Python config.result_dir() Examples

def locate_result_subdir(run_id_or_result_subdir):
    if isinstance(run_id_or_result_subdir, str) and os.path.isdir(run_id_or_result_subdir):
        return run_id_or_result_subdir

    searchdirs = []
    searchdirs += ['']
    searchdirs += ['results']
    searchdirs += ['networks']

    for searchdir in searchdirs:
        dir = config.result_dir if searchdir == '' else os.path.join(config.result_dir, searchdir)
        dir = os.path.join(dir, str(run_id_or_result_subdir))
        if os.path.isdir(dir):
            return dir
        prefix = '%03d' % run_id_or_result_subdir if isinstance(run_id_or_result_subdir, int) else str(run_id_or_result_subdir)
        dirs = sorted(glob.glob(os.path.join(config.result_dir, searchdir, prefix + '-*')))
        dirs = [dir for dir in dirs if os.path.isdir(dir)]
        if len(dirs) == 1:
            return dirs[0]
    raise IOError('Cannot locate result subdir for run', run_id_or_result_subdir) 

def locate_run_dir(run_id_or_run_dir):
    if isinstance(run_id_or_run_dir, str):
        if os.path.isdir(run_id_or_run_dir):
            return run_id_or_run_dir
        converted = dnnlib.submission.submit.convert_path(run_id_or_run_dir)
        if os.path.isdir(converted):
            return converted

    run_dir_pattern = re.compile('^0*%s-' % str(run_id_or_run_dir))
    for search_dir in ['']:
        full_search_dir = config.result_dir if search_dir == '' else os.path.normpath(os.path.join(config.result_dir, search_dir))
        run_dir = os.path.join(full_search_dir, str(run_id_or_run_dir))
        if os.path.isdir(run_dir):
            return run_dir
        run_dirs = sorted(glob.glob(os.path.join(full_search_dir, '*')))
        run_dirs = [run_dir for run_dir in run_dirs if run_dir_pattern.match(os.path.basename(run_dir))]
        run_dirs = [run_dir for run_dir in run_dirs if os.path.isdir(run_dir)]
        if len(run_dirs) == 1:
            return run_dirs[0]
    raise IOError('Cannot locate result subdir for run', run_id_or_run_dir) 

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 locate_result_subdir(run_id_or_result_subdir):
    if isinstance(run_id_or_result_subdir, str) and os.path.isdir(run_id_or_result_subdir):
        return run_id_or_result_subdir

    searchdirs = []
    searchdirs += ['']
    searchdirs += ['results']
    searchdirs += ['networks']

    for searchdir in searchdirs:
        dir = config.result_dir if searchdir == '' else os.path.join(config.result_dir, searchdir)
        dir = os.path.join(dir, str(run_id_or_result_subdir))
        if os.path.isdir(dir):
            return dir
        prefix = '%03d' % run_id_or_result_subdir if isinstance(run_id_or_result_subdir, int) else str(run_id_or_result_subdir)
        dirs = sorted(glob.glob(os.path.join(config.result_dir, searchdir, prefix + '-*')))
        dirs = [dir for dir in dirs if os.path.isdir(dir)]
        if len(dirs) == 1:
            return dirs[0]
    raise IOError('Cannot locate result subdir for run', run_id_or_result_subdir) 

def locate_run_dir(run_id_or_run_dir):
    if isinstance(run_id_or_run_dir, str):
        if os.path.isdir(run_id_or_run_dir):
            return run_id_or_run_dir
        converted = dnnlib.submission.submit.convert_path(run_id_or_run_dir)
        if os.path.isdir(converted):
            return converted

    run_dir_pattern = re.compile('^0*%s-' % str(run_id_or_run_dir))
    for search_dir in ['']:
        full_search_dir = config.result_dir if search_dir == '' else os.path.normpath(os.path.join(config.result_dir, search_dir))
        run_dir = os.path.join(full_search_dir, str(run_id_or_run_dir))
        if os.path.isdir(run_dir):
            return run_dir
        run_dirs = sorted(glob.glob(os.path.join(full_search_dir, '*')))
        run_dirs = [run_dir for run_dir in run_dirs if run_dir_pattern.match(os.path.basename(run_dir))]
        run_dirs = [run_dir for run_dir in run_dirs if os.path.isdir(run_dir)]
        if len(run_dirs) == 1:
            return run_dirs[0]
    raise IOError('Cannot locate result subdir for run', run_id_or_run_dir) 

