justchenhao / sili_cd Goto Github PK

Official Pytorch Implementation of “Continuous Cross-resolution Remote Sensing Image Change Detection”

License: BSD 2-Clause "Simplified" License

Python 99.85% Shell 0.15%

change-detection cross-resolution-change-detection

sili_cd's Introduction

Continuous Cross-resolution Change Detection

Here, we provide the pytorch implementation of the paper: Continuous Cross-resolution Remote Sensing Image Change Detection.

For more ore information, please see our published paper at IEEE TGRS or arxiv.

The pipeline of our proposed scale-invariant learning with implicit neural networks for remote sensing image change detection is illustrated as follows:

Requirements

python 3.7.7
pytorch 1.10.1
torchvision 0.11.2
wanbd 0.12.11
kornia 0.6.3
timm 0.5.4
omegaconf 2.1.1
einops 0.3.0

Logs

20231021: initialize the code.

Installation

Clone this repository:

git clone https://github.com/justchenhao/SILI_CD.git
cd SILI_CD

Quick Start

Download the checkpoint at https://pan.baidu.com/s/1R2XWu4lDfU1emhXbgrx17A (code: 358c) , and put the folder ours_levir1x in the folder checkpoints;
Execute the script python try_cd.py to evaluate our model;
The prediction results for samples in samples/levir_cut are saved in the folder checkpoints/ours_levir1x. Here, you can see the prediction results of different bitemporal resolution difference ratios.

Usages

Dataset configurations

You can configure the name/path/folder_name of the dataset in the file data_config.py, as shown below:

if data_name == 'LEVIR':
    self.root_dir = 'Path of the LEVIR-CD root'
    self.img_folder_names = ['A', 'B']
elif data_name == 'SV_CD':
    self.root_dir = 'Path of the SV-CD root'
    self.img_folder_names = ['A', 'B']
elif data_name == 'DE_CD':
    self.root_dir = 'Path of the DE-CD root'
    self.img_folder_names = ['A_low', 'B']

Training

An example of training script can be found in scripts\cd_train.sh.

A default configuration for our CD method could be found in ./conf/cd_ours.yaml. You could also modify certain parameters in the command line.

#!/usr/bin/env bash

gpus=0
config_path=./conf/cd_ours.yaml
checkpoint_root=checkpoints
pretrained=imagenet
splits=train
model_name=ifa_inter234_local4n_lpe_edgeconv_up2_resnet18_concat
with_wandb=2
scale_mode=3
data_name=LEVIR
scale_ratios=0.25/0.5/0.75/1,0.25
python main_cd.py --scale_mode ${scale_mode}  --data_name ${data_name} --with_wandb $with_wandb --splits ${splits} --scale_ratios ${scale_ratios} --model_name ${model_name} --config_path ${config_path} --gpu_ids ${gpus} --pretrained ${pretrained} --checkpoint_root ${checkpoint_root}

Validation

An example of validation script can be found in scripts\cd_eval.sh.

You can testing the model performance on samples with varying bitemporal resolution difference ratios by setting different scale ratios.

config_path=./conf/cd_ours.yaml
data_name=LEVIR
model_name=ifa_inter234_local4n_lpe_edgeconv_up2_resnet18_concat
checkpoint_dir='checkpoints/ours_levir1x' # modify it for your checkpoint folder
python main_eval.py --model_name ${model_name} --config_path ${config_path} --data_name ${data_name} --checkpoint_dir ${checkpoint_dir}

Dataset Preparation

Data structure

"""
Change detection data set with pixel-level binary labels；
├─A
├─B
├─label
└─list
"""

A: images of t1 phase;

B:images of t2 phase;

label: label maps;

list: contains train.txt, val.txt and test.txt, each file records the image names (XXX.png) in the change detection dataset.

Data Download

LEVIR-CD: https://justchenhao.github.io/LEVIR/

SV-CD: https://drive.google.com/file/d/1GX656JqqOyBi_Ef0w65kDGVto-nHrNs9/edit

DE-CD:

Our processed DE-CD data could be downloaded at https://pan.baidu.com/s/1NNoXnwAba41HZppG3flX6A (code: v76s)
You can also download the original DynamicEarthNet data at https://mediatum.ub.tum.de/1650201

License

Code is released for non-commercial and research purposes only. For commercial purposes, please contact the authors.

