use SVG files as input

[SanketDhuri]

I aim to input SVG files representing the top, bottom, and side orthographic projections of an object. I want to transform these SVG files into a data format suitable for model input data, to reconstruct 3d model

can you give me code reference to do so

[bertjiazheng]

Please refer to parse_info.py to convert the SVGs into the desired format.

[SanketDhuri]

and how to create this infos['planks'] and infos['attach'] data for this line of code coords = np.array(infos['planks']) / args.scale since this coords and attach data is needed in json file

considering this 'f', 't', 's' view are new svg images

[bertjiazheng]

planks and attach are the expected outputs. You may ignore them if you do not have the ground truth. However, you need to modify the dataset to exclude ground truth during inference.

[SanketDhuri]

planks and attach are the expected outputs. You may ignore them if you do not have the ground truth. However, you need to modify the dataset to exclude ground truth during inference.

thanks @bertjiazheng it worked