Python matplotlib.pyplot.imshow() Examples

def save_frames(images, filename):
    num_sequences, n_steps, w, h = images.shape

    fig = plt.figure()
    im = plt.imshow(combine_multiple_img(images[:, 0]), cmap=plt.cm.get_cmap('Greys'), interpolation='none')
    plt.axis('image')

    def updatefig(*args):
        im.set_array(combine_multiple_img(images[:, args[0]]))
        return im,

    ani = animation.FuncAnimation(fig, updatefig, interval=500, frames=n_steps)

    # Either avconv or ffmpeg need to be installed in the system to produce the videos!
    try:
        writer = animation.writers['avconv']
    except KeyError:
        writer = animation.writers['ffmpeg']
    writer = writer(fps=3)
    ani.save(filename, writer=writer)
    plt.close(fig) 

def plotNNFilter(units, figure_id, interp='bilinear', colormap=cm.jet, colormap_lim=None):
    plt.ion()
    filters = units.shape[2]
    n_columns = round(math.sqrt(filters))
    n_rows = math.ceil(filters / n_columns) + 1
    fig = plt.figure(figure_id, figsize=(n_rows*3,n_columns*3))
    fig.clf()

    for i in range(filters):
        ax1 = plt.subplot(n_rows, n_columns, i+1)
        plt.imshow(units[:,:,i].T, interpolation=interp, cmap=colormap)
        plt.axis('on')
        ax1.set_xticklabels([])
        ax1.set_yticklabels([])
        plt.colorbar()
        if colormap_lim:
            plt.clim(colormap_lim[0],colormap_lim[1])

    plt.subplots_adjust(wspace=0, hspace=0)
    plt.tight_layout()

# Epochs 

def save_movie_to_frame(images, filename, idx=0, cmap='Blues'):
    # Collect to single image
    image = movie_to_frame(images[idx])

    # Flip it
    # image = np.fliplr(image)
    # image = np.flipud(image)

    f = plt.figure(figsize=[12, 12])
    plt.imshow(image, cmap=plt.cm.get_cmap(cmap), interpolation='none', vmin=0, vmax=1)

    plt.axis('image')
    plt.xticks([])
    plt.yticks([])
    plt.savefig(filename, format='png', bbox_inches='tight', dpi=80)
    plt.close(f) 

def generate_png_chess_dp_vertex(self):
    """Produces pictures of the dominant product vertex a chessboard convention"""
    import matplotlib.pylab as plt
    plt.ioff()
    dab2v = self.get_dp_vertex_doubly_sparse()
    for i, ab in enumerate(dab2v): 
        fname = "chess-v-{:06d}.png".format(i)
        print('Matrix No.#{}, Size: {}, Type: {}'.format(i+1, ab.shape, type(ab)), fname)
        if type(ab) != 'numpy.ndarray': ab = ab.toarray()
        fig = plt.figure()
        ax = fig.add_subplot(1,1,1)
        ax.set_aspect('equal')
        plt.imshow(ab, interpolation='nearest', cmap=plt.cm.ocean)
        plt.colorbar()
        plt.savefig(fname)
        plt.close(fig) 

def show_result_pyplot(model, img, result, score_thr=0.3, fig_size=(15, 10)):
    """Visualize the detection results on the image.

    Args:
        model (nn.Module): The loaded detector.
        img (str or np.ndarray): Image filename or loaded image.
        result (tuple[list] or list): The detection result, can be either
            (bbox, segm) or just bbox.
        score_thr (float): The threshold to visualize the bboxes and masks.
        fig_size (tuple): Figure size of the pyplot figure.
    """
    if hasattr(model, 'module'):
        model = model.module
    img = model.show_result(img, result, score_thr=score_thr, show=False)
    plt.figure(figsize=fig_size)
    plt.imshow(mmcv.bgr2rgb(img))
    plt.show() 

def test_interpolate_grid_elmdata_dicontinuous(self, sphere3_msh):
        data = sphere3_msh.elm.tag1
        f = mesh_io.ElementData(data, mesh=sphere3_msh)
        n = (200, 130, 1)
        affine = np.array([[1, 0, 0, -100.1],
                           [0,-1, 0, 65.1],
                           [0, 0, 1, 0],
                           [0, 0, 0, 1]], dtype=float)
        interp = f.interpolate_to_grid(n, affine, method='linear', continuous=False)
        '''
        import matplotlib.pyplot as plt
        plt.figure()
        plt.imshow(np.squeeze(interp))
        plt.colorbar()
        plt.show()
        '''
        assert np.allclose(interp[6:10, 65, 0], 5, atol=1e-1)
        assert np.allclose(interp[11:15, 65, 0], 4, atol=1e-1)
        assert np.allclose(interp[16:100, 65, 0], 3, atol=1e-1) 

