot(X__[10:,0:4], "-x")
    pl.subplot(512)
    pl.title("X[prediction error]")
    pl.plot(X__[10:,4:], "-x")
    pl.subplot(513)
    pl.title("state pred")
    pl.plot(S_pred)
    pl.subplot(514)
    pl.title("error state - goal")
    pl.plot(E_pred)
    pl.subplot(515)
    pl.title("state")
    pl.plot(M)
    pl.show()
active_inference_basic.py 文件源码 项目:actinf 作者: x75 项目源码 文件源码 阅读 23 收藏 0 点赞 0 评论 0
def rh_model_plot(self):
        """prepare and plot model outputs over input variations from sweep"""
        assert hasattr(self, "X_model_sweep")
        assert hasattr(self, "Y_model_sweep")

        print "%s.rh_plot_model sweepsteps = %d" % (self.__class__.__name__, self.X_model_sweep.shape[0])
        print "%s.rh_plot_model environment = %s" % (self.__class__.__name__, self.environment)
        print "%s.rh_plot_model environment proprio dims = %d" % (self.__class__.__name__, self.environment.conf.m_ndims)

        # scatter_data_raw   = np.hstack((self.X_model_sweep[:,1:], self.Y_model_sweep))
        # scatter_data_cols  = ["X%d" % i for i in range(1, self.X_model_sweep.shape[1])]
        # scatter_data_cols += ["Y%d" % i for i in range(self.Y_model_sweep.shape[1])]
        # print "scatter_data_raw", scatter_data_raw.shape
        # # df = pd.DataFrame(scatter_data_raw, columns=["x_%d" % i for i in range(scatter_data_raw.shape[1])])
        # df = pd.DataFrame(scatter_data_raw, columns=scatter_data_cols)

        title = "%s, input/output sweep of model %s at time %d" % (self.mode, self.model, -1)

        # plot_scattermatrix(df)
        # plot_scattermatrix_reduced(df)
        plot_colormeshmatrix_reduced(self.X_model_sweep, self.Y_model_sweep, ymin = -1.0, ymax = 1.0, title = title)

    ################################################################################
active_inference_basic.py 文件源码 项目:actinf 作者: x75 项目源码 文件源码 阅读 19 收藏 0 点赞 0 评论 0
def plot_scattermatrix(df, title = "plot_scattermatrix"):
    """plot a scattermatrix of dataframe df"""
    if df is None:
        print "plot_scattermatrix: no data passed"
        return

    from pandas.tools.plotting import scatter_matrix
    # df = pd.DataFrame(X, columns=['x1_t', 'x2_t', 'x1_tptau', 'x2_tptau', 'u_t'])
    # scatter_data_raw = np.hstack((np.array(Xs), np.array(Ys)))
    # scatter_data_raw = np.hstack((Xs, Ys))
    # print "scatter_data_raw", scatter_data_raw.shape

