Python misc.create_result_subdir() Examples

def generate_fake_images(run_id, snapshot=None, grid_size=[1,1], num_pngs=1, image_shrink=1, png_prefix=None, random_seed=1000, minibatch_size=8):
    network_pkl = misc.locate_network_pkl(run_id, snapshot)
    if png_prefix is None:
        png_prefix = misc.get_id_string_for_network_pkl(network_pkl) + '-'
    random_state = np.random.RandomState(random_seed)

    print('Loading network from "%s"...' % network_pkl)
    G, D, Gs = misc.load_network_pkl(run_id, snapshot)

    result_subdir = misc.create_result_subdir(config.result_dir, config.desc)
    for png_idx in range(num_pngs):
        print('Generating png %d / %d...' % (png_idx, num_pngs))
        latents = misc.random_latents(np.prod(grid_size), Gs, random_state=random_state)
        labels = np.zeros([latents.shape[0], 0], np.float32)
        images = Gs.run(latents, labels, minibatch_size=minibatch_size, num_gpus=config.num_gpus, out_mul=127.5, out_add=127.5, out_shrink=image_shrink, out_dtype=np.uint8)
        misc.save_image_grid(images, os.path.join(result_subdir, '%s%06d.png' % (png_prefix, png_idx)), [0,255], grid_size)
    open(os.path.join(result_subdir, '_done.txt'), 'wt').close()

#----------------------------------------------------------------------------
# Generate MP4 video of random interpolations using a previously trained network.
# To run, uncomment the appropriate line in config.py and launch train.py. 

def generate_fake_images(run_id, snapshot=None, grid_size=[1,1], num_pngs=1, image_shrink=1, png_prefix=None, random_seed=1000, minibatch_size=8):
    network_pkl = misc.locate_network_pkl(run_id, snapshot)
    if png_prefix is None:
        png_prefix = misc.get_id_string_for_network_pkl(network_pkl) + '-'
    random_state = np.random.RandomState(random_seed)

    print('Loading network from "%s"...' % network_pkl)
    G, D, Gs = misc.load_network_pkl(run_id, snapshot)

    result_subdir = misc.create_result_subdir(config.result_dir, config.desc)
    for png_idx in range(num_pngs):
        print('Generating png %d / %d...' % (png_idx, num_pngs))
        latents = misc.random_latents(np.prod(grid_size), Gs, random_state=random_state)
        labels = np.zeros([latents.shape[0], 0], np.float32)
        images = Gs.run(latents, labels, minibatch_size=minibatch_size, num_gpus=config.num_gpus, out_mul=127.5, out_add=127.5, out_shrink=image_shrink, out_dtype=np.uint8)
        misc.save_image_grid(images, os.path.join(result_subdir, '%s%06d.png' % (png_prefix, png_idx)), [0,255], grid_size)
    open(os.path.join(result_subdir, '_done.txt'), 'wt').close()

#----------------------------------------------------------------------------
# Generate MP4 video of random interpolations using a previously trained network.
# To run, uncomment the appropriate line in config.py and launch train.py. 

def create_result_subdir(result_dir, run_desc):

    # Select run ID and create subdir.
    while True:
        run_id = 0
        for fname in glob.glob(os.path.join(result_dir, '*')):
            try:
                fbase = os.path.basename(fname)
                ford = int(fbase[:fbase.find('-')])
                run_id = max(run_id, ford + 1)
            except ValueError:
                pass

        result_subdir = os.path.join(result_dir, '%03d-%s' % (run_id, run_desc))
        try:
            os.makedirs(result_subdir)
            break
        except OSError:
            if os.path.isdir(result_subdir):
                continue
            raise

    print ("Saving results to", result_subdir)
    return result_subdir 

def create_result_subdir(result_dir, run_desc):