def plotNNFilter(units, figure_id, interp='bilinear', colormap=cm.jet, colormap_lim=None):
    plt.ion()
    filters = units.shape[2]
    n_columns = round(math.sqrt(filters))
    n_rows = math.ceil(filters / n_columns) + 1
    fig = plt.figure(figure_id, figsize=(n_rows*3,n_columns*3))
    fig.clf()

    for i in range(filters):
        ax1 = plt.subplot(n_rows, n_columns, i+1)
        plt.imshow(units[:,:,i].T, interpolation=interp, cmap=colormap)
        plt.axis('on')
        ax1.set_xticklabels([])
        ax1.set_yticklabels([])
        plt.colorbar()
        if colormap_lim:
            plt.clim(colormap_lim[0],colormap_lim[1])

    plt.subplots_adjust(wspace=0, hspace=0)
    plt.tight_layout()

# Load options 

def show(image):
    """
    Render a given numpy.uint8 2D array of pixel data.
    """
    plt.imshow(image, cmap='gray')
    plt.show() 

def visualize_sampling(self, permutations):
        max_length = len(permutations[0])
        grid = np.zeros([max_length,max_length]) # initialize heatmap grid to 0

        transposed_permutations = np.transpose(permutations)
        for t, cities_t in enumerate(transposed_permutations): # step t, cities chosen at step t
            city_indices, counts = np.unique(cities_t,return_counts=True,axis=0)
            for u,v in zip(city_indices, counts):
                grid[t][u]+=v # update grid with counts from the batch of permutations

        # plot heatmap
        fig = plt.figure()
        rcParams.update({'font.size': 22})
        ax = fig.add_subplot(1,1,1)
        ax.set_aspect('equal')
        plt.imshow(grid, interpolation='nearest', cmap='gray')
        plt.colorbar()
        plt.title('Sampled permutations')
        plt.ylabel('Time t')
        plt.xlabel('City i')
        plt.show() 

def test_interpolate_grid_elmdata_linear(self, sphere3_msh):
        data = sphere3_msh.elements_baricenters().value[:, 0]
        f = mesh_io.ElementData(data, mesh=sphere3_msh)
        n = (130, 130, 1)
        affine = np.array([[1, 0, 0, -65],
                           [0, 1, 0, -65],
                           [0, 0, 1, 0],
                           [0, 0, 0, 1]], dtype=float)
        X, _ = np.meshgrid(np.arange(130), np.arange(130), indexing='ij')
        interp = f.interpolate_to_grid(n, affine, method='linear', continuous=True)
        '''
        import matplotlib.pyplot as plt
        plt.figure()
        plt.imshow(np.squeeze(interp))
        plt.colorbar()
        plt.show()
        '''
        assert np.allclose(interp[:, :, 0], X - 64.5, atol=1) 

def test_interpolate_grid_rotate_nodedata(self, sphere3_msh):
        data = np.zeros(sphere3_msh.nodes.nr)
        b = sphere3_msh.nodes.node_coord.copy()
        f = mesh_io.NodeData(data, mesh=sphere3_msh)
        # Assign quadrant numbers
        f.value[(b[:, 0] >= 0) * (b[:, 1] >= 0)] = 1.
        f.value[(b[:, 0] <= 0) * (b[:, 1] >= 0)] = 2.
        f.value[(b[:, 0] <= 0) * (b[:, 1] <= 0)] = 3.
        f.value[(b[:, 0] >= 0) * (b[:, 1] <= 0)] = 4.
        n = (200, 200, 1)
        affine = np.array([[np.cos(np.pi/4.), np.sin(np.pi/4.), 0, -141],
                           [-np.sin(np.pi/4.), np.cos(np.pi/4.), 0, 0],
                           [0, 0, 1, .5],
                           [0, 0, 0, 1]], dtype=float)
        interp = f.interpolate_to_grid(n, affine)
        '''
        import matplotlib.pyplot as plt
        plt.imshow(np.squeeze(interp), interpolation='nearest')
        plt.colorbar()
        plt.show()
        '''
        assert np.isclose(interp[190, 100, 0], 4)
        assert np.isclose(interp[100, 190, 0], 1)
        assert np.isclose(interp[10, 100, 0], 2)
        assert np.isclose(interp[100, 10, 0], 3) 

