wudongming97 / rmot Goto Github PK
View Code? Open in Web Editor NEW[CVPR2023] Referring Multi-Object Tracking
License: Other
[CVPR2023] Referring Multi-Object Tracking
License: Other
Hi, Developer team.
I have encounter some problems when i try the testing part. Below are some outputs from the command line
No param transformer.decoder.layers.0.update_attn.in_proj_weight.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param transformer.decoder.layers.0.update_attn.in_proj_bias.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param transformer.decoder.layers.0.update_attn.out_proj.weight.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param transformer.decoder.layers.0.update_attn.out_proj.bias.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
I have strictly follow the read.me and download the checkpoint: checkpoint0099.pth, but it seems that some parameters from pre-trained weights can not find corresponding parameters in our model? I want to know is it right?
Hello, I used the command you provided to test:
python inference.py --meta_arch rmot --dataset_file e2e_rmot --epoch 200 --with_box_refine --lr_drop 100 --lr 2e-4 --lr_backbone 2e-5 --batch_size 1 --sample_mode random_interval --sample_interval 1 --sampler_steps 50 90 150 --samp
ler_lengths 2 3 4 5 --update_query_pos --merger_dropout 0 -lt/checkpoint0099.pth --output_dir exps/default --visualization
but the following problem occurred during runtime:
raise HFValidationError(
huggingface_hub.utils._validators.HFValidationError: Repo id must be in the form 'repo_name' or 'namespace/repo_name': '/data/wudongming/FairMOT/src/roberta_base/'. Use repo_type
argument if needed.
I wonder which part of the command line needs to be modified?
As it can be seemed here:
root@tony:~/449_RMOT/exps/default$ ls
checkpoint0099.pth
root@tony:~/449_RMOT/exps/default$ cdd
root@tony:~/449_RMOT$ sh configs/r50_rmot_test.sh
Training with Extra Self Attention in Every Decoder.
Training with Self-Cross Attention.
Namespace(accurate_ratio=False, append_crowd=False, aux_loss=True, backbone='resnet50', batch_size=1, bbox_loss_coef=5, cache_mode=False, cj=False, clip_max_norm=0.1, cls_loss_coef=2, coco_panoptic_path=None, coco_path='/data/workspace/detectron2/datasets/coco/', crop=False, data_txt_path_train='./datasets/data_path/refer-kitti.train', dataset_file='e2e_rmot', dec_layers=6, dec_n_points=4, decoder_cross_self=False, device='cuda', dice_loss_coef=1, dilation=False, dim_feedforward=1024, dropout=0.0, enable_fpn=False, enc_layers=6, enc_n_points=4, epochs=200, eval=False, exp_name='submit', extra_track_attn=True, filter_ignore=False, focal_alpha=0.25, fp_ratio=0.3, frozen_weights=None, giou_loss_coef=2, gt_file_train=None, gt_file_val=None, hidden_dim=256, img_path='data/valid/JPEGImages/', input_video='figs/demo.mp4', loss_normalizer=False, lr=0.0002, lr_backbone=2e-05, lr_backbone_names=['backbone.0'], lr_drop=100, lr_drop_epochs=None, lr_linear_proj_mult=0.1, lr_linear_proj_names=['reference_points', 'sampling_offsets'], mask_loss_coef=1, masks=False, max_size=1333, memory_bank_len=4, memory_bank_score_thresh=0.0, memory_bank_type=None, memory_bank_with_self_attn=False, merger_dropout=0.0, meta_arch='rmot', mix_match=False, nheads=8, num_anchors=1, num_feature_levels=4, num_queries=300, num_workers=2, output_dir='exps/default', position_embedding='sine', position_embedding_scale=6.283185307179586, pretrained=None, query_interaction_layer='QIM', random_drop=0.1, refer_loss_coef=2, remove_difficult=False, resume='exps/default/checkpoint0099.pth', rmot_path='/data/Dataset/refer-kitti', sample_interval=1, sample_mode='random_interval', sampler_lengths=[2, 3, 4, 5], sampler_steps=[50, 90, 150], save_period=50, seed=42, set_cost_bbox=5, set_cost_class=2, set_cost_giou=2, set_cost_refer=2, sgd=False, sigmoid_attn=False, start_epoch=0, two_stage=False, update_query_pos=True, use_checkpoint=False, val_width=800, vis=False, visualization=True, weight_decay=0.0001, with_box_refine=True)
Traceback (most recent call last):
File "inference.py", line 547, in <module>
checkpoint = torch.load(args.resume, map_location='cpu')
File "/root/miniconda3/lib/python3.8/site-packages/torch/serialization.py", line 600, in load
with _open_zipfile_reader(opened_file) as opened_zipfile:
File "/root/miniconda3/lib/python3.8/site-packages/torch/serialization.py", line 242, in __init__
super(_open_zipfile_reader, self).__init__(torch._C.PyTorchFileReader(name_or_buffer))
RuntimeError: PytorchStreamReader failed reading zip archive: failed finding central directory
root@tony:~/449_RMOT$
explain where is wrong, which py file should I look into
I have config the checkpoint and run the code, but the checkpoint file seem to be buggy, does anyone know the possible behavior causing this? Thanks!