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 locate_result_subdir(run_id_or_result_subdir):
    if isinstance(run_id_or_result_subdir, str) and os.path.isdir(run_id_or_result_subdir):
        return run_id_or_result_subdir

    searchdirs = []
    searchdirs += ['']
    searchdirs += ['results']
    searchdirs += ['networks']

    for searchdir in searchdirs:
        dir = config.result_dir if searchdir == '' else os.path.join(config.result_dir, searchdir)
        dir = os.path.join(dir, str(run_id_or_result_subdir))
        if os.path.isdir(dir):
            return dir
        prefix = '%03d' % run_id_or_result_subdir if isinstance(run_id_or_result_subdir, int) else str(run_id_or_result_subdir)
        dirs = sorted(glob.glob(os.path.join(config.result_dir, searchdir, prefix + '-*')))
        dirs = [dir for dir in dirs if os.path.isdir(dir)]
        if len(dirs) == 1:
            return dirs[0]
    raise IOError('Cannot locate result subdir for run', run_id_or_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 locate_result_subdir(run_id):
    if isinstance(run_id, str) and os.path.isdir(run_id):
        return run_id

    searchdirs = []
    searchdirs += ['.']
    searchdirs += ['results']
    searchdirs += ['networks']

    import config
    for searchdir in searchdirs:
        dir = os.path.join(config.result_dir, searchdir, str(run_id))
        if os.path.isdir(dir):
            return dir
        dirs = glob.glob(os.path.join(config.result_dir, searchdir, '%s-*' % str(run_id)))
        if len(dirs) == 1 and os.path.isdir(dirs[0]):
            return dirs[0]
    raise IOError('Cannot locate result subdir for run', run_id) 

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 locate_result_subdir(run_id_or_result_subdir):
    if isinstance(run_id_or_result_subdir, str) and os.path.isdir(run_id_or_result_subdir):
        return run_id_or_result_subdir

    searchdirs = []
    searchdirs += ['']
    searchdirs += ['results']
    searchdirs += ['networks']

    for searchdir in searchdirs:
        dir = config.result_dir if searchdir == '' else os.path.join(config.result_dir, searchdir)
        dir = os.path.join(dir, str(run_id_or_result_subdir))
        if os.path.isdir(dir):
            return dir
        prefix = '%03d' % run_id_or_result_subdir if isinstance(run_id_or_result_subdir, int) else str(run_id_or_result_subdir)
        dirs = sorted(glob.glob(os.path.join(config.result_dir, searchdir, prefix + '-*')))
        dirs = [dir for dir in dirs if os.path.isdir(dir)]
        if len(dirs) == 1:
            return dirs[0]
    raise IOError('Cannot locate result subdir for run', run_id_or_result_subdir) 

def main():
    submit_config = dnnlib.SubmitConfig()

    # Which metrics to evaluate?
    metrics = []
    metrics += [metric_base.fid50k]
    #metrics += [metric_base.ppl_zfull]
    #metrics += [metric_base.ppl_wfull]
    #metrics += [metric_base.ppl_zend]
    #metrics += [metric_base.ppl_wend]
    #metrics += [metric_base.ls]
    #metrics += [metric_base.dummy]

    # Which networks to evaluate them on?
    tasks = []
    tasks += [EasyDict(run_func_name='run_metrics.run_pickle', network_pkl='https://drive.google.com/uc?id=1MEGjdvVpUsu1jB4zrXZN7Y4kBBOzizDQ', dataset_args=EasyDict(tfrecord_dir='ffhq', shuffle_mb=0), mirror_augment=True)] # karras2019stylegan-ffhq-1024x1024.pkl
    #tasks += [EasyDict(run_func_name='run_metrics.run_snapshot', run_id=100, snapshot=25000)]
    #tasks += [EasyDict(run_func_name='run_metrics.run_all_snapshots', run_id=100)]