Citation

If you use this code for your research, please cite our paper:

@Article{chen2023,
    title={Continuous Cross-resolution Remote Sensing Image Change Detection},
    author={Hao Chen, Haotian Zhang, Keyan Chen, Chenyao Zhou, Song Chen, Zhengxia Zou, Zhenwei Shi},
    year={2023},
    journal={IEEE Transactions on Geoscience and Remote Sensing},
    volume={},
    number={},
    pages={1-21},
    doi={10.1109/TGRS.2023.3325829}
}

sili_cd's People

Contributors

Stargazers

Watchers

Forkers

scott-mao luo-yafei

sili_cd's Issues

Checkpoint download

Could you please upload the checkpoint on another cloud storage medium, too? Maybe Google Drive?

Error loading state_dict for OptimizedModule: Missing key(s) in state_dict

When following the steps for a Quick Start:

Download the checkpoint at https://pan.baidu.com/s/1R2XWu4lDfU1emhXbgrx17A (code: 358c) , and put the folder ours_levir1x in the folder checkpoints;
Execute the script python try_cd.py to evaluate our model;
The prediction results for samples in samples/levir_cut are saved in the folder checkpoints/ours_levir1x. Here, you can see the prediction results of different bitemporal resolution difference ratios.

This error arises:

File ~/.local/lib/python3.10/site-packages/torch/nn/modules/module.py:2152, in Module.load_state_dict(self, state_dict, strict, assign)
2147 error_msgs.insert(
2148 0, 'Missing key(s) in state_dict: {}. '.format(
2149 ', '.join(f'"{k}"' for k in missing_keys)))
2151 if len(error_msgs) > 0:
-> 2152 raise RuntimeError('Error(s) in loading state_dict for {}:\n\t{}'.format(
2153 self.class.name, "\n\t".join(error_msgs)))
2154 return _IncompatibleKeys(missing_keys, unexpected_keys)

