OneSixth

@tianchunzhi Hello, I do not recommend you to use this repo. It is too old. It uses tensorflow-gpu-1.10 and tensorlayer-1.91 version.

The DCGAN's loss should be used in the original article. But when I used DCGAN's loss, I found that the generation ability was not good, so I switched to BEGAN's...

You can try to avoid this by downgrading the tensorlayer version to 1.91. Or, according to the error prompt, give a new name to the error layer. Look here https://github.com/tensorlayer/tensorlayer/blob/TensorLayer-1.x/tensorlayer/layers/inputs.py#L70.

The official fix is too slow, I made a fix version myself. You can install it using the following command. v0.12.3. I conducted a simple test and found no abnormalities....

The official fix of fairseq is too slow. I have created a fixed version of fairseq that works properly on Python 3.11. You can try this If you need. ```...

@Java-S12138 这个软件现在还能工作，那就稍微更新下，让它更好用把。

@UuuNyaa We can divide our work to make us more efficient.. For the material library, I have a relatively clear implementation idea, and in the next few days I can...

@nagadomi I think the material library properties can be placed in mmd_tools or mmd_uuunya_tool. But I don't think it should be used as a standalone plugin, which I think might...

@UuuNyaa @nagadomi Hello, I have preliminarily finished the material library base feature. Also added material_morph support for obj_mat. The code is here: https://github.com/One-sixth/blender_mmd_tools/tree/add_material_library_feature Some idea has changed. It is now...

@UuuNyaa Hello, I have completed the custom_node features. Here's the code. https://github.com/One-sixth/blender_mmd_tools/tree/add_custom_node_features I have organized the code as mmd_tools, which should be easy to modify and move elsewhere. This is...