why is the following happening? RuntimeError: Error(s) in loading state_dict for GEN_VLKT:
Opened this issue · 10 comments
Traceback (most recent call last):
File "main.py", line 597, in
main(args)
File "main.py", line 433, in main
model_without_ddp.load_state_dict(checkpoint['model'], strict=True)
File "C:\Users\wanni\anaconda3\envs\hoiclip\lib\site-packages\torch\nn\modules\module.py", line 2152, in load_state_dict
raise RuntimeError('Error(s) in loading state_dict for {}:\n\t{}'.format(
RuntimeError: Error(s) in loading state_dict for GEN_VLKT:
It seems the checkpoint is incomplete or missing, could you provide more error logs?
Thank you very much for your reply！In the visualization_hico.sh file, using the pretrained model parameters provided by --pretrained params/detr-r50-pre-2branch-hico.pth, the following error is always displayed, Looking forward to your reply.
use clip text encoder to init classifier weight
VISUALIZATION
number of params: 42089226
init dataloader
train contains 37633 images and 117871 annotations
val contains 9546 images and 0 annotations
rare:138, non-rare:462
val contains 9546 images and 0 annotations
rare:138, non-rare:462
dataloader finished
model
Traceback (most recent call last):
File "main.py", line 597, in
main(args)
File "main.py", line 433, in main
model_without_ddp.load_state_dict(checkpoint['model'], strict=True)
File "C:\Users\wanni\anaconda3\envs\hoiclip\lib\site-packages\torch\nn\modules\module.py", line 2152, in load_state_dict
raise RuntimeError('Error(s) in loading state_dict for {}:\n\t{}'.format(
RuntimeError: Error(s) in loading state_dict for GEN_VLKT:
Missing key(s) in state_dict: "logit_scale", "obj_logit_scale", "verb2hoi_proj", "verb2hoi_proj_eval", "query_embed_h.weight", "query_embed_o.weight", "pos_guided_embedd.weight", "inter2verb.layers.0.weight", "inter2verb
.layers.0.bias", "inter2verb.layers.1.weight", "inter2verb.layers.1.bias", "inter2verb.layers.2.weight", "inter2verb.layers.2.bias", "clip_model.positional_embedding", "clip_model.text_projection", "clip_model.logit_scale", "cli
p_model.visual.class_embedding", "clip_model.visual.positional_embedding", "clip_model.visual.proj", "clip_model.visual.conv1.weight", "clip_model.visual.ln_pre.weight", "clip_model.visual.ln_pre.bias", "clip_model.visual.transf
ormer.resblocks.0.attn.in_proj_weight", "clip_model.visual.transformer.resblocks.0.attn.in_proj_bias", "clip_model.visual.transformer.resblocks.0.attn.out_proj.weight", "clip_model.visual.transformer.resblocks.0.attn.out_proj.bi
as", "clip_model.visual.transformer.resblocks.0.ln_1.weight", "clip_model.visual.transformer.resblocks.0.ln_1.bias", "clip_model.visual.transformer.resblocks.0.mlp.c_fc.weight", "clip_model.visual.transformer.resblocks.0.mlp.c_f
c.bias", "clip_model.visual.transformer.resblocks.0.mlp.c_proj.weight", "clip_model.visual.transformer.resblocks.0.mlp.c_proj.bias", "clip_model.visual.transformer.resblocks.0.ln_2.weight", "clip_model.visual.transformer.resbloc
ks.0.ln_2.bias", "clip_model.visual.transformer.resblocks.1.attn.in_proj_weight", "clip_model.visual.transformer.resblocks.1.attn.in_proj_bias", "clip_model.visual.transformer.resblocks.1.attn.out_proj.weight", "clip_model.visua
l.transformer.resblocks.1.attn.out_proj.bias", "clip_model.visual.transformer.resblocks.1.ln_1.weight", "clip_model.visual.transformer.resblocks.1.ln_1.bias", "clip_model.visual.transformer.resblocks.1.mlp.c_fc.weight", "clip_mo
del.visual.transformer.resblocks.1.mlp.c_fc.bias", "clip_model.visual.transformer.resblocks.1.mlp.c_proj.weight", "clip_model.visual.transformer.resblocks.1.mlp.c_proj.bias", "clip_model.visual.transformer.resblocks.1.ln_2.weigh
t", "clip_model.visual.transformer.resblocks.1.ln_2.bias", "clip_model.visual.transformer.resblocks.2.attn.in_proj_weight", "clip_model.visual.transformer.resblocks.2.attn.in_proj_bias", "clip_model.visual.transformer.resblocks.