I solved this one, the checkpoint file is corrupted somehow, after I reinstall and config the project, it works with the following massive warning :
I have downloaded the pretrained models you provided. But when i run inference, the result is bad. can you give the detail of the inference and some results of it?
Hi, your work is amazing, can you provide more details on how to replicate your work? For example, I want to know where can get the file:/data/wudongming/FairMOT/SRC/roberta_base /.I would appreciate your reply
Hi, thanks for your great work!
About the pretrained Deformable DETR model used in training, could you specify which one is used in your paper, since there are several versions provided in the repo, and each has different performances on COCO.
Also, for kitti images, I guess the it shoud be the link marked below, is that right?
Why are the json files of the "persons in the right" and "persons in the left" in video 16 exactly the same when the two expressions mean opposite things? Could you please explain how you distinguish between left and right when labeling data?
Hi, I just have a small question. Did you use the text feature to initialize the detect query in the decoder?
https://github.com/wudongming97/RMOT/blob/cb5fd35364a078f355c102358fddc682f37af786/models/transrmot.py#L648C1-L648C1
Hi, could you please explain how the Train/Test set is splitted?
The paper mentions that 18 videos are used as training set and 3 as test set. But it looks like code of this repo does not specify the train/test split.
The default argument of data_txt_path_train
in main.py
is ./datasets/data_path/refer-kitti.train
, but there is no infomation about the folder/file refer-kitti.train
.
Hi, thanks for your excellent work!
Would you please provide the codes/models of other trackers?
For example, the detection(referent) results from FairMOT with integrated cross-modal fusion module.
Thanks~
我复现了您的代码,发现您的测试过程是对于training set里的5,11,13 seq进行测试。但是这几个seq不是training data吗,治理是不是稍微有一点问题。
Hello, thank you very much for your great work!
I would like to know more details about your dataset labeling method and the annotation tool you mentioned in the paper, because I really want to work on the dataset I need to study, which means how to annotate custom datasets and train them?
Hello,
Thanks for your excellent work!
Thanks~
Hello developer team, thank you for this noval work. When I am trying to do reproduction work on it, I met some problems. Here is the issue:
exps/default/checkpoint0099.pth
sh configs/r50_rmot_test.sh
, and it says this:(deformable_detr) root@tony:~/449_RMOT$ pip install MultiScaleDeformableAttention
File "/root/449_RMOT/models/ops/functions/ms_deform_attn_func.py", line 21, in <module>
import MultiScaleDeformableAttention as MSDA
ImportError: /root/miniconda3/envs/deformable_detr/lib/python3.7/site-packages/MultiScaleDeformableAttention-1.0-py3.7-linux-x86_64.egg/MultiScaleDeformableAttention.cpython-37m-x86_64-linux-gnu.so: undefined symbol: _ZN6caffe28TypeMeta21_typeMetaDataInstanceISt7complexIdEEEPKNS_6detail12TypeMetaDataEv
(deformable_detr) root@tony:~/449_RMOT$
I tried to solve it with GPT, but can not progress. Could you instruct me on where is the possible problem? For instance, what is this MSDA model and how should I download it?
