-
Notifications
You must be signed in to change notification settings - Fork 5
Description
Hi! @StarCycle
First of all, I would like to express my sincere gratitude for your excellent work.
I downloaded the pre-trained model that only uses Ego4D videos based on the following content from the readme.md of GR-MG.
2. Pretrain Multi-modal Goal Conditioned Policy
We use the method described in GR-1 and pretrain our policy with Ego4D videos. You can download the pretrained model checkpoint here. You can also pretrain the policy yourself using the scripts we provide. Before doing this, you'll need to download the Ego4D dataset.
I attempted to train based on this pre-trained model. I modified the GR1-Training/configs.json file as follows:
"bytedance_ckpt_path": "/data3/xuyuxuan/pretrained.pt",
"load_bytedance_ckpt": true,
However, when I started the training, I encountered the following error message:
warnings.warn(
load /data3/xuyuxuan/pretrained.pt
missing:
['transformer.wte.weight', 'transformer.wpe.weight', 'transformer.h.0.attn.bias', 'transformer.h.0.attn.masked_bias', 'transformer.h.1.attn.bias', 'transformer.h.1.attn.masked_bias', 'transformer.h.2.attn.bias', 'transformer.h.2.attn.masked_bias', 'transformer.h.3.attn.bias',
...
'model_clip.transformer.resblocks.11.mlp.c_fc.weight', 'model_clip.transformer.resblocks.11.mlp.c_fc.bias', 'model_clip.transformer.resblocks.11.mlp.c_proj.weight', 'model_clip.transformer.resblocks.11.mlp.c_proj.bias', 'pred_act_mlps.0.weight', 'pred_act_mlps.0.bias', 'pred_act_mlps.1.weight', 'pred_act_mlps.1.bias', 'pred_arm_act.weight', 'pred_arm_act.bias', 'pred_gripper_act.weight', 'pred_gripper_act.bias']
unexpected:
['text_encoder.positional_embedding', 'text_encoder.text_projection', 'text_encoder.logit_scale', 'text_encoder.visual.class_embedding', 'text_encoder.visual.positional_embedding', 'text_encoder.visual.proj',
...
'text_encoder.transformer.resblocks.11.mlp.c_proj.weight', 'text_encoder.transformer.resblocks.11.mlp.c_proj.bias', 'text_encoder.transformer.resblocks.11.ln_2.weight', 'text_encoder.transformer.resblocks.11.ln_2.bias']
Could you please help to explain why this error occurred? Is there something wrong with my understanding?
Thank you very much for your help.
best