[Project] add Bactteria_Dataset project in dev-1.x #2568

tianbinli · 2023-02-07T04:00:50Z

Thanks for your contribution and we appreciate it a lot. The following instructions would make your pull request more healthy and more easily get feedback. If you do not understand some items, don't worry, just make the pull request and seek help from maintainers.

Motivation

Please describe the motivation of this PR and the goal you want to achieve through this PR.

Modification

Please briefly describe what modification is made in this PR.

BC-breaking (Optional)

Does the modification introduce changes that break the backward-compatibility of the downstream repos?
If so, please describe how it breaks the compatibility and how the downstream projects should modify their code to keep compatibility with this PR.

Use cases (Optional)

If this PR introduces a new feature, it is better to list some use cases here, and update the documentation.

Checklist

Pre-commit or other linting tools are used to fix the potential lint issues.
The modification is covered by complete unit tests. If not, please add more unit test to ensure the correctness.
If the modification has potential influence on downstream projects, this PR should be tested with downstream projects, like MMDet or MMDet3D.
The documentation has been modified accordingly, like docstring or example tutorials.

projects/Bactteria_Dataset/README.md

projects/Bactteria_Dataset/configs/Bactteria_Det_unet_0.0001_CrossEntropyLoss.py

Ezra-Yu · 2023-02-09T02:10:40Z

projects/Bactteria_Dataset/README.md

+
+### Bactteria detection with darkfield microscopy Dataset
+
+|     Method      | Backbone | Crop Size |   lr   | mIoU  | mDice |                                                                        config                                                                        |


It would be more convincing to provide some logs, if you don't have a server, you can put them on GitHub, something like https://github.com/Ezra-Yu/MY_STORE/releases/tag/v0.0.1

Ezra-Yu · 2023-02-09T02:16:02Z

projects/Bactteria_Dataset/README.md

+
+### Dataset preparing
+
+Preparing `Bactteria detection with darkfield microscopy Dataset` dataset in following format as below.


It is doubtful whether this directory is the result of processing before or after using the script. As the random_split.py is in the below.

...teria_detection/configs/fcn-unet-s5-d16_unet_1xb16-0.0001-20k_bactteria-detection-512x512.py

projects/bactteria_detection/tools/prepare_dataset.py

projects/bactteria_detection/datasets/bactteria_detection_dataset.py

projects/bactteria_detection/README.md

Dev 1.x

projects/medical/2d_image/microscopy_images/bactteria_detection/README.md

MeowZheng · 2023-02-21T13:53:46Z

projects/medical/2d_image/microscopy_images/bactteria_detection/README.md

+To train on multiple GPUs, e.g. 8 GPUs, run the following command:
+
+```shell
+mim train mmseg ./configs/${CONFIG_PATH}  --launcher pytorch --gpus 8
+```


From this config file name, is there no need to use 8 GPUs to train?

MeowZheng · 2023-02-21T13:55:15Z

projects/medical/2d_image/microscopy_images/bactteria_detection/tools/prepare_dataset.py

+all_imgs = glob.glob('data/bactteria_detection/Bacteria_detection_with_\
+darkfield_microscopy_datasets/images/*' + img_suffix)  # noqa


Suggested change

all_imgs = glob.glob('data/bactteria_detection/Bacteria_detection_with_\

darkfield_microscopy_datasets/images/*' + img_suffix) # noqa

all_imgs = glob.glob('data/bactteria_detection/Bacteria_detection_with_darkfield_microscopy_datasets/images/*' + img_suffix) # noqa

...teria_detection/configs/fcn-unet-s5-d16_unet_1xb16-0.0001-20k_bactteria-detection-512x512.py

projects/medical/2d_image/microscopy_images/bactteria_detection/tools/prepare_dataset.py