    # How many GPUs to use?
    submit_config.num_gpus = 1
    #submit_config.num_gpus = 2
    #submit_config.num_gpus = 4
    #submit_config.num_gpus = 8

    # Execute.
    submit_config.run_dir_root = dnnlib.submission.submit.get_template_from_path(config.result_dir)
    submit_config.run_dir_ignore += config.run_dir_ignore
    for task in tasks:
        for metric in metrics:
            submit_config.run_desc = '%s-%s' % (task.run_func_name, metric.name)
            if task.run_func_name.endswith('run_snapshot'):
                submit_config.run_desc += '-%s-%s' % (task.run_id, task.snapshot)
            if task.run_func_name.endswith('run_all_snapshots'):
                submit_config.run_desc += '-%s' % task.run_id
            submit_config.run_desc += '-%dgpu' % submit_config.num_gpus
            dnnlib.submit_run(submit_config, metric_args=metric, **task)

#---------------------------------------------------------------------------- 

def create_result_subdir(result_dir, 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, desc))
        try:
            os.makedirs(result_subdir)
            break
        except OSError:
            if os.path.isdir(result_subdir):
                continue
            raise

    print("Saving results to", result_subdir)
    set_output_log_file(os.path.join(result_subdir, 'log.txt'))

    # Export config.
    try:
        with open(os.path.join(result_subdir, 'config.txt'), 'wt') as fout:
            for k, v in sorted(config.__dict__.items()):
                if not k.startswith('_'):
                    fout.write("%s = %s\n" % (k, str(v)))
    except:
        pass

    return result_subdir 

def main():
    # Initialize TensorFlow.
    tflib.init_tf()

    # Load pre-trained network.
    url = 'https://drive.google.com/uc?id=1MEGjdvVpUsu1jB4zrXZN7Y4kBBOzizDQ' # karras2019stylegan-ffhq-1024x1024.pkl
    with dnnlib.util.open_url(url, cache_dir=config.cache_dir) as f:
        _G, _D, Gs = pickle.load(f)
        # _G = Instantaneous snapshot of the generator. Mainly useful for resuming a previous training run.
        # _D = Instantaneous snapshot of the discriminator. Mainly useful for resuming a previous training run.
        # Gs = Long-term average of the generator. Yields higher-quality results than the instantaneous snapshot.

    # Print network details.
    Gs.print_layers()

    # Pick latent vector.
    rnd = np.random.RandomState(5)
    latents = rnd.randn(1, Gs.input_shape[1])

    # Generate image.
    fmt = dict(func=tflib.convert_images_to_uint8, nchw_to_nhwc=True)
    images = Gs.run(latents, None, truncation_psi=0.7, randomize_noise=True, output_transform=fmt)

    # Save image.
    os.makedirs(config.result_dir, exist_ok=True)
    png_filename = os.path.join(config.result_dir, 'example.png')
    PIL.Image.fromarray(images[0], 'RGB').save(png_filename) 

def main():
    submit_config = dnnlib.SubmitConfig()

    # Which metrics to evaluate?
    metrics = []
    metrics += [metric_base.fid50k]
    #metrics += [metric_base.ppl_zfull]
    #metrics += [metric_base.ppl_wfull]
    #metrics += [metric_base.ppl_zend]
    #metrics += [metric_base.ppl_wend]
    #metrics += [metric_base.ls]
    #metrics += [metric_base.dummy]

    # Which networks to evaluate them on?
    tasks = []
    tasks += [EasyDict(run_func_name='run_metrics.run_pickle', network_pkl='https://drive.google.com/uc?id=1MEGjdvVpUsu1jB4zrXZN7Y4kBBOzizDQ', dataset_args=EasyDict(tfrecord_dir='ffhq', shuffle_mb=0), mirror_augment=True)] # karras2019stylegan-ffhq-1024x1024.pkl
    #tasks += [EasyDict(run_func_name='run_metrics.run_snapshot', run_id=100, snapshot=25000)]
    #tasks += [EasyDict(run_func_name='run_metrics.run_all_snapshots', run_id=100)]