Looking in indexes: http://mirrors.aliyun.com/pypi/simple
Requirement already satisfied: MultiScaleDeformableAttention in /root/miniconda3/envs/deformable_detr/lib/python3.7/site-packages/MultiScaleDeformableAttention-1.0-py3.7-linux-x86_64.egg (1.0)
My pip said it has downloaded it already
Why do I get an error when batchsize is set greater than 1? If batchsize=1, then what's the point of training multiple cards
Thanks for your excellent work. I want to know the details of KITTI you used.
Hello,
Thanks for your excellent work!
How long does it take to complete TransRMOT training (100 epochs) using 8 2080ti GPUs?
Thank you.
any explanation or instruction for how to understand the format of the annotation files, expression
and labels_with_ids
?
how to link each other.
Hi, could you please provide the Roberta model used in this project?
The path in the code is /data/wudongming/FairMOT/SRC/roberta_base
, but it is not provided.
train:
loaded ./data/r50_deformable_detr_plus_iterative_bbox_refinement-checkpoint.pth
Skip loading parameter class_embed.0.weight, required shapetorch.Size([1, 256]), loaded shapetorch.Size([91, 256]). If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
load class_embed: class_embed.0.weight shape=torch.Size([91, 256])
Skip loading parameter class_embed.0.bias, required shapetorch.Size([1]), loaded shapetorch.Size([91]). If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
load class_embed: class_embed.0.bias shape=torch.Size([91])
Skip loading parameter class_embed.1.weight, required shapetorch.Size([1, 256]), loaded shapetorch.Size([91, 256]). If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
load class_embed: class_embed.1.weight shape=torch.Size([91, 256])
Skip loading parameter class_embed.1.bias, required shapetorch.Size([1]), loaded shapetorch.Size([91]). If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
load class_embed: class_embed.1.bias shape=torch.Size([91])
Skip loading parameter class_embed.2.weight, required shapetorch.Size([1, 256]), loaded shapetorch.Size([91, 256]). If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
load class_embed: class_embed.2.weight shape=torch.Size([91, 256])
Skip loading parameter class_embed.2.bias, required shapetorch.Size([1]), loaded shapetorch.Size([91]). If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
load class_embed: class_embed.2.bias shape=torch.Size([91])
Skip loading parameter class_embed.3.weight, required shapetorch.Size([1, 256]), loaded shapetorch.Size([91, 256]). If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
load class_embed: class_embed.3.weight shape=torch.Size([91, 256])
Skip loading parameter class_embed.3.bias, required shapetorch.Size([1]), loaded shapetorch.Size([91]). If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
load class_embed: class_embed.3.bias shape=torch.Size([91])
Skip loading parameter class_embed.4.weight, required shapetorch.Size([1, 256]), loaded shapetorch.Size([91, 256]). If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
load class_embed: class_embed.4.weight shape=torch.Size([91, 256])
Skip loading parameter class_embed.4.bias, required shapetorch.Size([1]), loaded shapetorch.Size([91]). If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
load class_embed: class_embed.4.bias shape=torch.Size([91])
Skip loading parameter class_embed.5.weight, required shapetorch.Size([1, 256]), loaded shapetorch.Size([91, 256]). If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
load class_embed: class_embed.5.weight shape=torch.Size([91, 256])
Skip loading parameter class_embed.5.bias, required shapetorch.Size([1]), loaded shapetorch.Size([91]). If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
load class_embed: class_embed.5.bias shape=torch.Size([91])
No param track_embed.self_attn.in_proj_weight.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param track_embed.self_attn.in_proj_bias.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param track_embed.self_attn.out_proj.weight.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param track_embed.self_attn.out_proj.bias.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param track_embed.linear1.weight.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param track_embed.linear1.bias.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param track_embed.linear2.weight.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param track_embed.linear2.bias.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param track_embed.linear_pos1.weight.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param track_embed.linear_pos1.bias.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param track_embed.linear_pos2.weight.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param track_embed.linear_pos2.bias.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param track_embed.norm_pos.weight.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param track_embed.norm_pos.bias.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param track_embed.linear_feat1.weight.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param track_embed.linear_feat1.bias.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param track_embed.linear_feat2.weight.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param track_embed.linear_feat2.bias.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param track_embed.norm_feat.weight.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param track_embed.norm_feat.bias.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param track_embed.norm1.weight.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param track_embed.norm1.bias.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param track_embed.norm2.weight.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param track_embed.norm2.bias.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param track_embed.norm3.weight.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param track_embed.norm3.bias.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param refer_embed.0.weight.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param refer_embed.0.bias.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param refer_embed.1.weight.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param refer_embed.1.bias.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param refer_embed.2.weight.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param refer_embed.2.bias.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param refer_embed.3.weight.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param refer_embed.3.bias.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param refer_embed.4.weight.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param refer_embed.4.bias.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param refer_embed.5.weight.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param refer_embed.5.bias.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.embeddings.position_ids.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.embeddings.word_embeddings.weight.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.embeddings.position_embeddings.weight.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.embeddings.token_type_embeddings.weight.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.embeddings.LayerNorm.weight.