first-order-model-tf
first-order-model-tf copied to clipboard
TensorFlow port of first-order motion model. TF Lite and TF.js compatible, supports the original's checkpoints and implements in-graph kp processing, but inference only (no training).
What do I need to do to generate a larger and different size resolution? from 256x256 To 768x576?
Hello! Our static bug checker has found a performance issue in blob/main/run.py and blob/main/animate.py: [`animate`](https://github.com/lshug/first-order-model-tf/blob/f19d4278178ecc6cba49592d5ff6b653b3387bc4/run.py#L81) is repeatedly called in a for loop, but there are tf.function decorated functions [`slice_driving`](https://github.com/lshug/first-order-model-tf/blob/f19d4278178ecc6cba49592d5ff6b653b3387bc4/animate.py#L31) and...
Hello author, based on the information you provided me above and python code, I have drawn a flowchart to streamline the process of models inference. Could you please help me...