projects/medical/2d_image/microscopy_images/bactteria_detection/README.md

Dev 1.x

projects/medical/2d_image/microscopy_images/bactteria_detection/README.md

MeowZheng · 2023-03-06T11:21:14Z

projects/medical/2d_image/microscopy_images/bactteria_detection/README.md

+### Training commands
+
+```shell
+mim train mmseg ./configs/${CONFIG_PATH}


Suggested change

mim train mmseg ./configs/${CONFIG_PATH}

mim train mmseg ./configs/${CONFIG_FILE}

is FILE more precise than PATH? as ./configs/ is path

projects/medical/2d_image/tools/split_seg_dataset.py

MeowZheng · 2023-03-06T11:36:56Z

projects/medical/2d_image/microscopy_images/bactteria_detection/README.md

+
+### Bactteria detection with darkfield microscopy
+
+|     Method      | Backbone | Crop Size |   lr   | mIoU  | mDice |                                                                                                      config                                                                                                      |


do you share the pre-trained weights with other users?

MeowZheng · 2023-03-06T11:39:02Z

...dical/2d_image/microscopy_images/bactteria_detection/datasets/bactteria-detection_dataset.py

+                 reduce_zero_label=False,
+                 **kwargs) -> None:
+        super().__init__(
+            img_suffix=img_suffix,
+            seg_map_suffix=seg_map_suffix,
+            reduce_zero_label=reduce_zero_label,


If you really want to fix reduce_zero_label, just use hard code.

Suggested change

reduce_zero_label=False,

**kwargs) -> None:

super().__init__(

img_suffix=img_suffix,

seg_map_suffix=seg_map_suffix,

reduce_zero_label=reduce_zero_label,

**kwargs) -> None:

super().__init__(

img_suffix=img_suffix,

seg_map_suffix=seg_map_suffix,

reduce_zero_label=False,

MeowZheng · 2023-03-06T11:39:55Z

...dical/2d_image/microscopy_images/bactteria_detection/datasets/bactteria-detection_dataset.py

+        reduce_zero_label (bool): Whether to mark label zero as ignored.
+            Default to False.


Suggested change

reduce_zero_label (bool): Whether to mark label zero as ignored.

Default to False.

projects/medical/2d_image/microscopy_images/bactteria_detection/tools/prepare_dataset.py

projects/medical/2d_image/microscopy_images/bactteria_detection/README.md

…g directory

…mentation into PR_dev-1.x

MeowZheng · 2023-03-07T15:13:19Z

projects/medical/2d_image/microscopy_images/bactteria_detection/README.md

+- download dataset from [here](https://tianchi.aliyun.com/dataset/94411) and decompress data to path `'data/'`.
+- run script `"python tools/prepare_dataset.py"` to format data and change folder structure as below.
+- run script `"python ../../tools/split_seg_dataset.py"` to split dataset and generate `train.txt`, `val.txt` and `test.txt`. If the label of official validation set and test set can't be obtained, we generate `train.txt` and `val.txt` from the training set randomly.
+
+```none
+  mmsegmentation


I think it should add more details about

the path about dataset after decompress, as you just hard code the data_root in tools/prepare_dataset.py

the relationship between the below table of contents and these commands

dataset split ratio

MeowZheng · 2023-03-07T15:20:12Z

projects/medical/2d_image/microscopy_images/bactteria_detection/README.md

+### Dataset preparing
+
+- download dataset from [here](https://tianchi.aliyun.com/dataset/94411) and decompress data to path `'data/'`.
+- run script `"python tools/prepare_dataset.py"` to format data and change folder structure as below.


Suggested change

- run script `"python tools/prepare_dataset.py"` to format data and change folder structure as below.

- run script `python tools/prepare_dataset.py` to format data and change folder structure as below.

MeowZheng · 2023-03-07T15:20:22Z

projects/medical/2d_image/microscopy_images/bactteria_detection/README.md

+
+- download dataset from [here](https://tianchi.aliyun.com/dataset/94411) and decompress data to path `'data/'`.
+- run script `"python tools/prepare_dataset.py"` to format data and change folder structure as below.
+- run script `"python ../../tools/split_seg_dataset.py"` to split dataset and generate `train.txt`, `val.txt` and `test.txt`. If the label of official validation set and test set can't be obtained, we generate `train.txt` and `val.txt` from the training set randomly.


Suggested change

- run script `"python ../../tools/split_seg_dataset.py"` to split dataset and generate `train.txt`, `val.txt` and `test.txt`. If the label of official validation set and test set can't be obtained, we generate `train.txt` and `val.txt` from the training set randomly.