2.attn.out_proj.weight", "clip_model.visual.transformer.resblocks.2.attn.out_proj.bias", "clip_model.visual.transformer.resblocks.2.ln_1.weight", "clip_model.visual.transformer.resblocks.2.ln_1.bias", "clip_model.visual.transfor
mer.resblocks.2.mlp.c_fc.weight", "clip_model.visual.transformer.resblocks.2.mlp.c_fc.bias", "clip_model.visual.transformer.resblocks.2.mlp.c_proj.weight", "clip_model.visual.transformer.resblocks.2.mlp.c_proj.bias", "clip_model
.visual.transformer.resblocks.2.ln_2.weight", "clip_model.visual.transformer.resblocks.2.ln_2.bias", "clip_model.visual.transformer.resblocks.3.attn.in_proj_weight", "clip_model.visual.transformer.resblocks.3.attn.in_proj_bias",
"clip_model.visual.transformer.resblocks.3.attn.out_proj.weight", "clip_model.visual.transformer.resblocks.3.attn.out_proj.bias", "clip_model.visual.transformer.resblocks.3.ln_1.weight", "clip_model.visual.transformer.resblocks
.3.ln_1.bias", "clip_model.visual.transformer.resblocks.3.mlp.c_fc.weight", "clip_model.visual.transformer.resblocks.3.mlp.c_fc.bias", "clip_model.visual.transformer.resblocks.3.mlp.c_proj.weight", "clip_model.visual.transformer
.resblocks.3.mlp.c_proj.bias", "clip_model.visual.transformer.resblocks.3.ln_2.weight", "clip_model.visual.transformer.resblocks.3.ln_2.bias", "clip_model.visual.transformer.resblocks.4.attn.in_proj_weight", "clip_model.visual.t
ransformer.resblocks.4.attn.in_proj_bias", "clip_model.visual.transformer.resblocks.4.attn.out_proj.weight", "clip_model.visual.transformer.resblocks.4.attn.out_proj.bias", "clip_model.visual.transformer.resblocks.4.ln_1.weight"
, "clip_model.visual.transformer.resblocks.4.ln_1.bias", "clip_model.visual.transformer.resblocks.4.mlp.c_fc.weight", "clip_model.visual.transformer.resblocks.4.mlp.c_fc.bias", "clip_model.visual.transformer.resblocks.4.mlp.c_pr
oj.weight", "clip_model.visual.transformer.resblocks.4.mlp.c_proj.bias", "clip_model.visual.transformer.resblocks.4.ln_2.weight",..
Maybe you only load the pretrained DETR weights, not our HOICLIP weights. Do you set args.resume to one of our released models and make sure the args.resume points to a valid directory with a checkpoint_last.pth.