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.embeddings.LayerNorm.bias.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.0.attention.self.query.weight.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.0.attention.self.query.bias.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.0.attention.self.key.weight.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.0.attention.self.key.bias.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.0.attention.self.value.weight.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.0.attention.self.value.bias.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.0.attention.output.dense.weight.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.0.attention.output.dense.bias.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.0.attention.output.LayerNorm.weight.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.0.attention.output.LayerNorm.bias.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.0.intermediate.dense.weight.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.0.intermediate.dense.bias.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.0.output.dense.weight.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.0.output.dense.bias.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.0.output.LayerNorm.weight.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.0.output.LayerNorm.bias.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.1.attention.self.query.weight.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.1.attention.self.query.bias.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.1.attention.self.key.weight.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.1.attention.self.key.bias.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.1.attention.self.value.weight.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.1.attention.self.value.bias.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.1.attention.output.dense.weight.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.1.attention.output.dense.bias.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.1.attention.output.LayerNorm.weight.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.1.attention.output.LayerNorm.bias.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.1.intermediate.dense.weight.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.1.intermediate.dense.bias.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.1.output.dense.weight.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.1.output.dense.bias.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.1.output.LayerNorm.weight.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.1.output.LayerNorm.bias.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.2.attention.self.query.weight.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.2.attention.self.query.bias.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.2.attention.self.key.weight.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.2.attention.self.key.bias.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.2.attention.self.value.weight.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.2.attention.self.value.bias.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.2.attention.output.dense.weight.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.2.attention.output.dense.bias.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.2.attention.output.LayerNorm.weight.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.2.attention.output.LayerNorm.bias.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.2.intermediate.dense.weight.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.2.intermediate.dense.bias.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.2.output.dense.weight.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.2.output.dense.bias.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.2.output.LayerNorm.weight.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.2.output.LayerNorm.bias.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.3.attention.self.query.weight.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.3.attention.self.query.bias.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.3.attention.self.key.weight.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.3.attention.self.key.bias.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.3.attention.self.value.weight.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.3.attention.self.value.bias.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.3.attention.output.dense.weight.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.3.attention.output.dense.bias.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.3.attention.output.LayerNorm.weight.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.3.attention.output.LayerNorm.bias.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.3.intermediate.dense.weight.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.3.intermediate.dense.bias.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.3.output.dense.weight.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.3.output.dense.bias.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.3.output.LayerNorm.weight.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.3.output.LayerNorm.bias.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.4.attention.self.query.weight.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.4.attention.self.query.bias.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.4.attention.self.key.weight.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.4.attention.self.key.bias.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.4.attention.self.value.weight.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.4.attention.self.value.bias.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.4.attention.output.dense.weight.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.4.attention.output.dense.bias.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.4.attention.output.LayerNorm.weight.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.4.attention.output.LayerNorm.bias.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.4.intermediate.dense.weight.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.4.intermediate.dense.bias.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.4.output.dense.weight.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.4.output.dense.bias.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.4.output.LayerNorm.weight.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.4.output.LayerNorm.bias.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.5.attention.self.query.weight.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.5.attention.self.query.bias.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.5.attention.self.key.weight.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.5.attention.self.key.bias.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.5.attention.self.value.weight.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.5.attention.self.value.bias.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.5.attention.output.dense.weight.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.5.attention.output.dense.bias.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.5.attention.output.LayerNorm.weight.