    # Select run ID and create subdir.
    while True:
        run_id = 0
        for fname in glob.glob(os.path.join(result_dir, '*')):
            try:
                fbase = os.path.basename(fname)
                ford = int(fbase[:fbase.find('-')])
                run_id = max(run_id, ford + 1)
            except ValueError:
                pass

        result_subdir = os.path.join(result_dir, '%03d-%s' % (run_id, run_desc))
        try:
            os.makedirs(result_subdir)
            break
        except OSError:
            if os.path.isdir(result_subdir):
                continue
            raise

    print ("Saving results to", result_subdir)
    return result_subdir 

def generate_fake_images(run_id, snapshot=None, grid_size=[1,1], num_pngs=1, image_shrink=1, png_prefix=None, random_seed=1000, minibatch_size=8):
    network_pkl = misc.locate_network_pkl(run_id, snapshot)
    if png_prefix is None:
        png_prefix = misc.get_id_string_for_network_pkl(network_pkl) + '-'
    random_state = np.random.RandomState(random_seed)

    print('Loading network from "%s"...' % network_pkl)
    G, D, Gs = misc.load_network_pkl(run_id, snapshot)

    result_subdir = misc.create_result_subdir(config.result_dir, config.desc)
    for png_idx in range(num_pngs):
        print('Generating png %d / %d...' % (png_idx, num_pngs))
        latents = misc.random_latents(np.prod(grid_size), Gs, random_state=random_state)
        labels = np.zeros([latents.shape[0], 0], np.float32)
        images = Gs.run(latents, labels, minibatch_size=minibatch_size, num_gpus=config.num_gpus, out_mul=127.5, out_add=127.5, out_shrink=image_shrink, out_dtype=np.uint8)
        misc.save_image_grid(images, os.path.join(result_subdir, '%s%06d.png' % (png_prefix, png_idx)), [0,255], grid_size)
    open(os.path.join(result_subdir, '_done.txt'), 'wt').close()

#----------------------------------------------------------------------------
# Generate MP4 video of random interpolations using a previously trained network.
# To run, uncomment the appropriate line in config.py and launch train.py. 

def generate_fake_images(run_id, snapshot=None, grid_size=[1,1], num_pngs=1, image_shrink=1, png_prefix=None, random_seed=1000, minibatch_size=8):
    network_pkl = misc.locate_network_pkl(run_id, snapshot)
    if png_prefix is None:
        png_prefix = misc.get_id_string_for_network_pkl(network_pkl) + '-'
    random_state = np.random.RandomState(random_seed)

    print('Loading network from "%s"...' % network_pkl)
    G, D, Gs = misc.load_network_pkl(run_id, snapshot)

    result_subdir = misc.create_result_subdir(config.result_dir, config.desc)
    for png_idx in range(num_pngs):
        print('Generating png %d / %d...' % (png_idx, num_pngs))
        latents = misc.random_latents(np.prod(grid_size), Gs, random_state=random_state)
        labels = np.zeros([latents.shape[0], 0], np.float32)
        images = Gs.run(latents, labels, minibatch_size=minibatch_size, num_gpus=config.num_gpus, out_mul=127.5, out_add=127.5, out_shrink=image_shrink, out_dtype=np.uint8)
        misc.save_image_grid(images, os.path.join(result_subdir, '%s%06d.png' % (png_prefix, png_idx)), [0,255], grid_size)
    open(os.path.join(result_subdir, '_done.txt'), 'wt').close()

#----------------------------------------------------------------------------
# Generate MP4 video of random interpolations using a previously trained network.
# To run, uncomment the appropriate line in config.py and launch train.py. 