    pl.ioff()
    # df = pd.DataFrame(scatter_data_raw, columns=["x_%d" % i for i in range(scatter_data_raw.shape[1])])
    sm = scatter_matrix(df, alpha=0.2, figsize=(10, 10), diagonal='hist')
    fig = sm[0,0].get_figure()
    fig.suptitle(title)
    if SAVEPLOTS:
        fig.savefig("fig_%03d_scattermatrix.pdf" % (fig.number), dpi=300)
    fig.show()
    # pl.show()
Fourier.py 文件源码 项目:ArduPi-ECG 作者: ferdavid1 项目源码 文件源码 阅读 27 收藏 0 点赞 0 评论 0
def main():
    data = pd.read_table('../Real_Values.txt').get_values()
    x = [float(d) for d in data]
    test = np.array([669, 592, 664, 1005, 699, 401, 646, 472, 598, 681, 1126, 1260, 562, 491, 714, 530, 521, 687, 776, 802, 499, 536, 871, 801, 965, 768, 381, 497, 458, 699, 549, 427, 358, 219, 635, 756, 775, 969, 598, 630, 649, 722, 835, 812, 724, 966, 778, 584, 697, 737, 777, 1059, 1218, 848, 713, 884, 879, 1056, 1273, 1848, 780, 1206, 1404, 1444, 1412, 1493, 1576, 1178, 836, 1087, 1101, 1082, 775, 698, 620, 651, 731, 906, 958, 1039, 1105, 620, 576, 707, 888, 1052, 1072, 1357, 768, 986, 816, 889, 973, 983, 1351, 1266, 1053, 1879, 2085, 2419, 1880, 2045, 2212, 1491, 1378, 1524, 1231, 1577, 2459, 1848, 1506, 1589, 1386, 1111, 1180, 1075, 1595, 1309, 2092, 1846, 2321, 2036, 3587, 1637, 1416, 1432, 1110, 1135, 1233, 1439, 894, 628, 967, 1176, 1069, 1193, 1771, 1199, 888, 1155, 1254, 1403, 1502, 1692, 1187, 1110, 1382, 1808, 2039, 1810, 1819, 1408, 803, 1568, 1227, 1270, 1268, 1535, 873, 1006, 1328, 1733, 1352, 1906, 2029, 1734, 1314, 1810, 1540, 1958, 1420, 1530, 1126, 721, 771, 874, 997, 1186, 1415, 973, 1146, 1147, 1079, 3854, 3407, 2257, 1200, 734, 1051, 1030, 1370, 2422, 1531, 1062, 530, 1030, 1061, 1249, 2080, 2251, 1190, 756, 1161, 1053, 1063, 932, 1604, 1130, 744, 930, 948, 1107, 1161, 1194, 1366, 1155, 785, 602, 903, 1142, 1410, 1256, 742, 985, 1037, 1067, 1196, 1412, 1127, 779, 911, 989, 946, 888, 1349, 1124, 761, 994, 1068, 971, 1157, 1558, 1223, 782, 2790, 1835, 1444, 1098, 1399, 1255, 950, 1110, 1345, 1224, 1092, 1446, 1210, 1122, 1259, 1181, 1035, 1325, 1481, 1278, 769, 911, 876, 877, 950, 1383, 980, 705, 888, 877, 638, 1065, 1142, 1090, 1316, 1270, 1048, 1256, 1009, 1175, 1176, 870, 856, 860])
    n_predict = 100
    extrapolation = fourierExtrapolation(x, n_predict)

    pl.figure()
    pl.plot(np.arange(len(x), len(extrapolation) + len(x)), extrapolation, 'r', label = 'extrapolation')
    pl.plot(x, 'b', label = 'Given Data', linewidth = 3)
    pl.legend()
    pl.ylabel('BPM')
    pl.xlabel('Sample')
    pl.title('Fourier Extrapolation')
    pl.savefig('FourierExtrapolation.png')
    #pl.show()
    with open('Fourier_PredValues.txt', 'w') as out:
        out.write(str([e for e in extrapolation]).strip('[]'))
pyroc.py 文件源码 项目:bokeh_roc_slider 作者: brianray 项目源码 文件源码 阅读 21 收藏 0 点赞 0 评论 0
def plot_multiple_rocs_separate(rocList,title='', labels = None, equal_aspect = True):
    """ Plot multiples ROC curves as separate at the same painting area. """
    pylab.clf()
    pylab.title(title)
    for ix, r in enumerate(rocList):
        ax = pylab.subplot(4,4,ix+1)
        pylab.ylim((0,1))
        pylab.xlim((0,1))
        ax.set_yticklabels([])
        ax.set_xticklabels([])
        if equal_aspect:
            cax = pylab.gca()
            cax.set_aspect('equal')

        if not labels:
            labels = ['' for x in rocList]

        pylab.text(0.2,0.1,labels[ix],fontsize=8)
        pylab.plot([x[0] for x in r.derived_points],[y[1] for y in r.derived_points], 'r-',linewidth=2)

    pylab.show()
pyroc.py 文件源码 项目:bokeh_roc_slider 作者: brianray 项目源码 文件源码 阅读 26 收藏 0 点赞 0 评论 0
def plot(self,title='',include_baseline=False,equal_aspect=True):
        """ Method that generates a plot of the ROC curve
            Parameters:
                title: Title of the chart
                include_baseline: Add the baseline plot line if it's True
                equal_aspect: Aspects to be equal for all plot
        """