    # How many GPUs to use?
    submit_config.num_gpus = 1
    #submit_config.num_gpus = 2
    #submit_config.num_gpus = 4
    #submit_config.num_gpus = 8

    # Execute.
    submit_config.run_dir_root = dnnlib.submission.submit.get_template_from_path(config.result_dir)
    submit_config.run_dir_ignore += config.run_dir_ignore
    for task in tasks:
        for metric in metrics:
            submit_config.run_desc = '%s-%s' % (task.run_func_name, metric.name)
            if task.run_func_name.endswith('run_snapshot'):
                submit_config.run_desc += '-%s-%s' % (task.run_id, task.snapshot)
            if task.run_func_name.endswith('run_all_snapshots'):
                submit_config.run_desc += '-%s' % task.run_id
            submit_config.run_desc += '-%dgpu' % submit_config.num_gpus
            dnnlib.submit_run(submit_config, metric_args=metric, **task)

#---------------------------------------------------------------------------- 

def main():
    tflib.init_tf()
    os.makedirs(config.result_dir, exist_ok=True)
    draw_uncurated_result_figure(os.path.join(config.result_dir, 'figure02-uncurated-ffhq.png'), load_Gs(url_ffhq), cx=0, cy=0, cw=1024, ch=1024, rows=3, lods=[0,1,2,2,3,3], seed=5)
    draw_style_mixing_figure(os.path.join(config.result_dir, 'figure03-style-mixing.png'), load_Gs(url_ffhq), w=1024, h=1024, src_seeds=[639,701,687,615,2268], dst_seeds=[888,829,1898,1733,1614,845], style_ranges=[range(0,4)]*3+[range(4,8)]*2+[range(8,18)])
    draw_noise_detail_figure(os.path.join(config.result_dir, 'figure04-noise-detail.png'), load_Gs(url_ffhq), w=1024, h=1024, num_samples=100, seeds=[1157,1012])
    draw_noise_components_figure(os.path.join(config.result_dir, 'figure05-noise-components.png'), load_Gs(url_ffhq), w=1024, h=1024, seeds=[1967,1555], noise_ranges=[range(0, 18), range(0, 0), range(8, 18), range(0, 8)], flips=[1])
    draw_truncation_trick_figure(os.path.join(config.result_dir, 'figure08-truncation-trick.png'), load_Gs(url_ffhq), w=1024, h=1024, seeds=[91,388], psis=[1, 0.7, 0.5, 0, -0.5, -1])
    draw_uncurated_result_figure(os.path.join(config.result_dir, 'figure10-uncurated-bedrooms.png'), load_Gs(url_bedrooms), cx=0, cy=0, cw=256, ch=256, rows=5, lods=[0,0,1,1,2,2,2], seed=0)
    draw_uncurated_result_figure(os.path.join(config.result_dir, 'figure11-uncurated-cars.png'), load_Gs(url_cars), cx=0, cy=64, cw=512, ch=384, rows=4, lods=[0,1,2,2,3,3], seed=2)
    draw_uncurated_result_figure(os.path.join(config.result_dir, 'figure12-uncurated-cats.png'), load_Gs(url_cats), cx=0, cy=0, cw=256, ch=256, rows=5, lods=[0,0,1,1,2,2,2], seed=1)

#---------------------------------------------------------------------------- 

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 create_result_subdir(result_dir, 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, desc))
        try:
            os.makedirs(result_subdir)
            break
        except OSError:
            if os.path.isdir(result_subdir):
                continue
            raise

    print("Saving results to", result_subdir)
    set_output_log_file(os.path.join(result_subdir, 'log.txt'))