def generate_interpolation_video(run_id, snapshot=None, grid_size=[1,1], image_shrink=1, image_zoom=1, duration_sec=60.0, smoothing_sec=1.0, mp4=None, mp4_fps=30, mp4_codec='libx265', mp4_bitrate='16M', random_seed=1000, minibatch_size=8):
    network_pkl = misc.locate_network_pkl(run_id, snapshot)
    if mp4 is None:
        mp4 = misc.get_id_string_for_network_pkl(network_pkl) + '-lerp.mp4'
    num_frames = int(np.rint(duration_sec * mp4_fps))
    random_state = np.random.RandomState(random_seed)

    print('Loading network from "%s"...' % network_pkl)
    G, D, Gs = misc.load_network_pkl(run_id, snapshot)

    print('Generating latent vectors...')
    shape = [num_frames, np.prod(grid_size)] + Gs.input_shape[1:] # [frame, image, channel, component]
    all_latents = random_state.randn(*shape).astype(np.float32)
    all_latents = scipy.ndimage.gaussian_filter(all_latents, [smoothing_sec * mp4_fps] + [0] * len(Gs.input_shape), mode='wrap')
    all_latents /= np.sqrt(np.mean(np.square(all_latents)))

    # Frame generation func for moviepy.
    def make_frame(t):
        frame_idx = int(np.clip(np.round(t * mp4_fps), 0, num_frames - 1))
        latents = all_latents[frame_idx]
        labels = np.zeros([latents.shape[0], 0], np.float32)
        images = Gs.run(latents, labels, minibatch_size=minibatch_size, num_gpus=config.num_gpus, out_mul=127.5, out_add=127.5, out_shrink=image_shrink, out_dtype=np.uint8)
        grid = misc.create_image_grid(images, grid_size).transpose(1, 2, 0) # HWC
        if image_zoom > 1:
            grid = scipy.ndimage.zoom(grid, [image_zoom, image_zoom, 1], order=0)
        if grid.shape[2] == 1:
            grid = grid.repeat(3, 2) # grayscale => RGB
        return grid

    # Generate video.
    import moviepy.editor # pip install moviepy
    result_subdir = misc.create_result_subdir(config.result_dir, config.desc)
    moviepy.editor.VideoClip(make_frame, duration=duration_sec).write_videofile(os.path.join(result_subdir, mp4), fps=mp4_fps, codec='libx264', bitrate=mp4_bitrate)
    open(os.path.join(result_subdir, '_done.txt'), 'wt').close()

#----------------------------------------------------------------------------
# Generate MP4 video of training progress for a previous training run.
# To run, uncomment the appropriate line in config.py and launch train.py. 

def generate_interpolation_video(run_id, snapshot=None, grid_size=[1,1], image_shrink=1, image_zoom=1, duration_sec=60.0, smoothing_sec=1.0, mp4=None, mp4_fps=30, mp4_codec='libx265', mp4_bitrate='16M', random_seed=1000, minibatch_size=8):
    network_pkl = misc.locate_network_pkl(run_id, snapshot)
    if mp4 is None:
        mp4 = misc.get_id_string_for_network_pkl(network_pkl) + '-lerp.mp4'
    num_frames = int(np.rint(duration_sec * mp4_fps))
    random_state = np.random.RandomState(random_seed)

    print('Loading network from "%s"...' % network_pkl)
    G, D, Gs = misc.load_network_pkl(run_id, snapshot)

    print('Generating latent vectors...')
    shape = [num_frames, np.prod(grid_size)] + Gs.input_shape[1:] # [frame, image, channel, component]
    all_latents = random_state.randn(*shape).astype(np.float32)
    all_latents = scipy.ndimage.gaussian_filter(all_latents, [smoothing_sec * mp4_fps] + [0] * len(Gs.input_shape), mode='wrap')
    all_latents /= np.sqrt(np.mean(np.square(all_latents)))

    # Frame generation func for moviepy.
    def make_frame(t):
        frame_idx = int(np.clip(np.round(t * mp4_fps), 0, num_frames - 1))
        latents = all_latents[frame_idx]
        labels = np.zeros([latents.shape[0], 0], np.float32)
        images = Gs.run(latents, labels, minibatch_size=minibatch_size, num_gpus=config.num_gpus, out_mul=127.5, out_add=127.5, out_shrink=image_shrink, out_dtype=np.uint8)
        grid = misc.create_image_grid(images, grid_size).transpose(1, 2, 0) # HWC
        if image_zoom > 1:
            grid = scipy.ndimage.zoom(grid, [image_zoom, image_zoom, 1], order=0)
        if grid.shape[2] == 1:
            grid = grid.repeat(3, 2) # grayscale => RGB
        return grid

