cvlab-kaist / GaussianTalker

Official implementation of “GaussianTalker: Real-Time High-Fidelity Talking Head Synthesis with Audio-Driven 3D Gaussian Splatting” by Kyusun Cho, Joungbin Lee, Heeji Yoon, Yeobin Hong, Jaehoon Ko, Sangjun Ahn and Seungryong Kim
Other
264 stars 32 forks source link

The location of trained model #28

Closed justin4ai closed 2 months ago

justin4ai commented 3 months ago

Hello, thank you for providing such a great project. I finished training session as shown below:

image

However, I cannot find the checkpoint nowhere in my folders.

image

No outputfolder has been created. I will be so glad if you help me out with this!

joungbinlee commented 2 months ago

Thank you for using our model! The model will probably be saved in the directory you specified with the following training command:

python train.py -s ${YOUR_DATASET_DIR}/${DATASET_NAME} --model_path ${YOUR_MODEL_DIR} --configs arguments/64_dim_1_transformer.py

Please check that it is saved in the ${YOUR_MODEL_DIR} you specified in the code. Thank you.

justin4ai commented 2 months ago

Oh yeah there we go. I thought the ,,model'' meant certain checkpoint, not a folder. Then it makes sense. Appreciate your great work!

Cheers, Junyeong Ahn

AMEERAZAM08 commented 2 months ago

@joungbinlee how the resuts. ?