PS D:\Code\BachKhoa\ai-personal-trainer\Custom-MoViNet> python train.py --data data --batch_size 8 --num_frames 32 --resolution 172 --num_epochs 100 --pre_ckpt weights/modelA5_statedict_v3_folder/ --save_ckpt checkpoints/ckpt-1 --export my_model/model_MoViNet_A5 --model_id a5 --save model_MoViNet_A5.tflite --float 16
2024-03-13 10:46:27.204046: I tensorflow/core/util/port.cc:113] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable TF_ENABLE_ONEDNN_OPTS=0.
2024-03-13 10:46:27.929813: I tensorflow/core/util/port.cc:113] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable TF_ENABLE_ONEDNN_OPTS=0.
Traceback (most recent call last):
File "D:\Code\BachKhoa\ai-personal-trainer\Custom-MoViNet\train.py", line 3, in
from official.projects.movinet.modeling import movinet
ModuleNotFoundError: No module named 'official.projects'
PS D:\Code\BachKhoa\ai-personal-trainer\Custom-MoViNet>