    # Generate video.
    import moviepy.editor # pip install moviepy
    result_subdir = misc.create_result_subdir(config.result_dir, config.desc)
    moviepy.editor.VideoClip(make_frame, duration=duration_sec).write_videofile(os.path.join(result_subdir, mp4), fps=mp4_fps, codec='libx264', bitrate=mp4_bitrate)
    open(os.path.join(result_subdir, '_done.txt'), 'wt').close()

#----------------------------------------------------------------------------
# Generate MP4 video of training progress for a previous training run.
# To run, uncomment the appropriate line in config.py and launch train.py. 

def predict_gan():
    separate_funcs          = False
    drange_net              = [-1,1]
    drange_viz              = [-1,1]
    image_grid_size         = None
    image_grid_type         = 'default'
    resume_network          = 'pre-trained_weight'
    
    np.random.seed(config.random_seed)

    if resume_network:
        print("Resuming weight from:"+resume_network)
        G = Generator(num_channels=3, resolution=128, label_size=0, **config.G)
        G = load_G_weights(G,resume_network,True)

    print(G.summary())

    # Misc init.

    if image_grid_type == 'default':
        if image_grid_size is None:
            w, h = G.output_shape[1], G.output_shape[2]
            print("w:%d,h:%d"%(w,h))
            image_grid_size = np.clip(int(1920 // w), 3, 16).astype('int'), np.clip(1080 / h, 2, 16).astype('int')
        
        print("image_grid_size:",image_grid_size)
    else:
        raise ValueError('Invalid image_grid_type', image_grid_type)

    result_subdir = misc.create_result_subdir('pre-trained_result', config.run_desc)

    for i in range(1,6):
        snapshot_fake_latents = random_latents(np.prod(image_grid_size), G.input_shape)
        snapshot_fake_images = G.predict_on_batch(snapshot_fake_latents)
        misc.save_image_grid(snapshot_fake_images, os.path.join(result_subdir, 'pre-trained_%03d.png'%i), drange=drange_viz, grid_size=image_grid_size) 

def generate_interpolation_video(run_id, snapshot=None, grid_size=[1,1], image_shrink=1, image_zoom=1, duration_sec=60.0, smoothing_sec=1.0, mp4=None, mp4_fps=30, mp4_codec='libx265', mp4_bitrate='16M', random_seed=1000, minibatch_size=8):
    network_pkl = misc.locate_network_pkl(run_id, snapshot)
    if mp4 is None:
        mp4 = misc.get_id_string_for_network_pkl(network_pkl) + '-lerp.mp4'
    num_frames = int(np.rint(duration_sec * mp4_fps))
    random_state = np.random.RandomState(random_seed)

    print('Loading network from "%s"...' % network_pkl)
    G, D, Gs = misc.load_network_pkl(run_id, snapshot)

    print('Generating latent vectors...')
    shape = [num_frames, np.prod(grid_size)] + Gs.input_shape[1:] # [frame, image, channel, component]
    all_latents = random_state.randn(*shape).astype(np.float32)
    all_latents = scipy.ndimage.gaussian_filter(all_latents, [smoothing_sec * mp4_fps] + [0] * len(Gs.input_shape), mode='wrap')
    all_latents /= np.sqrt(np.mean(np.square(all_latents)))

    # Frame generation func for moviepy.
    def make_frame(t):
        frame_idx = int(np.clip(np.round(t * mp4_fps), 0, num_frames - 1))
        latents = all_latents[frame_idx]
        labels = np.zeros([latents.shape[0], 0], np.float32)
        images = Gs.run(latents, labels, minibatch_size=minibatch_size, num_gpus=config.num_gpus, out_mul=127.5, out_add=127.5, out_shrink=image_shrink, out_dtype=np.uint8)
        grid = misc.create_image_grid(images, grid_size).transpose(1, 2, 0) # HWC
        if image_zoom > 1:
            grid = scipy.ndimage.zoom(grid, [image_zoom, image_zoom, 1], order=0)
        if grid.shape[2] == 1:
            grid = grid.repeat(3, 2) # grayscale => RGB
        return grid