Loading checkpoint_default.pth still has the following error：
RuntimeError: Error(s) in loading state_dict for GEN_VLKT:
Unexpected key(s) in state_dict: "transformer.clip_interaction_decoder.layers.0.self_attn.in_proj_weight", "transformer.clip_interaction_decoder.layers.0.self_attn.in_proj_bias", "transformer.clip_interaction_decoder.lay
ers.0.self_attn.out_proj.weight", "transformer.clip_interaction_decoder.layers.0.self_attn.out_proj.bias", "transformer.clip_interaction_decoder.layers.0.multihead_attn.in_proj_weight", "transformer.clip_interaction_decoder.laye
rs.0.multihead_attn.in_proj_bias", "transformer.clip_interaction_decoder.layers.0.multihead_attn.out_proj.weight", "transformer.clip_interaction_decoder.layers.0.multihead_attn.out_proj.bias", "transformer.clip_interaction_decod
er.layers.0.linear1.weight", "transformer.clip_interaction_decoder.layers.0.linear1.bias", "transformer.clip_interaction_decoder.layers.0.linear2.weight", "transformer.clip_interaction_decoder.layers.0.linear2.bias", "transforme
r.clip_interaction_decoder.layers.0.norm1.weight", "transformer.clip_interaction_decoder.layers.0.norm1.bias", "transformer.clip_interaction_decoder.layers.0.norm2.weight", "transformer.clip_interaction_decoder.layers.0.norm2.bi
as", "transformer.clip_interaction_decoder.layers.0.norm3.weight", "transformer.clip_interaction_decoder.layers.0.norm3.bias", "transformer.clip_interaction_decoder.layers.0.norm4.weight", "transformer.clip_interaction_decoder.l
ayers.0.norm4.bias", "transformer.clip_interaction_decoder.layers.1.self_attn.in_proj_weight", "transformer.clip_interaction_decoder.layers.1.self_attn.in_proj_bias", "transformer.clip_interaction_decoder.layers.1.self_attn.out_
proj.weight", "transformer.clip_interaction_decoder.layers.1.self_attn.out_proj.bias", "transformer.clip_interaction_decoder.layers.1.multihead_attn.in_proj_weight", "transformer.clip_interaction_decoder.layers.1.multihead_attn.
in_proj_bias", "transformer.clip_interaction_decoder.layers.1.multihead_attn.out_proj.weight", "transformer.clip_interaction_decoder.layers.1.multihead_attn.out_proj.bias", "transformer.clip_interaction_decoder.layers.1.linear1.
weight", "transformer.clip_interaction_decoder.layers.1.linear1.bias", "transformer.clip_interaction_decoder.layers.1.linear2.weight", "transformer.clip_interaction_decoder.layers.1.linear2.bias", "transformer.clip_interaction_d
ecoder.layers.1.norm1.weight", "transformer.clip_interaction_decoder.layers.1.norm1.bias", "transformer.clip_interaction_decoder.layers.1.norm2.weight", "transformer.clip_interaction_decoder.layers.1.norm2.bias", "transformer.cl
ip_interaction_decoder.layers.1.norm3.weight", "transformer.clip_interaction_decoder.layers.1.norm3.bias", "transformer.clip_interaction_decoder.layers.1.norm4.weight", "transformer.clip_interaction_decoder.layers.1.norm4.bias",
"transformer.clip_interaction_decoder.layers.2.self_attn.in_proj_weight", "transformer.clip_interaction_decoder.layers.2.self_attn.in_proj_bias", "transformer.clip_interaction_decoder.layers.2.self_attn.out_proj.weight", "trans
former.clip_interaction_decoder.layers.2.self_attn.out_proj.bias", "transformer.clip_interaction_decoder.layers.2.multihead_attn.in_proj_weight", "transformer.clip_interaction_decoder.layers.2.multihead_attn.in_proj_bias", "tran
sformer.clip_interaction_decoder.layers.2.multihead_attn.out_proj.weight", "transformer.clip_interaction_decoder.layers.2.multihead_attn.out_proj.bias", "transformer.clip_interaction_decoder.layers.2.linear1.weight", "transforme
r.clip_interaction_decoder.layers.2.linear1.bias", "transformer.clip_interaction_decoder.layers.2.linear2.weight", "transformer.clip_interaction_decoder.layers.2.linear2.bias", "transformer.clip_interaction_decoder.layers.2.norm
1.weight", "transformer.clip_interaction_decoder.layers.2.norm1.bias", "transformer.clip_interaction_decoder.layers.2.norm2.weight", "transformer.clip_interaction_decoder.layers.2.norm2.bias", "transformer.clip_interaction_decod
er.layers.2.norm3.weight", "transformer.clip_interaction_decoder.layers.2.norm3.bias", "transformer.clip_interaction_decoder.layers.2.norm4.weight", "transformer.clip_interaction_decoder.layers.2.norm4.bias", "transformer.clip_i
nteraction_decoder.norm.weight", "transformer.clip_interaction_decoder.norm.bias", "transformer.inter_guided_embedd.weight", "transformer.queries2spacial_proj.weight", "transformer.queries2spacial_proj.bias", "transformer.queries2spacial_proj_norm.weight", "transformer.queries2spacial_proj_norm.bias", "transformer.obj_class_fc.weight", "transformer.obj_class_fc.bias", "transformer.obj_class_ln.weight", "transformer.obj_class_ln.bias".