RuntimeError: Error(s) in loading state_dict for OptimizedModule:
Missing key(s) in state_dict: "_orig_mod.backbone.backbone.conv1.weight", "_orig_mod.backbone.backbone.bn1.weight", "_orig_mod.backbone.backbone.bn1.bias", "_orig_mod.backbone.backbone.bn1.running_mean", "_orig_mod.backbone.backbone.bn1.running_var", "_orig_mod.backbone.backbone.layer1.0.conv1.weight", "_orig_mod.backbone.backbone.layer1.0.bn1.weight", "_orig_mod.backbone.backbone.layer1.0.bn1.bias", "_orig_mod.backbone.backbone.layer1.0.bn1.running_mean", "_orig_mod.backbone.backbone.layer1.0.bn1.running_var", "_orig_mod.backbone.backbone.layer1.0.conv2.weight", "_orig_mod.backbone.backbone.layer1.0.bn2.weight", "_orig_mod.backbone.backbone.layer1.0.bn2.bias", "_orig_mod.backbone.backbone.layer1.0.bn2.running_mean", "_orig_mod.backbone.backbone.layer1.0.bn2.running_var", "_orig_mod.backbone.backbone.layer1.1.conv1.weight", "_orig_mod.backbone.backbone.layer1.1.bn1.weight", "_orig_mod.backbone.backbone.layer1.1.bn1.bias", "_orig_mod.backbone.backbone.layer1.1.bn1.running_mean", "_orig_mod.backbone.backbone.layer1.1.bn1.running_var", "_orig_mod.backbone.backbone.layer1.1.conv2.weight", "_orig_mod.backbone.backbone.layer1.1.bn2.weight", "_orig_mod.backbone.backbone.layer1.1.bn2.bias", "_orig_mod.backbone.backbone.layer1.1.bn2.running_mean", "_orig_mod.backbone.backbone.layer1.1.bn2.running_var", "_orig_mod.backbone.backbone.layer2.0.conv1.weight", "_orig_mod.backbone.backbone.layer2.0.bn1.weight", "_orig_mod.backbone.backbone.layer2.0.bn1.bias", "_orig_mod.backbone.backbone.layer2.0.bn1.running_mean", "_orig_mod.backbone.backbone.layer2.0.bn1.running_var", "_orig_mod.backbone.backbone.layer2.0.conv2.weight", "_orig_mod.backbone.backbone.layer2.0.bn2.weight", "_orig_mod.backbone.backbone.layer2.0.bn2.bias", "_orig_mod.backbone.backbone.layer2.0.bn2.running_mean", "_orig_mod.backbone.backbone.layer2.0.bn2.running_var", "_orig_mod.backbone.backbone.layer2.0.downsample.0.weight", "_orig_mod.backbone.backbone.layer2.0.downsample.1.weight", "_orig_mod.backbone.backbone.layer2.0.downsample.1.bias", "_orig_mod.backbone.backbone.layer2.0.downsample.1.running_mean", "_orig_mod.backbone.backbone.layer2.0.downsample.1.running_var", "_orig_mod.backbone.backbone.layer2.1.conv1.weight", "_orig_mod.backbone.backbone.layer2.1.bn1.weight", "_orig_mod.backbone.backbone.layer2.1.bn1.bias", "_orig_mod.backbone.backbone.layer2.1.bn1.running_mean", "_orig_mod.backbone.backbone.layer2.1.bn1.running_var", "_orig_mod.backbone.backbone.layer2.1.conv2.weight", "_orig_mod.backbone.backbone.layer2.1.bn2.weight", "_orig_mod.backbone.backbone.layer2.1.bn2.bias", "_orig_mod.backbone.backbone.layer2.1.bn2.running_mean", "_orig_mod.backbone.backbone.layer2.1.bn2.running_var", "_orig_mod.backbone.backbone.layer3.0.conv1.weight", "_orig_mod.backbone.backbone.layer3.0.bn1.weight", "_orig_mod.backbone.backbone.layer3.0.bn1.bias", "_orig_mod.backbone.backbone.layer3.0.bn1.running_mean", "_orig_mod.backbone.backbone.layer3.0.bn1.running_var", "_orig_mod.backbone.backbone.layer3.0.conv2.weight", "_orig_mod.backbone.backbone.layer3.0.bn2.weight", "_orig_mod.backbone.backbone.layer3.0.bn2.bias", "_orig_mod.backbone.backbone.layer3.0.bn2.running_mean", "_orig_mod.backbone.backbone.layer3.0.bn2.running_var", "_orig_mod.backbone.backbone.layer3.0.downsample.0.weight", "_orig_mod.backbone.backbone.layer3.0.downsample.1.weight", "_orig_mod.backbone.