    # Generate video.
    import moviepy.editor # pip install moviepy
    result_subdir = misc.create_result_subdir(config.result_dir, config.desc)
    moviepy.editor.VideoClip(make_frame, duration=duration_sec).write_videofile(os.path.join(result_subdir, mp4), fps=mp4_fps, codec='libx264', bitrate=mp4_bitrate)
    open(os.path.join(result_subdir, '_done.txt'), 'wt').close()

#----------------------------------------------------------------------------
# Generate MP4 video of training progress for a previous training run.
# To run, uncomment the appropriate line in config.py and launch train.py. 

def generate_interpolation_video(run_id, snapshot=None, grid_size=[1,1], image_shrink=1, image_zoom=1, duration_sec=60.0, smoothing_sec=1.0, mp4=None, mp4_fps=30, mp4_codec='libx265', mp4_bitrate='16M', random_seed=1000, minibatch_size=8):
    network_pkl = misc.locate_network_pkl(run_id, snapshot)
    if mp4 is None:
        mp4 = misc.get_id_string_for_network_pkl(network_pkl) + '-lerp.mp4'
    num_frames = int(np.rint(duration_sec * mp4_fps))
    random_state = np.random.RandomState(random_seed)

    print('Loading network from "%s"...' % network_pkl)
    G, D, Gs = misc.load_network_pkl(run_id, snapshot)

    print('Generating latent vectors...')
    shape = [num_frames, np.prod(grid_size)] + Gs.input_shape[1:] # [frame, image, channel, component]
    all_latents = random_state.randn(*shape).astype(np.float32)
    all_latents = scipy.ndimage.gaussian_filter(all_latents, [smoothing_sec * mp4_fps] + [0] * len(Gs.input_shape), mode='wrap')
    all_latents /= np.sqrt(np.mean(np.square(all_latents)))

    # Frame generation func for moviepy.
    def make_frame(t):
        frame_idx = int(np.clip(np.round(t * mp4_fps), 0, num_frames - 1))
        latents = all_latents[frame_idx]
        labels = np.zeros([latents.shape[0], 0], np.float32)
        images = Gs.run(latents, labels, minibatch_size=minibatch_size, num_gpus=config.num_gpus, out_mul=127.5, out_add=127.5, out_shrink=image_shrink, out_dtype=np.uint8)
        grid = misc.create_image_grid(images, grid_size).transpose(1, 2, 0) # HWC
        if image_zoom > 1:
            grid = scipy.ndimage.zoom(grid, [image_zoom, image_zoom, 1], order=0)
        if grid.shape[2] == 1:
            grid = grid.repeat(3, 2) # grayscale => RGB
        return grid

    # Generate video.
    import moviepy.editor # pip install moviepy
    result_subdir = misc.create_result_subdir(config.result_dir, config.desc)
    moviepy.editor.VideoClip(make_frame, duration=duration_sec).write_videofile(os.path.join(result_subdir, mp4), fps=mp4_fps, codec='libx264', bitrate=mp4_bitrate)
    open(os.path.join(result_subdir, '_done.txt'), 'wt').close()

#----------------------------------------------------------------------------
# Generate MP4 video of training progress for a previous training run.
# To run, uncomment the appropriate line in config.py and launch train.py. 

def generate_training_video(run_id, duration_sec=20.0, time_warp=1.5, mp4=None, mp4_fps=30, mp4_codec='libx265', mp4_bitrate='16M'):
    src_result_subdir = misc.locate_result_subdir(run_id)
    if mp4 is None:
        mp4 = os.path.basename(src_result_subdir) + '-train.mp4'