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.5.attention.output.LayerNorm.bias.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.5.intermediate.dense.weight.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.5.intermediate.dense.bias.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.5.output.dense.weight.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.5.output.dense.bias.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.5.output.LayerNorm.weight.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.5.output.LayerNorm.bias.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.6.attention.self.query.weight.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.6.attention.self.query.bias.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.6.attention.self.key.weight.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.6.attention.self.key.bias.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.6.attention.self.value.weight.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.6.attention.self.value.bias.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.6.attention.output.dense.weight.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.6.attention.output.dense.bias.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.6.attention.output.LayerNorm.weight.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.6.attention.output.LayerNorm.bias.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.6.intermediate.dense.weight.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.6.intermediate.dense.bias.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.6.output.dense.weight.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.6.output.dense.bias.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.6.output.LayerNorm.weight.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.6.output.LayerNorm.bias.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.7.attention.self.query.weight.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.7.attention.self.query.bias.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.7.attention.self.key.weight.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.7.attention.self.key.bias.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.7.attention.self.value.weight.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.7.attention.self.value.bias.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.7.attention.output.dense.weight.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.7.attention.output.dense.bias.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.7.attention.output.LayerNorm.weight.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.7.attention.output.LayerNorm.bias.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.7.intermediate.dense.weight.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.7.intermediate.dense.bias.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.7.output.dense.weight.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.7.output.dense.bias.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.7.output.LayerNorm.weight.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.7.output.LayerNorm.bias.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.8.attention.self.query.weight.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.8.attention.self.query.bias.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.8.attention.self.key.weight.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.8.attention.self.key.bias.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.8.attention.self.value.weight.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.8.attention.self.value.bias.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.8.attention.output.dense.weight.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.8.attention.output.dense.bias.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.8.attention.output.LayerNorm.weight.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.8.attention.output.LayerNorm.bias.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.8.intermediate.dense.weight.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.8.intermediate.dense.bias.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.8.output.dense.weight.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.8.output.dense.bias.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.8.output.LayerNorm.weight.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.8.output.LayerNorm.bias.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.9.attention.self.query.weight.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.9.attention.self.query.bias.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.9.attention.self.key.weight.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.9.attention.self.key.bias.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.9.attention.self.value.weight.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.9.attention.self.value.bias.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.9.attention.output.dense.weight.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.9.attention.output.dense.bias.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.9.attention.output.LayerNorm.weight.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.9.attention.output.LayerNorm.bias.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.9.intermediate.dense.weight.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.9.intermediate.dense.bias.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.9.output.dense.weight.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.9.output.dense.bias.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.9.output.LayerNorm.weight.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.9.output.LayerNorm.bias.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.10.attention.self.query.weight.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.10.attention.self.query.bias.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.10.attention.self.key.weight.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.10.attention.self.key.bias.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.10.attention.self.value.weight.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.10.attention.self.value.bias.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.10.attention.output.dense.weight.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.10.attention.output.dense.bias.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.10.attention.output.LayerNorm.weight.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.10.attention.output.LayerNorm.bias.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.10.intermediate.dense.weight.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.10.intermediate.dense.bias.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.10.output.dense.weight.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.10.output.dense.bias.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.10.output.LayerNorm.weight.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.10.output.LayerNorm.bias.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.11.attention.self.query.weight.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.11.attention.self.query.bias.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.11.attention.self.key.weight.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.11.attention.self.key.bias.