backbone.layer3.0.downsample.1.bias", "_orig_mod.backbone.backbone.layer3.0.downsample.1.running_mean", "_orig_mod.backbone.backbone.layer3.0.downsample.1.running_var", "_orig_mod.backbone.backbone.layer3.1.conv1.weight", "_orig_mod.backbone.backbone.layer3.1.bn1.weight", "_orig_mod.backbone.backbone.layer3.1.bn1.bias", "_orig_mod.backbone.backbone.layer3.1.bn1.running_mean", "_orig_mod.backbone.backbone.layer3.1.bn1.running_var", "_orig_mod.backbone.backbone.layer3.1.conv2.weight", "_orig_mod.backbone.backbone.layer3.1.bn2.weight", "_orig_mod.backbone.backbone.layer3.1.bn2.bias", "_orig_mod.backbone.backbone.layer3.1.bn2.running_mean", "_orig_mod.backbone.backbone.layer3.1.bn2.running_var", "_orig_mod.backbone.backbone.layer4.0.conv1.weight", "_orig_mod.backbone.backbone.layer4.0.bn1.weight", "_orig_mod.backbone.backbone.layer4.0.bn1.bias", "_orig_mod.backbone.backbone.layer4.0.bn1.running_mean", "_orig_mod.backbone.backbone.layer4.0.bn1.running_var", "_orig_mod.backbone.backbone.layer4.0.conv2.weight", "_orig_mod.backbone.backbone.layer4.0.bn2.weight", "_orig_mod.backbone.backbone.layer4.0.bn2.bias", "_orig_mod.backbone.backbone.layer4.0.bn2.running_mean", "_orig_mod.backbone.backbone.layer4.0.bn2.running_var", "_orig_mod.backbone.backbone.layer4.0.downsample.0.weight", "_orig_mod.backbone.backbone.layer4.0.downsample.1.weight", "_orig_mod.backbone.backbone.layer4.0.downsample.1.bias", "_orig_mod.backbone.backbone.layer4.0.downsample.1.running_mean", "_orig_mod.backbone.backbone.layer4.0.downsample.1.running_var", "_orig_mod.backbone.backbone.layer4.1.conv1.weight", "_orig_mod.backbone.backbone.layer4.1.bn1.weight", "_orig_mod.backbone.backbone.layer4.1.bn1.bias", "_orig_mod.backbone.backbone.layer4.1.bn1.running_mean", "_orig_mod.backbone.backbone.layer4.1.bn1.running_var", "_orig_mod.backbone.backbone.layer4.1.conv2.weight", "_orig_mod.backbone.backbone.layer4.1.bn2.weight", "_orig_mod.backbone.backbone.layer4.1.bn2.bias", "_orig_mod.backbone.backbone.layer4.1.bn2.running_mean", "_orig_mod.backbone.backbone.layer4.1.bn2.running_var", "_orig_mod.backbone.backbone.fc.weight", "_orig_mod.backbone.backbone.fc.bias", "_orig_mod.backbone.bi_inter_models.0.norm1.weight", "_orig_mod.backbone.bi_inter_models.0.norm1.bias", "_orig_mod.backbone.bi_inter_models.0.attn.logit_scale", "_orig_mod.backbone.bi_inter_models.0.attn.q_bias", "_orig_mod.backbone.bi_inter_models.0.attn.v_bias", "_orig_mod.backbone.bi_inter_models.0.attn.relative_coords_table", "_orig_mod.backbone.bi_inter_models.0.attn.relative_position_index", "_orig_mod.backbone.bi_inter_models.0.attn.cpb_mlp.0.weight", "_orig_mod.backbone.bi_inter_models.0.attn.cpb_mlp.0.bias", "_orig_mod.backbone.bi_inter_models.0.attn.cpb_mlp.2.weight", "_orig_mod.backbone.bi_inter_models.0.attn.qkv.weight", "_orig_mod.backbone.bi_inter_models.0.attn.proj.weight", "_orig_mod.backbone.bi_inter_models.0.attn.proj.bias", "_orig_mod.backbone.bi_inter_models.0.norm2.weight", "_orig_mod.backbone.bi_inter_models.0.norm2.bias", "_orig_mod.backbone.bi_inter_models.0.mlp.fc1.weight", "_orig_mod.backbone.bi_inter_models.0.mlp.fc1.bias", "_orig_mod.backbone.bi_inter_models.0.mlp.fc2.weight", "_orig_mod.backbone.bi_inter_models.0.mlp.fc2.bias", "_orig_mod.backbone.bi_inter_models.1.norm1.weight", "_orig_mod.backbone.bi_inter_models.1.norm1.bias", "_orig_mod.backbone.bi_inter_models.1.attn.logit_scale", "_orig_mod.backbone.bi_inter_models.1.attn.q_bias", "_orig_mod.backbone.bi_inter_models.1.attn.v_bias", "_orig_mod.backbone.bi_inter_models.1.attn.relative_coords_table", "_orig_mod.backbone.bi_inter_models.1.attn.relative_position_index", "_orig_mod.backbone.bi_inter_models.1.attn.cpb_mlp.0.weight", "_orig_mod.backbone.bi_inter_models.1.attn.cpb_mlp.0.bias", "_orig_mod.backbone.bi_inter_models.1.attn.cpb_mlp.2.weight", "_orig_mod.backbone.bi_inter_models.1.attn.qkv.weight", "_orig_mod.backbone.bi_inter_models.1.attn.proj.weight", "_orig_mod.backbone.bi_inter_models.1.attn.proj.bias", "_orig_mod.backbone.bi_inter_models.1.norm2.weight", "_orig_mod.backbone.bi_inter_models.1.norm2.bias", "_orig_mod.backbone.bi_inter_models.1.mlp.fc1.weight", "_orig_mod.backbone.bi_inter_models.1.mlp.fc1.bias", "_orig_mod.backbone.bi_inter_models.1.mlp.fc2.weight", "_orig_mod.backbone.bi_inter_models.1.mlp.fc2.bias", "_orig_mod.backbone.bi_inter_models.2.norm1.weight", "_orig_mod.backbone.bi_inter_models.2.norm1.bias", "_orig_mod.backbone.bi_inter_models.2.attn.logit_scale", "_orig_mod.backbone.bi_inter_models.2.attn.q_bias", "_orig_mod.backbone.bi_inter_models.2.attn.v_bias", "_orig_mod.backbone.bi_inter_models.2.attn.relative_coords_table", "_orig_mod.backbone.bi_inter_models.2.attn.relative_position_index", "_orig_mod.backbone.bi_inter_models.2.attn.cpb_mlp.0.weight", "_orig_mod.backbone.bi_inter_models.2.attn.cpb_mlp.0.bias", "_orig_mod.backbone.bi_inter_models.2.attn.cpb_mlp.2.weight", "_orig_mod.backbone.bi_inter_models.2.attn.qkv.weight", "_orig_mod.backbone.bi_inter_models.2.attn.proj.weight", "_orig_mod.backbone.bi_inter_models.2.attn.proj.bias", "_orig_mod.backbone.bi_inter_models.2.norm2.weight", "_orig_mod.backbone.bi_inter_models.2.norm2.bias", "_orig_mod.backbone.bi_inter_models.2.mlp.fc1.weight", "_orig_mod.backbone.bi_inter_models.2.mlp.fc1.bias", "_orig_mod.backbone.bi_inter_models.2.mlp.fc2.weight", "_orig_mod.backbone.bi_inter_models.2.mlp.fc2.bias", "_orig_mod.mid_convs.0.0.weight", "_orig_mod.mid_convs.0.0.bias", "_orig_mod.mid_convs.1.0.weight", "_orig_mod.mid_convs.1.0.bias", "_orig_mod.mid_convs.2.0.weight", "_orig_mod.mid_convs.2.0.bias", "_orig_mod.mid_convs.3.0.weight", "_orig_mod.mid_convs.3.0.bias", "_orig_mod.edger.conv.weight", "_orig_mod.edger.conv.bias", "_orig_mod.ifa_fuse.pes.0.row_embed.weight", "_orig_mod.ifa_fuse.pes.0.col_embed.weight", "_orig_mod.ifa_fuse.pes.1.row_embed.weight", "_orig_mod.ifa_fuse.pes.1.col_embed.weight", "_orig_mod.ifa_fuse.pes.2.row_embed.weight", "_orig_mod.ifa_fuse.pes.2.col_embed.weight", "_orig_mod.ifa_fuse.pes.3.row_embed.weight", "_orig_mod.ifa_fuse.pes.3.col_embed.weight", "_orig_mod.ifa_fuse.imnet.0.weight", "_orig_mod.ifa_fuse.imnet.0.bias", "_orig_mod.ifa_fuse.imnet.1.weight", "_orig_mod.ifa_fuse.imnet.1.bias", "_orig_mod.ifa_fuse.imnet.1.running_mean", "_orig_mod.ifa_fuse.imnet.1.running_var", "_orig_mod.classifier.0.weight", "_orig_mod.classifier.1.weight", "_orig_mod.classifier.1.bias", "_orig_mod.classifier.1.running_mean", "_orig_mod.classifier.1.running_var", "_orig_mod.classifier.3.weight", "_orig_mod.classifier.3.bias".