    # Parse log.
    times = []
    snaps = [] # [(png, kimg, lod), ...]
    with open(os.path.join(src_result_subdir, 'log.txt'), 'rt') as log:
        for line in log:
            k = re.search(r'kimg ([\d\.]+) ', line)
            l = re.search(r'lod ([\d\.]+) ', line)
            t = re.search(r'time (\d+d)? *(\d+h)? *(\d+m)? *(\d+s)? ', line)
            if k and l and t:
                k = float(k.group(1))
                l = float(l.group(1))
                t = [int(t.group(i)[:-1]) if t.group(i) else 0 for i in range(1, 5)]
                t = t[0] * 24*60*60 + t[1] * 60*60 + t[2] * 60 + t[3]
                png = os.path.join(src_result_subdir, 'fakes%06d.png' % int(np.floor(k)))
                if os.path.isfile(png):
                    times.append(t)
                    snaps.append((png, k, l))
    assert len(times)

    # Frame generation func for moviepy.
    png_cache = [None, None] # [png, img]
    def make_frame(t):
        wallclock = ((t / duration_sec) ** time_warp) * times[-1]
        png, kimg, lod = snaps[max(bisect.bisect(times, wallclock) - 1, 0)]
        if png_cache[0] == png:
            img = png_cache[1]
        else:
            img = scipy.misc.imread(png)
            while img.shape[1] > 1920 or img.shape[0] > 1080:
                img = img.astype(np.float32).reshape(img.shape[0]//2, 2, img.shape[1]//2, 2, -1).mean(axis=(1,3))
            png_cache[:] = [png, img]
        img = misc.draw_text_label(img, 'lod %.2f' % lod, 16, img.shape[0]-4, alignx=0.0, aligny=1.0)
        img = misc.draw_text_label(img, misc.format_time(int(np.rint(wallclock))), img.shape[1]//2, img.shape[0]-4, alignx=0.5, aligny=1.0)
        img = misc.draw_text_label(img, '%.0f kimg' % kimg, img.shape[1]-16, img.shape[0]-4, alignx=1.0, aligny=1.0)
        return img

    # Generate video.
    import moviepy.editor # pip install moviepy
    result_subdir = misc.create_result_subdir(config.result_dir, config.desc)
    moviepy.editor.VideoClip(make_frame, duration=duration_sec).write_videofile(os.path.join(result_subdir, mp4), fps=mp4_fps, codec='libx264', bitrate=mp4_bitrate)
    open(os.path.join(result_subdir, '_done.txt'), 'wt').close()

#----------------------------------------------------------------------------
# Evaluate one or more metrics for a previous training run.
# To run, uncomment one of the appropriate lines in config.py and launch train.py. 

def generate_training_video(run_id, duration_sec=20.0, time_warp=1.5, mp4=None, mp4_fps=30, mp4_codec='libx265', mp4_bitrate='16M'):
    src_result_subdir = misc.locate_result_subdir(run_id)
    if mp4 is None:
        mp4 = os.path.basename(src_result_subdir) + '-train.mp4'

    # Parse log.
    times = []
    snaps = [] # [(png, kimg, lod), ...]
    with open(os.path.join(src_result_subdir, 'log.txt'), 'rt') as log:
        for line in log:
            k = re.search(r'kimg ([\d\.]+) ', line)
            l = re.search(r'lod ([\d\.]+) ', line)
            t = re.search(r'time (\d+d)? *(\d+h)? *(\d+m)? *(\d+s)? ', line)
            if k and l and t:
                k = float(k.group(1))
                l = float(l.group(1))
                t = [int(t.group(i)[:-1]) if t.group(i) else 0 for i in range(1, 5)]
                t = t[0] * 24*60*60 + t[1] * 60*60 + t[2] * 60 + t[3]
                png = os.path.join(src_result_subdir, 'fakes%06d.png' % int(np.floor(k)))
                if os.path.isfile(png):
                    times.append(t)
                    snaps.append((png, k, l))
    assert len(times)