        pylab.clf()
        pylab.plot([x[0] for x in self.derived_points], [y[1] for y in self.derived_points], self.linestyle)
        if include_baseline:
            pylab.plot([0.0,1.0], [0.0,1.0],'k-.')
        pylab.ylim((0,1))
        pylab.xlim((0,1))
        pylab.xticks(pylab.arange(0,1.1,.1))
        pylab.yticks(pylab.arange(0,1.1,.1))
        pylab.grid(True)
        if equal_aspect:
            cax = pylab.gca()
            cax.set_aspect('equal')
        pylab.xlabel('1 - Specificity')
        pylab.ylabel('Sensitivity')
        pylab.title(title)

        pylab.show()
common.py 文件源码 项目:mglex 作者: fungs 项目源码 文件源码 阅读 20 收藏 0 点赞 0 评论 0
def plot_clusters_pca(responsibilities, color_groups):
    from sklearn.decomposition import RandomizedPCA
    import pylab as pl
    from random import shuffle

    colors = list(colors_dict.values())
    shuffle(colors)

    pca = RandomizedPCA(n_components=2)
    X = pca.fit_transform(responsibilities)
    # print >>stderr, pca.explained_variance_ratio_

    pl.figure()
    pl.scatter(X[:, 0], X[:, 1], c="grey", label="unknown")
    for c, sub, i in zip(colors, color_groups, count(0)):
        pl.scatter(X[sub, 0], X[sub, 1], c=c, label=str(i))
    pl.legend()
    pl.title("PCA responsibility matrix")
    pl.show()
bench_plot_parallel_pairwise.py 文件源码 项目:Parallel-SGD 作者: angadgill 项目源码 文件源码 阅读 24 收藏 0 点赞 0 评论 0
def plot(func):
    random_state = check_random_state(0)
    one_core = []
    multi_core = []
    sample_sizes = range(1000, 6000, 1000)

    for n_samples in sample_sizes:
        X = random_state.rand(n_samples, 300)

        start = time.time()
        func(X, n_jobs=1)
        one_core.append(time.time() - start)

        start = time.time()
        func(X, n_jobs=-1)
        multi_core.append(time.time() - start)

    pl.figure('scikit-learn parallel %s benchmark results' % func.__name__)
    pl.plot(sample_sizes, one_core, label="one core")
    pl.plot(sample_sizes, multi_core, label="multi core")
    pl.xlabel('n_samples')
    pl.ylabel('Time (s)')
    pl.title('Parallel %s' % func.__name__)
    pl.legend()
data_visualization.py 文件源码 项目:Oedipus 作者: tum-i22 项目源码 文件源码 阅读 20 收藏 0 点赞 0 评论 0
def plotAccuracyGraph(X, Y, Xlabel='Variable', Ylabel='Accuracy', graphTitle="Test Accuracy Graph", filename="graph.pdf"):
    """ Plots and saves accuracy graphs """
    try:
        timestamp = int(time.time())
        fig = P.figure(figsize=(8,5))
        # Set the graph's title
        P.title(graphTitle, fontname='monospace')
        # Set the axes labels
        P.xlabel(Xlabel, fontsize=12, fontname='monospace')
        P.ylabel(Ylabel, fontsize=12, fontname='monospace')
        # Add horizontal and vertical lines to the graph
        P.grid(color='DarkGray', linestyle='--', linewidth=0.1, axis='both')
        # Add the data to the graph
        P.plot(X, Y, 'r-*', linewidth=1.0)
        # Save figure
        prettyPrint("Saving figure to ./%s" % filename)#(graphTitle.replace(" ","_"), timestamp))
        P.tight_layout()
        fig.savefig("./%s" % filename)#(graphTitle.replace(" ", "_"), timestamp))

    except Exception as e:
        prettyPrint("Error encountered in \"plotAccuracyGraph\": %s" % e, "error")
        return False

