How to get result images have same names suffix as testA?

[adnan0819]

Hi,

Firstly thank you very much for such a nice implementation. My question is related to CycleGan:

1. I have 500 files in /testA/ named such as 1.jpg, 2.jpg, ... , 500.jpg
2. I want to have the results to have outputs say 1_real.png , 1_fake.png, ..., 500_real.png, 500_fake.png - that refers to the original 1.jpg, .... , 500.jpg (in sequence).

Right now it comes as randomized even when number of test images is changed to 500 instead of the default.

Any tips on how to achieve this? I think it should be a simple change in some lines.

Thanks.

PS. As an aside (though not important), can the jpg format preserved and not changed to png?

[adnan0819]

Nevermind the first part. The arguments --batch_size 1 --serial_batches made it happen.

Still, any way to have outputs as jpg's (the same format as the inputs)?

[ayushanand18]

Hi @adnan0819 ! You can change the extension of the image file being saved in the 'save_image' function defined at /util/[visualizer.py] (https://github.com/junyanz/pytorch-CycleGAN-and-pix2pix/tree/003efc4c8819de47ff11b5a0af7ba09aee7f5fc1/util/visualizer.py)

def save_images(webpage, visuals, image_path, aspect_ratio=1.0, width=256, use_wandb=False):

"""Save images to the disk.
Parameters:
    webpage (the HTML class) -- the HTML webpage class that stores these imaegs (see html.py for more details)
    visuals (OrderedDict)    -- an ordered dictionary that stores (name, images (either tensor or numpy) ) pairs
    image_path (str)         -- the string is used to create image paths
    aspect_ratio (float)     -- the aspect ratio of saved images
    width (int)              -- the images will be resized to width x width
``This function will save images stored in 'visuals' to the HTML file specified by 'webpage'.
"""``

image_dir = webpage.get_image_dir()
short_path = ntpath.basename(image_path[0])
name = os.path.splitext(short_path)[0]
webpage.add_header(name)
ims, txts, links = [], [], []
ims_dict = {}
for label, im_data in visuals.items():
    im = util.tensor2im(im_data)

#Look here -----------------------------------------
    image_name = '%s_%s.png' % (name, label)     # Here the image name is being defined you can change it what way you want to.
#Change here --------------------------------------
    save_path = os.path.join(image_dir, image_name)
    util.save_image(im, save_path, aspect_ratio=aspect_ratio)
    ims.append(image_name)
    txts.append(label)
    links.append(image_name)
    if use_wandb:
        ims_dict[label] = wandb.Image(im)
webpage.add_images(ims, txts, links, width=width)
if use_wandb:
    wandb.log(ims_dict)``

Hope it helps!

[junyanz]

You can also change this line in the test.py.