- run script `python ../../tools/split_seg_dataset.py` to split dataset and generate `train.txt`, `val.txt` and `test.txt`. If the label of official validation set and test set can't be obtained, we generate `train.txt` and `val.txt` from the training set randomly.

projects/medical/2d_image/microscopy_images/bactteria_detection/README.md

...edical/2d_image/microscopy_images/bactteria_detection/configs/bactteria-detection_512x512.py

projects/medical/2d_image/microscopy_images/bactteria_detection/tools/prepare_dataset.py

MeowZheng · 2023-03-07T15:32:21Z

projects/medical/2d_image/microscopy_images/bactteria_detection/README.md

+
+## Results
+
+### Bactteria detection with darkfield microscopy


these results are for random test dataset or official val dataset?

…n/README.md

…mentation into PR_dev-1.x

add Bactteria_Dataset project in dev-1.x

aad9275

mm-assistant bot assigned xiexinch Feb 7, 2023

MeowZheng reviewed Feb 7, 2023

View reviewed changes

projects/Bactteria_Dataset/README.md Outdated Show resolved Hide resolved

add Prerequisites

e1295e6

MeowZheng reviewed Feb 8, 2023

View reviewed changes

projects/Bactteria_Dataset/README.md Outdated Show resolved Hide resolved

MeowZheng reviewed Feb 8, 2023

View reviewed changes

projects/Bactteria_Dataset/README.md Outdated Show resolved Hide resolved

Junjun2016 reviewed Feb 8, 2023

View reviewed changes

projects/Bactteria_Dataset/README.md Outdated Show resolved Hide resolved

Ezra-Yu reviewed Feb 9, 2023

View reviewed changes

tianbinli added 2 commits February 10, 2023 19:56

update coinfig file and readme

645f209

delete old project

2794ff6

MeowZheng reviewed Feb 12, 2023

View reviewed changes

...teria_detection/configs/fcn-unet-s5-d16_unet_1xb16-0.0001-20k_bactteria-detection-512x512.py Outdated Show resolved Hide resolved

MeowZheng reviewed Feb 12, 2023

View reviewed changes

projects/bactteria_detection/tools/prepare_dataset.py Outdated Show resolved Hide resolved

MeowZheng reviewed Feb 12, 2023

View reviewed changes

projects/bactteria_detection/datasets/bactteria_detection_dataset.py Outdated Show resolved Hide resolved

MeowZheng reviewed Feb 12, 2023

View reviewed changes

projects/bactteria_detection/datasets/bactteria_detection_dataset.py Outdated Show resolved Hide resolved

tianbinli added 2 commits February 13, 2023 18:00

update readme and add results

9bfb617

rename config file and dataset file in mednode project

e5f4296

MeowZheng added the medical label Feb 17, 2023

add PYTHONPATH info

a29b440

MeowZheng changed the title ~~add Bactteria_Dataset project in dev-1.x~~ [Project] add Bactteria_Dataset project in dev-1.x Feb 20, 2023

MeowZheng reviewed Feb 20, 2023

View reviewed changes

projects/bactteria_detection/README.md Outdated Show resolved Hide resolved

projects/bactteria_detection/README.md Outdated Show resolved Hide resolved

projects/bactteria_detection/README.md Outdated Show resolved Hide resolved

tianbinli and others added 2 commits February 20, 2023 17:55

Merge pull request #3 from open-mmlab/dev-1.x

f7ce6f7

Dev 1.x

change medical project folder structure.

