Merge branch 'main' into tijmen-add-encode-decode-example

Author: Timen

README.md

@@ -38,8 +38,9 @@ python3 generate.py --gpt-ckpt-path model_weights/gpt.safetensors --shape-ckpt-p
 The output will be an `.obj` file saved in the specified `output` directory.
 
 If you want to render a turntable gif of the mesh, you can use the `--render-gif` flag, which will render a turntable gif of the mesh
-and save it as `turntable.gif` in the specified `output` directory. Note that you must have blender installed and in your path to render the turntable gif.
+and save it as `turntable.gif` in the specified `output` directory.
 
+> **Note**: You must have Blender installed and available in your system's PATH to render the turntable GIF. You can download it from [Blender's official website](https://www.blender.org/). Ensure that the Blender executable is accessible from the command line.
 
 ### Shaple tokenization and de-tokenization
 To tokenize a 3D shape into token indices and reconstruct it back, you can use the following command:
@@ -48,4 +49,4 @@ To tokenize a 3D shape into token indices and reconstruct it back, you can use t
 python3 vq_vae_encode_decode.py --shape-ckpt-path model_weights/shape.safetensors --mesh-path ./outputs/output.obj
 ```
 
-This will process the `.obj` file located at `./outputs/output.obj` and prints the tokenized representation as well as exports the mesh reconstructed from the token indices.
+This will process the `.obj` file located at `./outputs/output.obj` and prints the tokenized representation as well as exports the mesh reconstructed from the token indices.

configs/open_model.yaml

@@ -28,7 +28,6 @@ shape_model:
   num_encoder_layers: 13
   encoder_cross_attention_levels: [0, 2, 4, 8] 
   num_decoder_layers: 24
-  dropout: 0.0
   num_codes: 16384
 
 text_model_pretrained_model_name_or_path: "openai/clip-vit-large-patch14"