def test_heatmaps(heatmaps,img,i):
    heatmaps=heatmaps.numpy()
    #heatmaps=np.squeeze(heatmaps)
    heatmaps=heatmaps[:,:64,:]
    heatmaps=heatmaps.transpose(1,2,0)
    print('heatmap inside shape is',heatmaps.shape)
##    print('----------------here')
##    print(heatmaps.shape)
    img=img.numpy()
    #img=np.squeeze(img)
    img=img.transpose(1,2,0)
    img=cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
#    print('heatmaps',heatmaps.shape)
    heatmaps = cv2.resize(heatmaps,(0,0), fx=4,fy=4)
#    print('heatmapsafter',heatmaps.shape)
    for j in range(0, 16):
        heatmap = heatmaps[:,:,j]
        heatmap = heatmap.reshape((256,256,1))
        heatmapimg = np.array(heatmap * 255, dtype = np.uint8)
        heatmap = cv2.applyColorMap(heatmapimg, cv2.COLORMAP_JET)
        heatmap = heatmap/255
        plt.imshow(img)
        plt.imshow(heatmap, alpha=0.5)
        plt.show()
        #plt.savefig('hmtestpadh36'+str(i)+js[j]+'.png') 

def test_interpolate_grid_const_nn(self, sphere3_msh):
        data = sphere3_msh.elm.tag1
        f = mesh_io.ElementData(data, mesh=sphere3_msh)
        n = (200, 10, 1)
        affine = np.array([[1, 0, 0, -100.5],
                           [0, 1, 0, -5],
                           [0, 0, 1, 0],
                           [0, 0, 0, 1]], dtype=float)
        interp = f.interpolate_to_grid(n, affine, method='assign')
        '''
        import matplotlib.pyplot as plt
        plt.imshow(np.squeeze(interp))
        plt.colorbar()
        plt.show()
        assert False
        '''
        assert np.isclose(interp[100, 5, 0], 3)
        assert np.isclose(interp[187, 5, 0], 4)
        assert np.isclose(interp[193, 5, 0], 5)
        assert np.isclose(interp[198, 5, 0], 0) 

def plot_some_results(pred_fn, test_generator, n_images=10):
    fig_ctr = 0
    for data, seg in test_generator:
        res = pred_fn(data)
        for d, s, r in zip(data, seg, res):
            plt.figure(figsize=(12, 6))
            plt.subplot(1, 3, 1)
            plt.imshow(d.transpose(1,2,0))
            plt.title("input patch")
            plt.subplot(1, 3, 2)
            plt.imshow(s[0])
            plt.title("ground truth")
            plt.subplot(1, 3, 3)
            plt.imshow(r)
            plt.title("segmentation")
            plt.savefig("road_segmentation_result_%03.0f.png"%fig_ctr)
            plt.close()
            fig_ctr += 1
            if fig_ctr > n_images:
                break 

def save_movies_to_frame(images, filename, cmap='Blues'):
    # Binarize images
    # images[images > 0] = 1.

    # Grid images
    images = np.swapaxes(images, 1, 0)
    images = np.array([combine_multiple_img(image) for image in images])

    # Collect to single image
    image = movie_to_frame(images)

    f = plt.figure(figsize=[12, 12])
    plt.imshow(image, cmap=plt.cm.get_cmap(cmap), interpolation='none', vmin=0, vmax=1)
    plt.axis('image')
    plt.savefig(filename, format='png', bbox_inches='tight', dpi=80)
    plt.close(f) 

def classify(self, features, show=False):
        recs, _ = features.shape
        result_shape = (features.shape[0], len(self.root))
        scores = np.zeros(result_shape)
        print scores.shape
        R = Record(np.arange(recs, dtype=int), features)

        for i, T in enumerate(self.root):
            for idxs, result in classify(T, R):
                for idx in idxs.indexes():
                    scores[idx, i] = float(result[0]) / sum(result.values())


        if show:
            plt.cla()
            plt.clf()
            plt.close()

            plt.imshow(scores, cmap=plt.cm.gray)
            plt.title('Scores matrix')
            plt.savefig(r"../scratch/tree_scores.png", bbox_inches='tight')
        