    # Export config.
    try:
        with open(os.path.join(result_subdir, 'config.txt'), 'wt') as fout:
            for k, v in sorted(config.__dict__.items()):
                if not k.startswith('_'):
                    fout.write("%s = %s\n" % (k, str(v)))
    except:
        pass

    return result_subdir 

def __init__(self, num_images, image_shape, image_dtype, minibatch_size):
        import config
        self.network_dir = os.path.join(config.result_dir, '_inception_fid')
        self.network_file = check_or_download_inception(self.network_dir)
        self.sess = tf.get_default_session()
        create_inception_graph(self.network_file) 

def __init__(self, num_images, image_shape, image_dtype, minibatch_size):
        import config
        globals()['MODEL_DIR'] = os.path.join(config.result_dir, '_inception')
        self.sess = tf.get_default_session()
        _init_inception() 

def main():
    # Initialize TensorFlow.
    tflib.init_tf()

    # Load pre-trained network.
    url = 'https://drive.google.com/uc?id=1MEGjdvVpUsu1jB4zrXZN7Y4kBBOzizDQ' # karras2019stylegan-ffhq-1024x1024.pkl
    with dnnlib.util.open_url(url, cache_dir=config.cache_dir) as f:
        _G, _D, Gs = pickle.load(f)
        # _G = Instantaneous snapshot of the generator. Mainly useful for resuming a previous training run.
        # _D = Instantaneous snapshot of the discriminator. Mainly useful for resuming a previous training run.
        # Gs = Long-term average of the generator. Yields higher-quality results than the instantaneous snapshot.

    # Print network details.
    Gs.print_layers()

    # Pick latent vector.
    rnd = np.random.RandomState(5)
    latents = rnd.randn(1, Gs.input_shape[1])

    # Generate image.
    fmt = dict(func=tflib.convert_images_to_uint8, nchw_to_nhwc=True)
    images = Gs.run(latents, None, truncation_psi=0.7, randomize_noise=True, output_transform=fmt)

    # Save image.
    os.makedirs(config.result_dir, exist_ok=True)
    png_filename = os.path.join(config.result_dir, 'example.png')
    PIL.Image.fromarray(images[0], 'RGB').save(png_filename) 

def main():
    tflib.init_tf()
    os.makedirs(config.result_dir, exist_ok=True)
    draw_uncurated_result_figure(os.path.join(config.result_dir, 'figure02-uncurated-ffhq.png'), load_Gs(url_ffhq), cx=0, cy=0, cw=1024, ch=1024, rows=3, lods=[0,1,2,2,3,3], seed=5)
    draw_style_mixing_figure(os.path.join(config.result_dir, 'figure03-style-mixing.png'), load_Gs(url_ffhq), w=1024, h=1024, src_seeds=[639,701,687,615,2268], dst_seeds=[888,829,1898,1733,1614,845], style_ranges=[range(0,4)]*3+[range(4,8)]*2+[range(8,18)])
    draw_noise_detail_figure(os.path.join(config.result_dir, 'figure04-noise-detail.png'), load_Gs(url_ffhq), w=1024, h=1024, num_samples=100, seeds=[1157,1012])
    draw_noise_components_figure(os.path.join(config.result_dir, 'figure05-noise-components.png'), load_Gs(url_ffhq), w=1024, h=1024, seeds=[1967,1555], noise_ranges=[range(0, 18), range(0, 0), range(8, 18), range(0, 8)], flips=[1])
    draw_truncation_trick_figure(os.path.join(config.result_dir, 'figure08-truncation-trick.png'), load_Gs(url_ffhq), w=1024, h=1024, seeds=[91,388], psis=[1, 0.7, 0.5, 0, -0.5, -1])
    draw_uncurated_result_figure(os.path.join(config.result_dir, 'figure10-uncurated-bedrooms.png'), load_Gs(url_bedrooms), cx=0, cy=0, cw=256, ch=256, rows=5, lods=[0,0,1,1,2,2,2], seed=0)
    draw_uncurated_result_figure(os.path.join(config.result_dir, 'figure11-uncurated-cars.png'), load_Gs(url_cars), cx=0, cy=64, cw=512, ch=384, rows=4, lods=[0,1,2,2,3,3], seed=2)
    draw_uncurated_result_figure(os.path.join(config.result_dir, 'figure12-uncurated-cats.png'), load_Gs(url_cats), cx=0, cy=0, cw=256, ch=256, rows=5, lods=[0,0,1,1,2,2,2], seed=1)