    return True
random_walk.py 文件源码 项目:MIT-CS-lectures 作者: William-Python-King 项目源码 文件源码 阅读 19 收藏 0 点赞 0 评论 0
def ansQuest(maxTime,numTrials):
    means=[]
    distLists=performSim(maxTime,numTrials)
    for t in range(maxTime+1):
        tot=0.0
        for distL  in  distLists:
            tot+=distL[t]
        means.append(tot/len(distL))
    pylab.figure()
    pylab.plot(means)
    pylab.xlabel('distance')
    pylab.ylabel('time')
    pylab.title('Average Distance  vs. Time ('+str(len(distLists))+'trials)')
TensorFlowInterface.py 文件源码 项目:IntroToDeepLearning 作者: robb-brown 项目源码 文件源码 阅读 24 收藏 0 点赞 0 评论 0
def plotFields(layer,fieldShape=None,channel=None,figOffset=1,cmap=None,padding=0.01):
    # Receptive Fields Summary
    try:
        W = layer.W
    except:
        W = layer
    wp = W.eval().transpose();
    if len(np.shape(wp)) < 4:       # Fully connected layer, has no shape
        fields = np.reshape(wp,list(wp.shape[0:-1])+fieldShape) 
    else:           # Convolutional layer already has shape
        features, channels, iy, ix = np.shape(wp)
        if channel is not None:
            fields = wp[:,channel,:,:]
        else:
            fields = np.reshape(wp,[features*channels,iy,ix])

    perRow = int(math.floor(math.sqrt(fields.shape[0])))
    perColumn = int(math.ceil(fields.shape[0]/float(perRow)))

    fig = mpl.figure(figOffset); mpl.clf()

    # Using image grid
    from mpl_toolkits.axes_grid1 import ImageGrid
    grid = ImageGrid(fig,111,nrows_ncols=(perRow,perColumn),axes_pad=padding,cbar_mode='single')
    for i in range(0,np.shape(fields)[0]):
        im = grid[i].imshow(fields[i],cmap=cmap); 

    grid.cbar_axes[0].colorbar(im)
    mpl.title('%s Receptive Fields' % layer.name)

    # old way
    # fields2 = np.vstack([fields,np.zeros([perRow*perColumn-fields.shape[0]] + list(fields.shape[1:]))])
    # tiled = []
    # for i in range(0,perColumn*perRow,perColumn):
    #   tiled.append(np.hstack(fields2[i:i+perColumn]))
    # 
    # tiled = np.vstack(tiled)
    # mpl.figure(figOffset); mpl.clf(); mpl.imshow(tiled,cmap=cmap); mpl.title('%s Receptive Fields' % layer.name); mpl.colorbar();
    mpl.figure(figOffset+1); mpl.clf(); mpl.imshow(np.sum(np.abs(fields),0),cmap=cmap); mpl.title('%s Total Absolute Input Dependency' % layer.name); mpl.colorbar()
TensorFlowInterface.py 文件源码 项目:IntroToDeepLearning 作者: robb-brown 项目源码 文件源码 阅读 31 收藏 0 点赞 0 评论 0
def plotOutput(layer,feed_dict,fieldShape=None,channel=None,figOffset=1,cmap=None):
    # Output summary
    try:
        W = layer.output
    except:
        W = layer
    wp = W.eval(feed_dict=feed_dict);
    if len(np.shape(wp)) < 4:       # Fully connected layer, has no shape
        temp = np.zeros(np.product(fieldShape)); temp[0:np.shape(wp.ravel())[0]] = wp.ravel()
        fields = np.reshape(temp,[1]+fieldShape)
    else:           # Convolutional layer already has shape
        wp = np.rollaxis(wp,3,0)
        features, channels, iy,ix = np.shape(wp)
        if channel is not None:
            fields = wp[:,channel,:,:]
        else:
            fields = np.reshape(wp,[features*channels,iy,ix])

    perRow = int(math.floor(math.sqrt(fields.shape[0])))
    perColumn = int(math.ceil(fields.shape[0]/float(perRow)))
    fields2 = np.vstack([fields,np.zeros([perRow*perColumn-fields.shape[0]] + list(fields.shape[1:]))])
    tiled = []
    for i in range(0,perColumn*perRow,perColumn):
        tiled.append(np.hstack(fields2[i:i+perColumn]))

