How can I run this on a standalone B&W picture? about spade HOT 5 OPEN

I am not sure what you exactly mean.

Do you mean coloring black-and-white images like this?

Or do you mean creating realistic photos from simple greyscale outline, like [this][(https://cg.cs.tsinghua.edu.cn/montage/main.htm) or edges2cats section of this?

Both are somewhat different from the scope of SPADE. To achieve any of these methods, you will need to modify the code a bit. Most likely, you will want to remove the code block that creates a one-hot vector from semantic class label. You will want to just use the unmodified B&W input.

from spade.

Could you please help me with my problem?

I'm fairly new to Deep Learning, and I'm trying to solve a colorization problem.
Now I'm using AI Notebooks at Google Cloud, and I have some small images and their BW sketch versions.

I guess there are no instance maps in this case, and I deleted the one-hot vector block like taesungp said in the post above. However, when I try to train my model, it gives this output:

train.py --name experiment --dataset_mode custom --label_dir /home/jupyter/SPADE/labels/ --image_dir /home/jupyter/SPADE/images/
dataset [CustomDataset] of size 541 was created
Network [SPADEGenerator] was created. Total number of parameters: 92.4 million. To see the architecture, do print(network).
Network [MultiscaleDiscriminator] was created. Total number of parameters: 1.4 million. To see the architecture, do print(network).
create web directory ./checkpoints/experiment/web...
Traceback (most recent call last):
File "train.py", line 34, in
for i, data_i in enumerate(dataloader, start=iter_counter.epoch_iter):
File "/opt/anaconda3/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 615, in next
batch = self.collate_fn([self.dataset[i] for i in indices])
File "/opt/anaconda3/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 615, in
batch = self.collate_fn([self.dataset[i] for i in indices])
File "/home/jupyter/SPADE/data/pix2pix_dataset.py", line 81, in getitem
instance_path = self.instance_paths[index]
IndexError: list index out of range

The code tries to go through the indices of instance_paths, but I used the "--no_instance" option, and I shouldn't even have them. So I have an empty list of instance paths, and I can't enumerate them.

Can you see what's wrong with my code and correct it?

! python -m data.custom_dataset --name experiment --dataset_mode custom --label_dir /home/jupyter/SPADE/labels/ --image_dir /home/jupyter/SPADE/images/ --no_instance

! python train.py --name experiment --dataset_mode custom --label_dir /home/jupyter/SPADE/labels/ --image_dir /home/jupyter/SPADE/images/ 

Thanks in advance!

from spade.

I guess what I meant was using SPADE to generate art, just like in the youtube video. This is for a class to use Machine Learning to generate art. My input image is here: https://drive.google.com/file/d/1yyNBhciG8O-xkA9LELDx0iCOS1Pd1fJR/view?usp=sharing

What steps would I have to follow to create a landscape using the image above? I tried turning this image into B&W and put it in the datasets/coco_stuff/val_label and datasets/coco_stuff/val_inst directories, but got the following error:

RuntimeError: Invalid index in scatter at /Users/soumith/b101_2/2019_02_08/wheel_build_dirs/wheel_3.6/pytorch/aten/src/TH/generic/THTensorEvenMoreMath.cpp:546

Any help would be greatly appreciated. Thanks a ton!

from spade.

@MalharJ I think that trouble in your mask - it has labels equal 190 and 254, although in COCO-stuff number of input labels equal 182 and SPADE can't create one-hot vector from your mask.

from spade.

Could you please help me with my problem?

I'm fairly new to Deep Learning, and I'm trying to solve a colorization problem. Now I'm using AI Notebooks at Google Cloud, and I have some small images and their BW sketch versions.

I guess there are no instance maps in this case, and I deleted the one-hot vector block like taesungp said in the post above. However, when I try to train my model, it gives this output:

train.py --name experiment --dataset_mode custom --label_dir /home/jupyter/SPADE/labels/ --image_dir /home/jupyter/SPADE/images/
dataset [CustomDataset] of size 541 was created
Network [SPADEGenerator] was created. Total number of parameters: 92.4 million. To see the architecture, do print(network).
Network [MultiscaleDiscriminator] was created. Total number of parameters: 1.4 million. To see the architecture, do print(network).
create web directory ./checkpoints/experiment/web...
Traceback (most recent call last):
File "train.py", line 34, in
for i, data_i in enumerate(dataloader, start=iter_counter.epoch_iter):
File "/opt/anaconda3/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 615, in next
batch = self.collate_fn([self.dataset[i] for i in indices])
File "/opt/anaconda3/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 615, in
batch = self.collate_fn([self.dataset[i] for i in indices])
File "/home/jupyter/SPADE/data/pix2pix_dataset.py", line 81, in getitem
instance_path = self.instance_paths[index]
IndexError: list index out of range

The code tries to go through the indices of instance_paths, but I used the "--no_instance" option, and I shouldn't even have them. So I have an empty list of instance paths, and I can't enumerate them.

Can you see what's wrong with my code and correct it?

! python -m data.custom_dataset --name experiment --dataset_mode custom --label_dir /home/jupyter/SPADE/labels/ --image_dir /home/jupyter/SPADE/images/ --no_instance

! python train.py --name experiment --dataset_mode custom --label_dir /home/jupyter/SPADE/labels/ --image_dir /home/jupyter/SPADE/images/ 

Thanks in advance!

Hi @nkaufie , did you solve the problem? I got the same situation with you. I was trying to do RGB2RGB translated task, but struggling with this error. Any helps I will very appreciate it ! Thanks

from spade.