    # Frame generation func for moviepy.
    png_cache = [None, None] # [png, img]
    def make_frame(t):
        wallclock = ((t / duration_sec) ** time_warp) * times[-1]
        png, kimg, lod = snaps[max(bisect.bisect(times, wallclock) - 1, 0)]
        if png_cache[0] == png:
            img = png_cache[1]
        else:
            img = scipy.misc.imread(png)
            while img.shape[1] > 1920 or img.shape[0] > 1080:
                img = img.astype(np.float32).reshape(img.shape[0]//2, 2, img.shape[1]//2, 2, -1).mean(axis=(1,3))
            png_cache[:] = [png, img]
        img = misc.draw_text_label(img, 'lod %.2f' % lod, 16, img.shape[0]-4, alignx=0.0, aligny=1.0)
        img = misc.draw_text_label(img, misc.format_time(int(np.rint(wallclock))), img.shape[1]//2, img.shape[0]-4, alignx=0.5, aligny=1.0)
        img = misc.draw_text_label(img, '%.0f kimg' % kimg, img.shape[1]-16, img.shape[0]-4, alignx=1.0, aligny=1.0)
        return img

    # Generate video.
    import moviepy.editor # pip install moviepy
    result_subdir = misc.create_result_subdir(config.result_dir, config.desc)
    moviepy.editor.VideoClip(make_frame, duration=duration_sec).write_videofile(os.path.join(result_subdir, mp4), fps=mp4_fps, codec='libx264', bitrate=mp4_bitrate)
    open(os.path.join(result_subdir, '_done.txt'), 'wt').close()

#----------------------------------------------------------------------------
# Evaluate one or more metrics for a previous training run.
# To run, uncomment one of the appropriate lines in config.py and launch train.py. 

def generate_training_video(run_id, duration_sec=20.0, time_warp=1.5, mp4=None, mp4_fps=30, mp4_codec='libx265', mp4_bitrate='16M'):
    src_result_subdir = misc.locate_result_subdir(run_id)
    if mp4 is None:
        mp4 = os.path.basename(src_result_subdir) + '-train.mp4'

    # Parse log.
    times = []
    snaps = [] # [(png, kimg, lod), ...]
    with open(os.path.join(src_result_subdir, 'log.txt'), 'rt') as log:
        for line in log:
            k = re.search(r'kimg ([\d\.]+) ', line)
            l = re.search(r'lod ([\d\.]+) ', line)
            t = re.search(r'time (\d+d)? *(\d+h)? *(\d+m)? *(\d+s)? ', line)
            if k and l and t:
                k = float(k.group(1))
                l = float(l.group(1))
                t = [int(t.group(i)[:-1]) if t.group(i) else 0 for i in range(1, 5)]
                t = t[0] * 24*60*60 + t[1] * 60*60 + t[2] * 60 + t[3]
                png = os.path.join(src_result_subdir, 'fakes%06d.png' % int(np.floor(k)))
                if os.path.isfile(png):
                    times.append(t)
                    snaps.append((png, k, l))
    assert len(times)

    # Frame generation func for moviepy.
    png_cache = [None, None] # [png, img]
    def make_frame(t):
        wallclock = ((t / duration_sec) ** time_warp) * times[-1]
        png, kimg, lod = snaps[max(bisect.bisect(times, wallclock) - 1, 0)]
        if png_cache[0] == png:
            img = png_cache[1]
        else:
            img = scipy.misc.imread(png)
            while img.shape[1] > 1920 or img.shape[0] > 1080:
                img = img.astype(np.float32).reshape(img.shape[0]//2, 2, img.shape[1]//2, 2, -1).mean(axis=(1,3))
            png_cache[:] = [png, img]
        img = misc.draw_text_label(img, 'lod %.2f' % lod, 16, img.shape[0]-4, alignx=0.0, aligny=1.0)
        img = misc.draw_text_label(img, misc.format_time(int(np.rint(wallclock))), img.shape[1]//2, img.shape[0]-4, alignx=0.5, aligny=1.0)
        img = misc.draw_text_label(img, '%.0f kimg' % kimg, img.shape[1]-16, img.shape[0]-4, alignx=1.0, aligny=1.0)
        return img