        return scores 

def preprocess_image(img_path):
    img = io.imread(img_path)
    if np.max(img.shape[:2]) != config.img_size:
        print('Resizing so the max image size is %d..' % config.img_size)
        scale = (float(config.img_size) / np.max(img.shape[:2]))
    else:
        scale = 1.0#scaling_factor
    center = np.round(np.array(img.shape[:2]) / 2).astype(int)
    # image center in (x,y)
    center = center[::-1]
    crop, proc_param = img_util.scale_and_crop(img, scale, center,
                                               config.img_size)
    # import ipdb; ipdb.set_trace()
    # Normalize image to [-1, 1]
    # plt.imshow(crop/255.0)
    # plt.show()
    crop = 2 * ((crop / 255.) - 0.5)

    return crop, proc_param, img 

def plotNNFilterOverlay(input_im, units, figure_id, interp='bilinear',
                        colormap=cm.jet, colormap_lim=None, title='', alpha=0.8):
    plt.ion()
    filters = units.shape[2]
    fig = plt.figure(figure_id, figsize=(5,5))
    fig.clf()

    for i in range(filters):
        plt.imshow(input_im[:,:,0], interpolation=interp, cmap='gray')
        plt.imshow(units[:,:,i], interpolation=interp, cmap=colormap, alpha=alpha)
        plt.axis('off')
        plt.colorbar()
        plt.title(title, fontsize='small')
        if colormap_lim:
            plt.clim(colormap_lim[0],colormap_lim[1])

    plt.subplots_adjust(wspace=0, hspace=0)
    plt.tight_layout()

    # plt.savefig('{}/{}.png'.format(dir_name,time.time()))




## Load options 

def plot_attention(sentences, attentions, labels, **kwargs):
    fig, ax = plt.subplots(**kwargs)
    im = ax.imshow(attentions, interpolation='nearest',
                   vmin=attentions.min(), vmax=attentions.max())
    plt.colorbar(im, shrink=0.5, ticks=[0, 1])
    plt.setp(ax.get_xticklabels(), rotation=45, ha="right",
             rotation_mode="anchor")
    ax.set_yticks(range(len(labels)))
    ax.set_yticklabels(labels, fontproperties=getChineseFont())
    # Loop over data dimensions and create text annotations.
    for i in range(attentions.shape[0]):
        for j in range(attentions.shape[1]):
            text = ax.text(j, i, sentences[i][j],
                           ha="center", va="center", color="b", size=10,
                           fontproperties=getChineseFont())

    ax.set_title("Attention Visual")
    fig.tight_layout()
    plt.show() 

def plotNNFilter(units, figure_id, interp='bilinear', colormap=cm.jet, colormap_lim=None, title=''):
    plt.ion()
    filters = units.shape[2]
    n_columns = round(math.sqrt(filters))
    n_rows = math.ceil(filters / n_columns) + 1
    fig = plt.figure(figure_id, figsize=(n_rows*3,n_columns*3))
    fig.clf()

    for i in range(filters):
        ax1 = plt.subplot(n_rows, n_columns, i+1)
        plt.imshow(units[:,:,i].T, interpolation=interp, cmap=colormap)
        plt.axis('on')
        ax1.set_xticklabels([])
        ax1.set_yticklabels([])
        plt.colorbar()
        if colormap_lim:
            plt.clim(colormap_lim[0],colormap_lim[1])

    plt.subplots_adjust(wspace=0, hspace=0)
    plt.tight_layout()
    plt.suptitle(title) 

def test(self):

        list_ = os.listdir("./maps/val/")
        nums_file = list_.__len__()
        saver = tf.train.Saver(tf.get_collection(tf.GraphKeys.GLOBAL_VARIABLES, "generator"))
        saver.restore(self.sess, "./save_para/model.ckpt")
        rand_select = np.random.randint(0, nums_file)
        INPUTS_CONDITION = np.zeros([1, self.img_h, self.img_w, 3])
        INPUTS = np.zeros([1, self.img_h, self.img_w, 3])
        img = np.array(Image.open(self.path + list_[rand_select]))
        img_h, img_w = img.shape[0], img.shape[1]
        INPUTS_CONDITION[0] = misc.imresize(img[:, img_w//2:], [self.img_h, self.img_w]) / 127.5 - 1.0
        INPUTS[0] = misc.imresize(img[:, :img_w//2], [self.img_h, self.img_w]) / 127.5 - 1.0
        [fake_img] = self.sess.run([self.inputs_fake], feed_dict={self.inputs_condition: INPUTS_CONDITION})
        out_img = np.concatenate((INPUTS_CONDITION[0], fake_img[0], INPUTS[0]), axis=1)
        Image.fromarray(np.uint8((out_img + 1.0)*127.5)).save("./results/1.jpg")
        plt.imshow(np.uint8((out_img + 1.0)*127.5))
        plt.grid("off")
        plt.axis("off")
        plt.show() 

