bupt-ai-cz / bci

BCI: Breast Cancer Immunohistochemical Image Generation through Pyramid Pix2pix

MIC Group

Homepage | Google Scholar | Researchgate

⚡News

• We released the code of ProML, and the paper was accepted by IJCAI 2023.

• We released the code of PyramidPix2pix, and the paper was accepted by 2022 CVPR workshop.

• We released the code of PGDF, which is the new SOTA of image classification with noisy labels.

• We released the code of HSA-NRL, and the paper was accepted by IEEE Transactions on Medical Imaging (TMI).

• We released the code of HHCL-ReID, which is the new SOTA of unsupervised person re-identification.

• We released the code of BALNMP, and the paper was accepted by Frontiers in Oncology.

⭐Ours Repositories

BCI	PGDF	HSA-NRL	HHCL-ReID	BALNMP	LLVIP	Meta Self-Learning	IAST	CAC-UNet

bci's Issues

Could you release the registration codes?

Hi,

Could you release the registration codes, so that we can try your algorithm correctly on a custom dataset?

I have training weights, how to perform prediction on unseen images. If possible please share the code snippet.

Wrong image extension

I cannot open any image from dataset by double clicking unless I replace .png with .jpg.
I use Ubuntu 20.04.

AttributeError: 'Sequential' object has no attribute 'model'

I have test images, downloaded BCI pretrained model and use the following command:

!python test.py --dataroot /kaggle/input/bci-img2img/BCI_for_GrandChallenge-20230210T115047Z-001/BCI_for_GrandChallenge/test --gpu_ids 0

However, I get an AttributeError, here is the output:

/bin/bash: /opt/conda/lib/libtinfo.so.6: no version information available (required by /bin/bash)
----------------- Options ---------------
             aspect_ratio: 1.0                           
               batch_size: 2                             
          checkpoints_dir: ./checkpoints                 
                crop_size: 256                           
                 dataroot: /kaggle/input/bci-img2img/BCI_for_GrandChallenge-20230210T115047Z-001/BCI_for_GrandChallenge/test	[default: ./datasets/BCI]
             dataset_mode: aligned                       
                direction: AtoB                          
          display_winsize: 256                           
                    epoch: latest                        
                     eval: False                         
                  gpu_ids: 0                             
                init_gain: 0.02                          
                init_type: normal                        
                 input_nc: 3                             
                  isTrain: False                         	[default: None]
                load_iter: 0                             	[default: 0]
                load_size: 320                           
         max_dataset_size: inf                           
                    model: pix2pix                       
               n_layers_D: 3                             
                     name: pyramidpix2pix                
                      ndf: 64                            
                     netD: basic                         
                     netG: resnet_9blocks                
                      ngf: 64                            
               no_dropout: False                         
                  no_flip: False                         
                     norm: batch                         
                 num_test: 1000                          
              num_threads: 4                             
                output_nc: 3                             
                  pattern: L1_L2_L3_L4                   
                    phase: test                          
               preprocess: scale_width_and_midcrop       
              results_dir: ./results/                    
           serial_batches: False                         
                   suffix:                               
                  verbose: False                         
----------------- End -------------------
dataset [AlignedDataset] was created
initialize network with normal
model [Pix2PixModel] was created
loading the model from ./checkpoints/pyramidpix2pix/latest_net_G.pth
Traceback (most recent call last):
  File "test.py", line 47, in <module>
    model.setup(opt)               # regular setup: load and print networks; create schedulers
  File "/kaggle/working/BCI-main/PyramidPix2pix/models/base_model.py", line 88, in setup
    self.load_networks(load_suffix)
  File "/kaggle/working/BCI-main/PyramidPix2pix/models/base_model.py", line 198, in load_networks
    self.__patch_instance_norm_state_dict(state_dict, net, key.split('.'))
  File "/kaggle/working/BCI-main/PyramidPix2pix/models/base_model.py", line 174, in __patch_instance_norm_state_dict
    self.__patch_instance_norm_state_dict(state_dict, getattr(module, key), keys, i + 1)
  File "/kaggle/working/BCI-main/PyramidPix2pix/models/base_model.py", line 174, in __patch_instance_norm_state_dict
    self.__patch_instance_norm_state_dict(state_dict, getattr(module, key), keys, i + 1)
  File "/opt/conda/lib/python3.7/site-packages/torch/nn/modules/module.py", line 1208, in __getattr__
    type(self).__name__, name))
AttributeError: 'Sequential' object has no attribute 'model'

Could someone help me with this? Thank you!

visdom无法正常显示训练loss和训练过程输出图像

原始数据集下载问题

您好，我在挑战赛官网上注册后，根据主办方提供的数据集下载主页登记了个人信息，但是点击下载按钮的时候无法进行正常下载，提示Error! There is some issue with the server.请问如何获取数据集呢？非常感谢！

evaluate

how to evaluate
here is my result"there is something wrong with 00255_test_0_fake_B.png
there is something wrong with 00256_test_2+_fake_B.png
there is something wrong with 00257_test_1+_fake_B.png
there is something wrong with 00258_test_2+_fake_B.png"

请问如何下载数据集呢？

请问如何下载数据集呢？

Which part of the dataset is for validation

    In paper "Breast Cancer Immunohistochemical Image Generation: a Benchmark Dataset and Challenge Review", it is menntioned that "The dataset used in this challenge consists of 3396 pairs of the training set images, 500 pairs of the validation set images", but I can't  find any information for the val set both on the official website https://bci.grand-challenge.org/ and the dataset

    So, which part in the train fold is for validation? Or just split the dataset randomly

原始数据集下载问题

您好，我在BCI数据集官网投递多次申请后未收到回复邮件及下载链接，您可以在空余时间再度分享下吗，或者发我邮箱：[email protected], 或者[email protected]

如何进行测试呢？

当我使用预训练模型进行推理的时候发生了错误：
torch.nn.modules.module.ModuleAttributeError: 'Sequential' object has no attribute 'model'

Requst pretrained checkpoints

Hi, I am very interested in your work. Recently, I am reading codes and I want to test some samples. Where can I download those pretrained checkpoints? I would appreciate it if you could provide pretrained weights.