Unexpected key(s) in state_dict: "backbone.backbone.conv1.weight", "backbone.backbone.bn1.weight", "backbone.backbone.bn1.bias", "backbone.backbone.bn1.running_mean", "backbone.backbone.bn1.running_var", "backbone.backbone.bn1.num_batches_tracked", "backbone.backbone.layer1.0.conv1.weight", "backbone.backbone.layer1.0.bn1.weight", "backbone.backbone.layer1.0.bn1.bias", "backbone.backbone.layer1.0.bn1.running_mean", "backbone.backbone.layer1.0.bn1.running_var", "backbone.backbone.layer1.0.bn1.num_batches_tracked", "backbone.backbone.layer1.0.conv2.weight", "backbone.backbone.layer1.0.bn2.weight", "backbone.backbone.layer1.0.bn2.bias", "backbone.backbone.layer1.0.bn2.running_mean", "backbone.backbone.layer1.0.bn2.running_var", "backbone.backbone.layer1.0.bn2.num_batches_tracked", "backbone.backbone.layer1.1.conv1.weight", "backbone.backbone.layer1.1.bn1.weight", "backbone.backbone.layer1.1.bn1.bias", "backbone.backbone.layer1.1.bn1.running_mean", "backbone.backbone.layer1.1.bn1.running_var", "backbone.backbone.layer1.1.bn1.num_batches_tracked", "backbone.backbone.layer1.1.conv2.weight", "backbone.backbone.layer1.1.bn2.weight", "backbone.backbone.layer1.1.bn2.bias", "backbone.backbone.layer1.1.bn2.running_mean", "backbone.backbone.layer1.1.bn2.running_var", "backbone.backbone.layer1.1.bn2.num_batches_tracked", "backbone.backbone.layer2.0.conv1.weight", "backbone.backbone.layer2.0.bn1.weight", "backbone.backbone.layer2.0.bn1.bias", "backbone.backbone.layer2.0.bn1.running_mean", "backbone.backbone.layer2.0.bn1.running_var", "backbone.backbone.layer2.0.bn1.num_batches_tracked", "backbone.backbone.layer2.0.conv2.weight", "backbone.backbone.layer2.0.bn2.weight", "backbone.backbone.layer2.0.bn2.bias", "backbone.backbone.layer2.0.bn2.running_mean", "backbone.backbone.layer2.0.bn2.running_var", "backbone.backbone.layer2.0.bn2.num_batches_tracked", "backbone.backbone.layer2.0.downsample.0.weight", "backbone.backbone.layer2.0.downsample.1.weight", "backbone.backbone.layer2.0.downsample.1.bias", "backbone.backbone.layer2.0.downsample.1.running_mean", "backbone.backbone.layer2.0.downsample.1.running_var", "backbone.backbone.layer2.0.downsample.1.num_batches_tracked", "backbone.backbone.layer2.1.conv1.weight", "backbone.backbone.layer2.1.bn1.weight", "backbone.backbone.layer2.1.bn1.bias", "backbone.backbone.layer2.1.bn1.running_mean", "backbone.backbone.layer2.1.bn1.running_var", "backbone.backbone.layer2.1.bn1.num_batches_tracked", "backbone.backbone.layer2.1.conv2.weight", "backbone.backbone.layer2.1.bn2.weight", "backbone.backbone.layer2.1.bn2.bias", "backbone.backbone.layer2.1.bn2.running_mean", "backbone.backbone.layer2.1.bn2.running_var", "backbone.backbone.layer2.1.bn2.num_batches_tracked", "backbone.backbone.layer3.0.conv1.weight", "backbone.backbone.layer3.0.bn1.weight", "backbone.backbone.layer3.0.bn1.bias", "backbone.backbone.layer3.0.bn1.running_mean", "backbone.backbone.layer3.0.bn1.running_var", "backbone.backbone.layer3.0.bn1.num_batches_tracked", "backbone.backbone.layer3.0.conv2.weight", "backbone.backbone.layer3.0.bn2.weight", "backbone.backbone.layer3.0.bn2.bias", "backbone.backbone.layer3.0.bn2.running_mean", "backbone.backbone.layer3.0.bn2.running_var", "backbone.backbone.layer3.0.bn2.num_batches_tracked", "backbone.backbone.layer3.0.downsample.0.weight", "backbone.backbone.layer3.0.downsample.1.weight", "backbone.backbone.layer3.0.downsample.1.bias", "backbone.backbone.layer3.0.downsample.1.running_mean", "backbone.backbone.layer3.0.downsample.1.running_var", "backbone.backbone.layer3.0.downsample.1.num_batches_tracked", "backbone.backbone.layer3.1.conv1.weight", "backbone.backbone.layer3.1.bn1.weight", "backbone.backbone.layer3.1.bn1.bias", "backbone.backbone.layer3.1.bn1.running