def test_interpolate_grid_rotate_nn(self, sphere3_msh):
        data = np.zeros(sphere3_msh.elm.nr)
        b = sphere3_msh.elements_baricenters().value
        f = mesh_io.ElementData(data, mesh=sphere3_msh)
        # Assign quadrant numbers
        f.value[(b[:, 0] > 0) * (b[:, 1] > 0)] = 1.
        f.value[(b[:, 0] < 0) * (b[:, 1] > 0)] = 2.
        f.value[(b[:, 0] < 0) * (b[:, 1] < 0)] = 3.
        f.value[(b[:, 0] > 0) * (b[:, 1] < 0)] = 4.
        n = (200, 200, 1)
        affine = np.array([[np.cos(np.pi/4.), np.sin(np.pi/4.), 0, -141],
                           [-np.sin(np.pi/4.), np.cos(np.pi/4.), 0, 0],
                           [0, 0, 1, .5],
                           [0, 0, 0, 1]], dtype=float)
        interp = f.interpolate_to_grid(n, affine, method='assign')
        '''
        import matplotlib.pyplot as plt
        plt.imshow(np.squeeze(interp))
        plt.colorbar()
        plt.show()
        '''
        assert np.isclose(interp[190, 100, 0], 4)
        assert np.isclose(interp[100, 190, 0], 1)
        assert np.isclose(interp[10, 100, 0], 2)
        assert np.isclose(interp[100, 10, 0], 3) 

def save_true_generated_frames(true, generated, filename):
    num_sequences, n_steps, w, h = true.shape

    # Background is 0, foreground as 1
    true = np.copy(true[:16])
    true[true > 0.1] = 1

    # Set foreground be near 0.5
    generated = generated * .5

    # Background is 1, foreground is near 0.5
    generated = 1 - generated[:16, :n_steps]

    # Subtract true from generated so background is 1, true foreground is 0,
    # and generated foreground is around 0.5
    images = generated - true
    # images[images > 0.5] = 1.

    fig = plt.figure()
    im = plt.imshow(combine_multiple_img(images[:, 0]), cmap=plt.cm.get_cmap('gist_heat'),
                    interpolation='none', vmin=0, vmax=1)
    plt.axis('image')

    def updatefig(*args):
        im.set_array(combine_multiple_img(images[:, args[0]]))
        return im,

    ani = animation.FuncAnimation(fig, updatefig, interval=500, frames=n_steps)

    try:
        writer = animation.writers['avconv']
    except KeyError:
        writer = animation.writers['ffmpeg']
    writer = writer(fps=3)
    ani.save(filename, writer=writer)
    plt.close(fig) 

def plot_mat(self, path, dictionary=None, annotate=False):
        plt.figure(dpi=600)
        plt.imshow(self.mat,
            cmap=plt.cm.jet,
            interpolation=None,
            extent=(0.5, np.shape(self.mat)[0]+0.5, np.shape(self.mat)[1]+0.5, 0.5))
        width, height = self.mat.shape
        if annotate:
            for x in range(width):
                for y in range(height):
                    plt.annotate(str(int(self.mat[x][y])), xy=(y+1, x+1),
                                 horizontalalignment='center',
                                 verticalalignment='center',
                                 fontsize=8)

        if dictionary is not None:
            plt.xticks([i+1 for i in range(width)],
                       [dictionary[i] for i in range(width)],
                       rotation='vertical')
            plt.yticks([i+1 for i in range(height)],
                       [dictionary[i] for i in range(height)])
        plt.xlabel('Ground Truth')
        plt.ylabel('Prediction')
        plt.colorbar()
        plt.tight_layout()
        plt.savefig(path, format='svg')
        plt.clf()

        # for i in range(width):
        #     if np.sum(self.mat[i,:]) != 0:
        #         self.precision.append(self.mat[i,i] / np.sum(self.mat[i,:]))
        #     if np.sum(self.mat[:,i]) != 0:
        #         self.recall.append(self.mat[i,i] / np.sum(self.mat[:,i]))
        # print('Average Precision: %0.4f' % np.mean(self.precision))
        # print('Average Recall: %0.4f' % np.mean(self.recall)) 

def test(fn):
    import matplotlib.pyplot as plt
    cfg.TRAIN.RANDOM_CROP = True
    im = Image.open(fn)
    im = np.asarray(im)[:, :, :3]
    imt = image_transform(im, 10, 10)
    plt.imshow(imt)
    plt.show() 

def main():