#---------------------------------------------------------------------------- 

def experiment_tcn():

    from config import result_dir, split_num, tcn_run_num, dataset_name
    
    if dataset_name in ['JIGSAWS_K', 'JIGSAWS_N']:
        feature_types = ['sensor']
    elif dataset_name == 'GTEA':
        feature_types = ['visual']
    else:
        feature_types = ['sensor', 'visual']

    ####################################################

    for feature_type in feature_types:

        tcn_cmd = 'python3 tcn_main.py --feature_type {}'.format(feature_type)
        
        Popen(tcn_cmd, shell=True).wait()
        #os.system(tcn_cmd)

        # Get Averaged Results: TCN
        template = 'tcn_result_{}_run_{}.npy'
    
        tcn_result = np.zeros((tcn_run_num, split_num, 6))
        for tcn_run_idx in range(1, 1 + tcn_run_num):
            run_result_file = template.format(feature_type, tcn_run_idx)
            run_result_file = os.path.join(result_dir, run_result_file)
            tcn_result[tcn_run_idx-1,:,:] = np.load(run_result_file)
            os.remove(run_result_file)

        tcn_result_file = 'tcn_avg_result_{}.npy'.format(feature_type)
        tcn_result_file = os.path.join(result_dir, tcn_result_file)
        #np.save(tcn_result_file, tcn_result.mean(0).mean(0))
        np.save(tcn_result_file, tcn_result) 

def create_result_subdir(result_dir, 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, desc))
        try:
            os.makedirs(result_subdir)
            break
        except OSError:
            if os.path.isdir(result_subdir):
                continue
            raise

    print("Saving results to", result_subdir)
    set_output_log_file(os.path.join(result_subdir, 'log.txt'))

    # Export config.
    try:
        with open(os.path.join(result_subdir, 'config.txt'), 'wt') as fout:
            for k, v in sorted(config.__dict__.items()):
                if not k.startswith('_'):
                    fout.write("%s = %s\n" % (k, str(v)))
    except:
        pass

    return result_subdir 

def __init__(self, num_images, image_shape, image_dtype, minibatch_size):
        import config
        self.network_dir = os.path.join(config.result_dir, '_inception_fid')
        self.network_file = check_or_download_inception(self.network_dir)
        self.sess = tf.get_default_session()
        create_inception_graph(self.network_file) 

def __init__(self, num_images, image_shape, image_dtype, minibatch_size):
        import config
        globals()['MODEL_DIR'] = os.path.join(config.result_dir, '_inception')
        self.sess = tf.get_default_session()
        _init_inception() 

def __init__(self, num_images, image_shape, image_dtype, minibatch_size):
        import config
        globals()['MODEL_DIR'] = os.path.join(config.result_dir, '_inception')
        self.sess = tf.get_default_session()
        _init_inception() 

def __init__(self, num_images, image_shape, image_dtype, minibatch_size):
        import config
        self.network_dir = os.path.join(config.result_dir, '_inception_fid')
        self.network_file = check_or_download_inception(self.network_dir)
        self.sess = tf.get_default_session()
        create_inception_graph(self.network_file) 

def create_result_subdir(result_dir, 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, desc))
        try:
            os.makedirs(result_subdir)
            break
        except OSError:
            if os.path.isdir(result_subdir):
                continue
            raise

    print("Saving results to", result_subdir)
    set_output_log_file(os.path.join(result_subdir, 'log.txt'))

    # Export config.
    try:
        with open(os.path.join(result_subdir, 'config.txt'), 'wt') as fout:
            for k, v in sorted(config.__dict__.items()):
                if not k.startswith('_'):
                    fout.write("%s = %s\n" % (k, str(v)))
    except:
        pass

    return result_subdir