_mean", "backbone.backbone.layer3.1.bn1.running_var", "backbone.backbone.layer3.1.bn1.num_batches_tracked", "backbone.backbone.layer3.1.conv2.weight", "backbone.backbone.layer3.1.bn2.weight", "backbone.backbone.layer3.1.bn2.bias", "backbone.backbone.layer3.1.bn2.running_mean", "backbone.backbone.layer3.1.bn2.running_var", "backbone.backbone.layer3.1.bn2.num_batches_tracked", "backbone.backbone.layer4.0.conv1.weight", "backbone.backbone.layer4.0.bn1.weight", "backbone.backbone.layer4.0.bn1.bias", "backbone.backbone.layer4.0.bn1.running_mean", "backbone.backbone.layer4.0.bn1.running_var", "backbone.backbone.layer4.0.bn1.num_batches_tracked", "backbone.backbone.layer4.0.conv2.weight", "backbone.backbone.layer4.0.bn2.weight", "backbone.backbone.layer4.0.bn2.bias", "backbone.backbone.layer4.0.bn2.running_mean", "backbone.backbone.layer4.0.bn2.running_var", "backbone.backbone.layer4.0.bn2.num_batches_tracked", "backbone.backbone.layer4.0.downsample.0.weight", "backbone.backbone.layer4.0.downsample.1.weight", "backbone.backbone.layer4.0.downsample.1.bias", "backbone.backbone.layer4.0.downsample.1.running_mean", "backbone.backbone.layer4.0.downsample.1.running_var", "backbone.backbone.layer4.0.downsample.1.num_batches_tracked", "backbone.backbone.layer4.1.conv1.weight", "backbone.backbone.layer4.1.bn1.weight", "backbone.backbone.layer4.1.bn1.bias", "backbone.backbone.layer4.1.bn1.running_mean", "backbone.backbone.layer4.1.bn1.running_var", "backbone.backbone.layer4.1.bn1.num_batches_tracked", "backbone.backbone.layer4.1.conv2.weight", "backbone.backbone.layer4.1.bn2.weight", "backbone.backbone.layer4.1.bn2.bias", "backbone.backbone.layer4.1.bn2.running_mean", "backbone.backbone.layer4.1.bn2.running_var", "backbone.backbone.layer4.1.bn2.num_batches_tracked", "backbone.backbone.fc.weight", "backbone.backbone.fc.bias", "backbone.bi_inter_models.0.norm1.weight", "backbone.bi_inter_models.0.norm1.bias", "backbone.bi_inter_models.0.attn.logit_scale", "backbone.bi_inter_models.0.attn.q_bias", "backbone.bi_inter_models.0.attn.v_bias", "backbone.bi_inter_models.0.attn.relative_coords_table", "backbone.bi_inter_models.0.attn.relative_position_index", "backbone.bi_inter_models.0.attn.cpb_mlp.0.weight", "backbone.bi_inter_models.0.attn.cpb_mlp.0.bias", "backbone.bi_inter_models.0.attn.cpb_mlp.2.weight", "backbone.bi_inter_models.0.attn.qkv.weight", "backbone.bi_inter_models.0.attn.proj.weight", "backbone.bi_inter_models.0.attn.proj.bias", "backbone.bi_inter_models.0.norm2.weight", "backbone.bi_inter_models.0.norm2.bias", "backbone.bi_inter_models.0.mlp.fc1.weight", "backbone.bi_inter_models.0.mlp.fc1.bias", "backbone.bi_inter_models.0.mlp.fc2.weight", "backbone.bi_inter_models.0.mlp.fc2.bias", "backbone.bi_inter_models.1.norm1.weight", "backbone.bi_inter_models.1.norm1.bias", "backbone.bi_inter_models.1.attn.logit_scale", "backbone.bi_inter_models.1.attn.q_bias", "backbone.bi_inter_models.1.attn.v_bias", "backbone.bi_inter_models.1.attn.relative_coords_table", "backbone.bi_inter_models.1.attn.relative_position_index", "backbone.bi_inter_models.1.attn.cpb_mlp.0.weight", "backbone.bi_inter_models.1.attn.cpb_mlp.0.bias", "backbone.bi_inter_models.1.attn.cpb_mlp.2.weight", "backbone.bi_inter_models.1.attn.qkv.weight", "backbone.bi_inter_models.1.attn.proj.weight", "backbone.bi_inter_models.1.attn.proj.bias", "backbone.bi_inter_models.1.norm2.weight", "backbone.bi_inter_models.1.norm2.bias