    # init conv net
    
    unet = UNet(3,1)
    if os.path.exists("./unet.pkl"):
        unet.load_state_dict(torch.load("./unet.pkl"))
        print("load unet")
    unet.cuda()

    cnn = CNNEncoder()
    if os.path.exists("./cnn.pkl"):
        cnn.load_state_dict(torch.load("./cnn.pkl"))
        print("load cnn")
    cnn.cuda()

    unet.eval()
    cnn.eval()
    
    print("load ok")

    while True:
        pull_screenshot("autojump.png") # obtain screen and save it to autojump.png
        image = Image.open('./autojump.png')
        set_button_position(image)
        image = preprocess(image)
        
        image = Variable(image.unsqueeze(0)).cuda()
        mask = unet(image)

        plt.imshow(mask.squeeze(0).squeeze(0).cpu().data.numpy(), cmap='hot', interpolation='nearest')
        plt.show()
        
        segmentation = image * mask

        press_time = cnn(segmentation)
        press_time = press_time.cpu().data[0].numpy()
        print(press_time)
        jump(press_time)
        
        time.sleep(random.uniform(0.6, 1.1)) 

def imshow(img):
    img = img / 2 + 0.5  # unnormalize
    npimg = img.numpy()
    plt.imshow(np.transpose(npimg, (1, 2, 0)))
    plt.show()


# get some random training images 

def sample_images(self, epoch):
        os.makedirs('images/%s' % self.dataset_name, exist_ok=True)
        r, c = 2, 2

        imgs_hr, imgs_lr = self.data_loader.load_data(batch_size=2, is_testing=True)
        fake_hr = self.generator.predict(imgs_lr)

        # Rescale images 0 - 1
        imgs_lr = 0.5 * imgs_lr + 0.5
        fake_hr = 0.5 * fake_hr + 0.5
        imgs_hr = 0.5 * imgs_hr + 0.5

        # Save generated images and the high resolution originals
        titles = ['Generated', 'Original']
        fig, axs = plt.subplots(r, c)
        cnt = 0
        for row in range(r):
            for col, image in enumerate([fake_hr, imgs_hr]):
                axs[row, col].imshow(image[row])
                axs[row, col].set_title(titles[col])
                axs[row, col].axis('off')
            cnt += 1
        fig.savefig("images/%s/%d.png" % (self.dataset_name, epoch))
        plt.close()

        # Save low resolution images for comparison
        for i in range(r):
            fig = plt.figure()
            plt.imshow(imgs_lr[i])
            fig.savefig('images/%s/%d_lowres%d.png' % (self.dataset_name, epoch, i))
            plt.close() 

def validation(test_path):
    
    file_path = 'success_vcode'
    os.chdir(PATH)
    if file_path not in os.listdir():
        os.makedirs(file_path)
    if 'Windows' in platform.platform():
        file_path = '{}\\{}\\'.format(PATH,'success_vcode')
        test_image_path = [file_path + i for i in os.listdir(file_path+'\\')]
    else:
        file_path = '{}/{}/'.format(PATH,'success_vcode')
        test_image_path = [file_path + i for i in os.listdir(file_path+'/')]
    
    sum_count = len(test_image_path)
    data_set = np.ndarray(( sum_count , 60, 200,3), dtype=np.uint8)
    i=0
    #s = time.time()
    while( i < sum_count ):
        image_name = test_image_path[i]
        image = cv2.imread(image_name)
        data_set[i] = image
        i=i+1
        if i%50 == 0: print('Processed {} of {}'.format(i, sum_count ) )
            
#--------------------------------------------------
    real_labels = []
    for text in test_image_path:
        if 'Windows' in platform.platform():
            text = text.split('\\')
        else:
            text = text.split('/')
        text = text[len(text)-1]
        text_set = text.replace('.png','')
        real_labels.append(text_set)
    image = cv2.imread(image_name)
    plt.imshow(image)
    
    text = main(image)
    print(text) 

def imshow(inp, title):
    """Imshow for Tensor."""
    inp = inp.numpy().transpose((1, 2, 0))
    inp = std * inp + mean
    inp = np.clip(inp, 0, 1)
    plt.imshow(inp)
    plt.title(title)
    plt.show()


# Get a batch of training data