Opps! I find a bug in visualization code. The visualization code actually visulize the results of GEN-VLKT. I fix the code in models/visualization_hoiclip/gen_vlkt.py:17, which is from .gen import build_gen -> from .et_gen import build_gen. You may try again with latest code.
Traceback (most recent call last):
File "main.py", line 597, in
main(args)
File "main.py", line 447, in main
return self._call_impl(*args, **kwargs)
File "C:\Users\wanni\anaconda3\envs\hoiclip\lib\site-packages\torch\nn\modules\module.py", line 1527, in _call_impl
return forward_call(*args, **kwargs)
File "E:\PycharmProject\hoiclip_new\HOICLIP-main\models\visualization_hoiclip\gen_vlkt.py", line 185, in forward
h_hs, o_hs, inter_hs, clip_cls_feature, clip_hoi_score, clip_visual, weight, weight_2 = self.transformer(self.input_proj(src), mask,
File "C:\Users\wanni\anaconda3\envs\hoiclip\lib\site-packages\torch\nn\modules\module.py", line 1518, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "C:\Users\wanni\anaconda3\envs\hoiclip\lib\site-packages\torch\nn\modules\module.py", line 1527, in _call_impl
return forward_call(*args, **kwargs)
File "E:\PycharmProject\hoiclip_new\HOICLIP-main\models\visualization_hoiclip\et_gen.py", line 121, in forward
clip_cls_feature, clip_visual = clip_model.encode_image(clip_src)
ValueError: too many values to unpack (expected 2)
Sorry for another bug. It should work with latest codes.
Thanks to the author, hope to update the code.
(hoiclip) ayushi@gpusrv002:/DATA/scene_graph/ayushi/HOICLIP$ python main.py --pretrained checkpoint_rf_uc.pth --dataset_file hico --hoi_path data/hico_20160224_det --num_obj_classes 80 --num_verb_classes 117 --backbone resnet50 --num_queries 64 --dec_layers 3 --eval --zero_shot_type default --with_clip_label --with_obj_clip_label --use_nms_filter
Not using distributed mode
setting up seeds
git:
sha: 06b6517, status: has uncommited changes, branch: main
Namespace(lr=0.0001, lr_backbone=1e-05, lr_clip=1e-05, batch_size=2, weight_decay=0.0001, epochs=150, lr_drop=100, clip_max_norm=0.1, eval_each=4, eval_each_lr_drop=2, frozen_weights=None, backbone='resnet50', dilation=False, position_embedding='sine', enc_layers=6, dec_layers=3, dim_feedforward=2048, hidden_dim=256, dropout=0.1, nheads=8, num_queries=64, pre_norm=False, masks=False, hoi=False, num_obj_classes=80, num_verb_classes=117, pretrained='checkpoint_rf_uc.pth', subject_category_id=0, verb_loss_type='focal', aux_loss=True, with_mimic=False, set_cost_class=1, set_cost_bbox=2.5, set_cost_giou=1, set_cost_obj_class=1, set_cost_verb_class=1, set_cost_hoi=1, mask_loss_coef=1, dice_loss_coef=1, bbox_loss_coef=2.5, giou_loss_coef=1, obj_loss_coef=1, verb_loss_coef=2, hoi_loss_coef=2, mimic_loss_coef=20, alpha=0.5, eos_coef=0.1, dataset_file='hico', coco_path=None, coco_panoptic_path=None, remove_difficult=False, hoi_path='data/hico_20160224_det', output_dir='', device='cuda', seed=42, resume='', start_epoch=0, eval=True, num_workers=2, world_size=1, dist_url='env://', use_nms_filter=True, thres_nms=0.7, nms_alpha=1, nms_beta=0.5, json_file='results.json', ft_clip_with_small_lr=False, with_clip_label=True, with_obj_clip_label=True, clip_model='ViT-B/32', fix_clip=False, clip_embed_dim=512, zero_shot_type='default', del_unseen=False, fix_backbone_mode=[], use_ddp=1, with_random_shuffle=2, gradient_accumulation_steps=1, opt_sched='multiStep', no_clip_cls_init=False, enable_amp=False, opt_level='O2', fix_clip_label=False, with_rec_loss=False, rec_loss_coef=2, no_training=False, dataset_root='GEN', model_name='GEN', eval_location=False, enable_cp=False, no_fix_clip_linear=False, analysis=False, alternative=1, eval_each_ap=False, topk_hoi=10, inter_dec_layers=3, verb_pth='', verb_weight=0.5, frac=-1.0, validation_split=-1.0, lr_drop_gamma=0.1, training_free_enhancement_path='', distributed=False)
/home/ayushi/.conda/envs/hoiclip/lib/python3.11/site-packages/torchvision/models/_utils.py:208: UserWarning: The parameter 'pretrained' is deprecated since 0.13 and may be removed in the future, please use 'weights' instead.