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.11.attention.self.value.weight.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.11.attention.self.value.bias.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.11.attention.output.dense.weight.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.11.attention.output.dense.bias.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.11.attention.output.LayerNorm.weight.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.11.attention.output.LayerNorm.bias.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.11.intermediate.dense.weight.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.11.intermediate.dense.bias.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.11.output.dense.weight.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.11.output.dense.bias.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.11.output.LayerNorm.weight.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.encoder.layer.11.output.LayerNorm.bias.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.pooler.dense.weight.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param text_encoder.pooler.dense.bias.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param txt_proj.fc.weight.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param txt_proj.fc.bias.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param txt_proj.layer_norm.weight.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param txt_proj.layer_norm.bias.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param fusion_module.multihead_attn.in_proj_weight.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param fusion_module.multihead_attn.in_proj_bias.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param fusion_module.multihead_attn.out_proj.weight.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param fusion_module.multihead_attn.out_proj.bias.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
Start training
set epoch: epoch 0 period_idx=0
[W reducer.cpp:1050] Warning: find_unused_parameters=True was specified in DDP constructor, but did not find any unused parameters. This flag results in an extra traversal of the autograd graph every iteration, which can adversely affect performance. If your model indeed never has any unused parameters, consider turning this flag off. Note that this warning may be a false positive your model has flow control causing later iterations to have unused parameters. (function operator())
Epoch: [0] [ 0/4976] eta: 2:15:40 loss: 21.0104 (21.0104) frame_0_loss_ce: 0.4476 (0.4476) frame_0_loss_bbox: 0.0030 (0.0030) frame_0_loss_giou: 0.0567 (0.0567) frame_0_loss_refer: 0.3673 (0.3673) frame_1_loss_ce: 0.4967 (0.4967) frame_1_loss_bbox: 0.0037 (0.0037) frame_1_loss_giou: 0.0800 (0.0800) frame_1_loss_refer: 0.3789 (0.3789) time: 1.6359 data: 0.3975 max mem: 2782
test:
loaded data/checkpoint0099.pth
No param transformer.decoder.layers.0.update_attn.in_proj_weight.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param transformer.decoder.layers.0.update_attn.in_proj_bias.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param transformer.decoder.layers.0.update_attn.out_proj.weight.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param transformer.decoder.layers.0.update_attn.out_proj.bias.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param transformer.decoder.layers.0.norm4.weight.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param transformer.decoder.layers.0.norm4.bias.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param transformer.decoder.layers.1.update_attn.in_proj_weight.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param transformer.decoder.layers.1.update_attn.in_proj_bias.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param transformer.decoder.layers.1.update_attn.out_proj.weight.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param transformer.decoder.layers.1.update_attn.out_proj.bias.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param transformer.decoder.layers.1.norm4.weight.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param transformer.decoder.layers.1.norm4.bias.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param transformer.decoder.layers.2.update_attn.in_proj_weight.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param transformer.decoder.layers.2.update_attn.in_proj_bias.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param transformer.decoder.layers.2.update_attn.out_proj.weight.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param transformer.decoder.layers.2.update_attn.out_proj.bias.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param transformer.decoder.layers.2.norm4.weight.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param transformer.decoder.layers.2.norm4.bias.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param transformer.decoder.layers.3.update_attn.in_proj_weight.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param transformer.decoder.layers.3.update_attn.in_proj_bias.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param transformer.decoder.layers.3.update_attn.out_proj.weight.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param transformer.decoder.layers.3.update_attn.out_proj.bias.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param transformer.decoder.layers.3.norm4.weight.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param transformer.decoder.layers.3.norm4.bias.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param transformer.decoder.layers.4.update_attn.in_proj_weight.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param transformer.decoder.layers.4.update_attn.in_proj_bias.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param transformer.decoder.layers.4.update_attn.out_proj.weight.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param transformer.decoder.layers.4.update_attn.out_proj.bias.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param transformer.decoder.layers.4.norm4.weight.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param transformer.decoder.layers.4.norm4.bias.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param transformer.decoder.layers.5.update_attn.in_proj_weight.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param transformer.decoder.layers.5.update_attn.in_proj_bias.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param transformer.decoder.layers.5.update_attn.out_proj.weight.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param transformer.decoder.layers.5.update_attn.out_proj.bias.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param transformer.decoder.layers.5.norm4.weight.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
No param transformer.decoder.layers.5.norm4.bias.If you see this, your model does not fully load the pre-trained weight. Please make sure you set the correct --num_classes for your own dataset.
Evaluating seq ['0005', 'black-cars-in-the-left.json']
Hi,
From reading the article and the code, I know that the txt files in labels_with_ids contain the track_id and bbox of the object in the corresponding frame, and I would like to know how these files are generated (what rules are followed?) ? It seems that there is not a one-to-one correspondence with the KITTI MOT labels.
Thanks.
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.