    tiled = np.vstack(tiled)
    if figOffset is not None:
        mpl.figure(figOffset); mpl.clf(); 

    mpl.imshow(tiled,cmap=cmap); mpl.title('%s Output' % layer.name); mpl.colorbar();
TensorFlowInterface.py 文件源码 项目:IntroToDeepLearning 作者: robb-brown 项目源码 文件源码 阅读 25 收藏 0 点赞 0 评论 0
def plotFields(layer,fieldShape=None,channel=None,maxFields=25,figName='ReceptiveFields',cmap=None,padding=0.01):
    # Receptive Fields Summary
    W = layer.W
    wp = W.eval().transpose();
    if len(np.shape(wp)) < 4:       # Fully connected layer, has no shape
        fields = np.reshape(wp,list(wp.shape[0:-1])+fieldShape)
    else:           # Convolutional layer already has shape
        features, channels, iy, ix = np.shape(wp)
        if channel is not None:
            fields = wp[:,channel,:,:]
        else:
            fields = np.reshape(wp,[features*channels,iy,ix])

    fieldsN = min(fields.shape[0],maxFields)
    perRow = int(math.floor(math.sqrt(fieldsN)))
    perColumn = int(math.ceil(fieldsN/float(perRow)))

    fig = mpl.figure(figName); mpl.clf()

    # Using image grid
    from mpl_toolkits.axes_grid1 import ImageGrid
    grid = ImageGrid(fig,111,nrows_ncols=(perRow,perColumn),axes_pad=padding,cbar_mode='single')
    for i in range(0,fieldsN):
        im = grid[i].imshow(fields[i],cmap=cmap);

    grid.cbar_axes[0].colorbar(im)
    mpl.title('%s Receptive Fields' % layer.name)

    # old way
    # fields2 = np.vstack([fields,np.zeros([perRow*perColumn-fields.shape[0]] + list(fields.shape[1:]))])
    # tiled = []
    # for i in range(0,perColumn*perRow,perColumn):
    #   tiled.append(np.hstack(fields2[i:i+perColumn]))
    #
    # tiled = np.vstack(tiled)
    # mpl.figure(figOffset); mpl.clf(); mpl.imshow(tiled,cmap=cmap); mpl.title('%s Receptive Fields' % layer.name); mpl.colorbar();
    mpl.figure(figName+' Total'); mpl.clf(); mpl.imshow(np.sum(np.abs(fields),0),cmap=cmap); mpl.title('%s Total Absolute Input Dependency' % layer.name); mpl.colorbar()
TensorFlowInterface.py 文件源码 项目:IntroToDeepLearning 作者: robb-brown 项目源码 文件源码 阅读 23 收藏 0 点赞 0 评论 0
def plotOutput(layer,feed_dict,fieldShape=None,channel=None,figOffset=1,cmap=None):
    # Output summary
    W = layer.output
    wp = W.eval(feed_dict=feed_dict);
    if len(np.shape(wp)) < 4:       # Fully connected layer, has no shape
        temp = np.zeros(np.product(fieldShape)); temp[0:np.shape(wp.ravel())[0]] = wp.ravel()
        fields = np.reshape(temp,[1]+fieldShape)
    else:           # Convolutional layer already has shape
        wp = np.rollaxis(wp,3,0)
        features, channels, iy,ix = np.shape(wp)
        if channel is not None:
            fields = wp[:,channel,:,:]
        else:
            fields = np.reshape(wp,[features*channels,iy,ix])

    perRow = int(math.floor(math.sqrt(fields.shape[0])))
    perColumn = int(math.ceil(fields.shape[0]/float(perRow)))
    fields2 = np.vstack([fields,np.zeros([perRow*perColumn-fields.shape[0]] + list(fields.shape[1:]))])
    tiled = []
    for i in range(0,perColumn*perRow,perColumn):
        tiled.append(np.hstack(fields2[i:i+perColumn]))

    tiled = np.vstack(tiled)
    if figOffset is not None:
        mpl.figure(figOffset); mpl.clf();

    mpl.imshow(tiled,cmap=cmap); mpl.title('%s Output' % layer.name); mpl.colorbar();


问题


面经


文章

微信
公众号

扫码关注公众号