warnings.warn(
/home/ayushi/.conda/envs/hoiclip/lib/python3.11/site-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or None for 'weights' are deprecated since 0.13 and may be removed in the future. The current behavior is equivalent to passing weights=None.
warnings.warn(msg)
GEN
number of params: 193327284
init dataloader
train contains 37633 images and 117871 annotations
val contains 9546 images and 0 annotations
rare:138, non-rare:462
val contains 9546 images and 0 annotations
rare:138, non-rare:462
dataloader finished
Traceback (most recent call last):
File "/DATA/scene_graph/ayushi/HOICLIP/main.py", line 588, in
main(args)
File "/DATA/scene_graph/ayushi/HOICLIP/main.py", line 425, in main
model_without_ddp.load_state_dict(checkpoint['model'], strict=True)
File "/home/ayushi/.conda/envs/hoiclip/lib/python3.11/site-packages/torch/nn/modules/module.py", line 2152, in load_state_dict
raise RuntimeError('Error(s) in loading state_dict for {}:\n\t{}'.format(
RuntimeError: Error(s) in loading state_dict for GEN_VLKT:
Unexpected key(s) in state_dict: "verb2hoi_proj", "verb2hoi_proj_eval", "inter2verb.layers.0.weight", "inter2verb.layers.0.bias", "inter2verb.layers.1.weight", "inter2verb.layers.1.bias", "inter2verb.layers.2.weight", "inter2verb.layers.2.bias", "verb_projection.weight", "eval_visual_projection.weight", "transformer.clip_interaction_decoder.layers.0.self_attn.in_proj_weight", "transformer.clip_interaction_decoder.layers.0.self_attn.in_proj_bias", "transformer.clip_interaction_decoder.layers.0.self_attn.out_proj.weight", "transformer.clip_interaction_decoder.layers.0.self_attn.out_proj.bias", "transformer.clip_interaction_decoder.layers.0.multihead_attn.in_proj_weight", "transformer.clip_interaction_decoder.layers.0.multihead_attn.in_proj_bias", "transformer.clip_interaction_decoder.layers.0.multihead_attn.out_proj.weight", "transformer.clip_interaction_decoder.layers.0.multihead_attn.out_proj.bias", "transformer.clip_interaction_decoder.layers.0.linear1.weight", "transformer.clip_interaction_decoder.layers.0.linear1.bias", "transformer.clip_interaction_decoder.layers.0.linear2.weight", "transformer.clip_interaction_decoder.layers.0.linear2.bias", "transformer.clip_interaction_decoder.layers.0.norm1.weight", "transformer.clip_interaction_decoder.layers.0.norm1.bias", "transformer.clip_interaction_decoder.layers.0.norm2.weight", "transformer.clip_interaction_decoder.layers.0.norm2.bias", "transformer.clip_interaction_decoder.layers.0.norm3.weight", "transformer.clip_interaction_decoder.layers.0.norm3.bias", "transformer.clip_interaction_decoder.layers.0.norm4.weight", "transformer.clip_interaction_decoder.layers.0.norm4.bias", "transformer.clip_interaction_decoder.layers.1.self_attn.in_proj_weight", "transformer.clip_interaction_decoder.layers.1.self_attn.in_proj_bias", "transformer.clip_interaction_decoder.layers.1.self_attn.out_proj.weight", "transformer.clip_interaction_decoder.layers.1.self_attn.out_proj.bias", "transformer.clip_interaction_decoder.layers.1.multihead_attn.in_proj_weight", "transformer.clip_interaction_decoder.layers.1.multihead_attn.in_proj_bias", "transformer.clip_interaction_decoder.layers.1.multihead_attn.out_proj.weight", "transformer.clip_interaction_decoder.layers.1.multihead_attn.out_proj.bias", "transformer.clip_interaction_decoder.layers.1.linear1.weight", "transformer.clip_interaction_decoder.layers.1.linear1.bias", "transformer.clip_interaction_decoder.layers.1.linear2.weight", "transformer.clip_interaction_decoder.layers.1.linear2.bias", "transformer.clip_interaction_decoder.layers.1.norm1.weight", "transformer.clip_interaction_decoder.layers.1.norm1.bias", "transformer.clip_interaction_decoder.layers.1.norm2.weight", "transformer.clip_interaction_decoder.layers.1.norm2.bias", "transformer.clip_interaction_decoder.layers.1.norm3.weight", "transformer.clip_interaction_decoder.layers.1.norm3.bias", "transformer.clip_interaction_decoder.layers.1.norm4.weight", "transformer.clip_interaction_decoder.layers.1.norm4.bias", "transformer.clip_interaction_decoder.layers.2.self_attn.in_proj_weight", "transformer.clip_interaction_decoder.layers.2.self_attn.in_proj_bias", "transformer.clip_interaction_decoder.layers.2.self_attn.out_proj.weight", "transformer.clip_interaction_decoder.layers.2.self_attn.out_proj.bias", "transformer.clip_interaction_decoder.layers.2.multihead_attn.in_proj_weight", "transformer.clip_interaction_decoder.layers.2.multihead_attn.in_proj_bias", "transformer.clip_interaction_decoder.layers.2.multihead_attn.out_proj.weight", "transformer.clip_interaction_decoder.layers.2.multihead_attn.out_proj.bias", "transformer.clip_interaction_decoder.layers.2.linear1.weight", "transformer.clip_interaction_decoder.layers.2.linear1.bias", "transformer.clip_interaction_decoder.layers.2.linear2.weight", "transformer.clip_interaction_decoder.layers.2.linear2.bias", "transformer.clip_interaction_decoder.layers.2.norm1.weight", "transformer.clip_interaction_decoder.layers.2.norm1.bias", "transformer.clip_interaction_decoder.layers.2.norm2.weight", "transformer.clip_interaction_decoder.layers.2.norm2.bias", "transformer.clip_interaction_decoder.layers.2.norm3.weight", "transformer.clip_interaction_decoder.layers.2.norm3.bias", "transformer.clip_interaction_decoder.layers.2.norm4.weight", "transformer.clip_interaction_decoder.layers.2.norm4.bias", "transformer.clip_interaction_decoder.norm.weight", "transformer.clip_interaction_decoder.norm.bias", "transformer.inter_guided_embedd.weight", "transformer.queries2spacial_proj.weight", "transformer.queries2spacial_proj.bias", "transformer.queries2spacial_proj_norm.weight", "transformer.queries2spacial_proj_norm.bias", "transformer.obj_class_fc.weight", "transformer.obj_class_fc.bias", "transformer.obj_class_ln.weight", "transformer.obj_class_ln.bias".
size mismatch for visual_projection.weight: copying a param with shape torch.Size([480, 512]) from checkpoint, the shape in current model is torch.Size([600, 512]).
size mismatch for visual_projection.bias: copying a param with shape torch.Size([480]) from checkpoint, the shape in current model is torch.Size([600]).
I am getting this error even with the updated code.
--zero_shot_type default
--zero_shot_type default mean you choose the model for default setting where there are 600 classes for prediction, however, you load a zero-shot setting model weight(checkpoint_rf_uc.pth), which cause the error