", "backbone.bi_inter_models.1.mlp.fc1.weight", "backbone.bi_inter_models.1.mlp.fc1.bias", "backbone.bi_inter_models.1.mlp.fc2.weight", "backbone.bi_inter_models.1.mlp.fc2.bias", "backbone.bi_inter_models.2.norm1.weight", "backbone.bi_inter_models.2.norm1.bias", "backbone.bi_inter_models.2.attn.logit_scale", "backbone.bi_inter_models.2.attn.q_bias", "backbone.bi_inter_models.2.attn.v_bias", "backbone.bi_inter_models.2.attn.relative_coords_table", "backbone.bi_inter_models.2.attn.relative_position_index", "backbone.bi_inter_models.2.attn.cpb_mlp.0.weight", "backbone.bi_inter_models.2.attn.cpb_mlp.0.bias", "backbone.bi_inter_models.2.attn.cpb_mlp.2.weight", "backbone.bi_inter_models.2.attn.qkv.weight", "backbone.bi_inter_models.2.attn.proj.weight", "backbone.bi_inter_models.2.attn.proj.bias", "backbone.bi_inter_models.2.norm2.weight", "backbone.bi_inter_models.2.norm2.bias", "backbone.bi_inter_models.2.mlp.fc1.weight", "backbone.bi_inter_models.2.mlp.fc1.bias", "backbone.bi_inter_models.2.mlp.fc2.weight", "backbone.bi_inter_models.2.mlp.fc2.bias", "mid_convs.0.0.weight", "mid_convs.0.0.bias", "mid_convs.1.0.weight", "mid_convs.1.0.bias", "mid_convs.2.0.weight", "mid_convs.2.0.bias", "mid_convs.3.0.weight", "mid_convs.3.0.bias", "edger.conv.weight", "edger.conv.bias", "ifa_fuse.pes.0.row_embed.weight", "ifa_fuse.pes.0.col_embed.weight", "ifa_fuse.pes.1.row_embed.weight", "ifa_fuse.pes.1.col_embed.weight", "ifa_fuse.pes.2.row_embed.weight", "ifa_fuse.pes.2.col_embed.weight", "ifa_fuse.pes.3.row_embed.weight", "ifa_fuse.pes.3.col_embed.weight", "ifa_fuse.imnet.0.weight", "ifa_fuse.imnet.0.bias", "ifa_fuse.imnet.1.weight", "ifa_fuse.imnet.1.bias", "ifa_fuse.imnet.1.running_mean", "ifa_fuse.imnet.1.running_var", "ifa_fuse.imnet.1.num_batches_tracked", "classifier.0.weight", "classifier.1.weight", "classifier.1.bias", "classifier.1.running_mean", "classifier.1.running_var", "classifier.1.num_batches_tracked", "classifier.3.weight", "classifier.3.bias".

Which is indicating a mismatch between the provided checkpoint and the expected one. This is true for the models.evaluator.CDEvaluator as well as models.basic_model.CDEvaluator. Others were not tested.

Recommend Projects

React

A declarative, efficient, and flexible JavaScript library for building user interfaces.
Vue.js

🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
Typescript

TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
TensorFlow

An Open Source Machine Learning Framework for Everyone
Django

The Web framework for perfectionists with deadlines.
Laravel

A PHP framework for web artisans
D3

Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

javascript

JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
web

Some thing interesting about web. New door for the world.
server

A server is a program made to process requests and deliver data to clients.
Machine learning

Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Visualization

Some thing interesting about visualization, use data art
Game

Some thing interesting about game, make everyone happy.

Recommend Org

Facebook

We are working to build community through open source technology. NB: members must have two-factor auth.
Microsoft

Open source projects and samples from Microsoft.
Google

Google ❤️ Open Source for everyone.
Alibaba

Alibaba Open Source for everyone
D3

Data-Driven Documents codes.
Tencent

China tencent open source team.