    # Generate video.
    import moviepy.editor # pip install moviepy
    result_subdir = misc.create_result_subdir(config.result_dir, config.desc)
    moviepy.editor.VideoClip(make_frame, duration=duration_sec).write_videofile(os.path.join(result_subdir, mp4), fps=mp4_fps, codec='libx264', bitrate=mp4_bitrate)
    open(os.path.join(result_subdir, '_done.txt'), 'wt').close()

#----------------------------------------------------------------------------
# Evaluate one or more metrics for a previous training run.
# To run, uncomment one of the appropriate lines in config.py and launch train.py. 

def generate_training_video(run_id, duration_sec=20.0, time_warp=1.5, mp4=None, mp4_fps=30, mp4_codec='libx265', mp4_bitrate='16M'):
    src_result_subdir = misc.locate_result_subdir(run_id)
    if mp4 is None:
        mp4 = os.path.basename(src_result_subdir) + '-train.mp4'

    # Parse log.
    times = []
    snaps = [] # [(png, kimg, lod), ...]
    with open(os.path.join(src_result_subdir, 'log.txt'), 'rt') as log:
        for line in log:
            k = re.search(r'kimg ([\d\.]+) ', line)
            l = re.search(r'lod ([\d\.]+) ', line)
            t = re.search(r'time (\d+d)? *(\d+h)? *(\d+m)? *(\d+s)? ', line)
            if k and l and t:
                k = float(k.group(1))
                l = float(l.group(1))
                t = [int(t.group(i)[:-1]) if t.group(i) else 0 for i in range(1, 5)]
                t = t[0] * 24*60*60 + t[1] * 60*60 + t[2] * 60 + t[3]
                png = os.path.join(src_result_subdir, 'fakes%06d.png' % int(np.floor(k)))
                if os.path.isfile(png):
                    times.append(t)
                    snaps.append((png, k, l))
    assert len(times)

    # Frame generation func for moviepy.
    png_cache = [None, None] # [png, img]
    def make_frame(t):
        wallclock = ((t / duration_sec) ** time_warp) * times[-1]
        png, kimg, lod = snaps[max(bisect.bisect(times, wallclock) - 1, 0)]
        if png_cache[0] == png:
            img = png_cache[1]
        else:
            img = scipy.misc.imread(png)
            while img.shape[1] > 1920 or img.shape[0] > 1080:
                img = img.astype(np.float32).reshape(img.shape[0]//2, 2, img.shape[1]//2, 2, -1).mean(axis=(1,3))
            png_cache[:] = [png, img]
        img = misc.draw_text_label(img, 'lod %.2f' % lod, 16, img.shape[0]-4, alignx=0.0, aligny=1.0)
        img = misc.draw_text_label(img, misc.format_time(int(np.rint(wallclock))), img.shape[1]//2, img.shape[0]-4, alignx=0.5, aligny=1.0)
        img = misc.draw_text_label(img, '%.0f kimg' % kimg, img.shape[1]-16, img.shape[0]-4, alignx=1.0, aligny=1.0)
        return img

    # Generate video.
    import moviepy.editor # pip install moviepy
    result_subdir = misc.create_result_subdir(config.result_dir, config.desc)
    moviepy.editor.VideoClip(make_frame, duration=duration_sec).write_videofile(os.path.join(result_subdir, mp4), fps=mp4_fps, codec='libx264', bitrate=mp4_bitrate)
    open(os.path.join(result_subdir, '_done.txt'), 'wt').close()

#----------------------------------------------------------------------------
# Evaluate one or more metrics for a previous training run.
# To run, uncomment one of the appropriate lines in config.py and launch train.py.