e96c37a

MeowZheng reviewed Feb 21, 2023

View reviewed changes

MeowZheng reviewed Feb 23, 2023

View reviewed changes

projects/medical/2d_image/microscopy_images/bactteria_detection/README.md Outdated Show resolved Hide resolved

tianbinli and others added 3 commits March 3, 2023 16:24

add dataset info to bactteria_detection project

bb438e8

format bactteria_detection project

4ace6f6

Merge pull request #5 from open-mmlab/dev-1.x

b519ea9

Dev 1.x

MeowZheng reviewed Mar 6, 2023

View reviewed changes

projects/medical/2d_image/microscopy_images/bactteria_detection/README.md Outdated Show resolved Hide resolved

format bactteria detection dataset

e97a6a2

tianbinli and others added 7 commits March 6, 2023 21:29

add model log and ckpt

d9d81b0

Delete projects/medical/2d_image/histopathology/breast_cancer_cell_se…

f0066ed

…g directory

fix reduce_zero_label=False

113583e

fix reduce_zero_label=False

d514ef0

Merge branch 'PR_dev-1.x' of https://github.com/ForeverBeliever/mmseg…

a536e7d

…mentation into PR_dev-1.x

fix reduce_zero_label=False

f4df810

fix reduce_zero_label=False

ab45fbb

MeowZheng reviewed Mar 7, 2023

View reviewed changes

tianbinli and others added 6 commits March 10, 2023 14:58

refine the introduction in the README.md

6327629

Update projects/medical/2d_image/microscopy_images/bactteria_detectio…

86c6698

…n/README.md

add dataset split info

ad0edb4

Merge branch 'PR_dev-1.x' of https://github.com/ForeverBeliever/mmseg…

651879e

…mentation into PR_dev-1.x

Merge remote-tracking branch 'upstream/dev-1.x' into PR_dev-1.x

b9bcd53

--fix=reset python path

de54e58

xiexinch approved these changes May 6, 2023

View reviewed changes

xiexinch merged commit b299120 into open-mmlab:dev-1.x May 6, 2023
9 of 11 checks passed

nahidnazifi87 pushed a commit to nahidnazifi87/mmsegmentation_playground that referenced this pull request Apr 5, 2024

[Project] add Bactteria_Dataset project in dev-1.x (open-mmlab#2568)

b40efb8

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

[Project] add Bactteria_Dataset project in dev-1.x #2568

[Project] add Bactteria_Dataset project in dev-1.x #2568

tianbinli commented Feb 7, 2023

Ezra-Yu Feb 9, 2023

Ezra-Yu Feb 9, 2023

MeowZheng Feb 21, 2023

MeowZheng Feb 21, 2023

MeowZheng Mar 6, 2023

MeowZheng Mar 6, 2023

MeowZheng Mar 6, 2023

MeowZheng Mar 6, 2023

MeowZheng Mar 7, 2023

MeowZheng Mar 7, 2023

MeowZheng Mar 7, 2023

MeowZheng Mar 7, 2023 •

edited


		### Bactteria detection with darkfield microscopy Dataset

		\| Method \| Backbone \| Crop Size \| lr \| mIoU \| mDice \| config \|


		### Dataset preparing

		Preparing `Bactteria detection with darkfield microscopy Dataset` dataset in following format as below.

		all_imgs = glob.glob('data/bactteria_detection/Bacteria_detection_with_\
		darkfield_microscopy_datasets/images/*' + img_suffix) # noqa

	mim train mmseg ./configs/${CONFIG_PATH}
	mim train mmseg ./configs/${CONFIG_FILE}

		reduce_zero_label (bool): Whether to mark label zero as ignored.
		Default to False.

	- run script `"python tools/prepare_dataset.py"` to format data and change folder structure as below.
	- run script `python tools/prepare_dataset.py` to format data and change folder structure as below.

	- run script `"python ../../tools/split_seg_dataset.py"` to split dataset and generate `train.txt`, `val.txt` and `test.txt`. If the label of official validation set and test set can't be obtained, we generate `train.txt` and `val.txt` from the training set randomly.
	- run script `python ../../tools/split_seg_dataset.py` to split dataset and generate `train.txt`, `val.txt` and `test.txt`. If the label of official validation set and test set can't be obtained, we generate `train.txt` and `val.txt` from the training set randomly.

[Project] add Bactteria_Dataset project in dev-1.x #2568

[Project] add Bactteria_Dataset project in dev-1.x #2568

Conversation

tianbinli commented Feb 7, 2023

Motivation

Modification

BC-breaking (Optional)

Use cases (Optional)

Checklist

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

MeowZheng Mar 7, 2023 • edited

Choose a reason for hiding this comment

MeowZheng Mar 7, 2023 •

edited