You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@singa.apache.org by zh...@apache.org on 2022/02/22 12:11:39 UTC

[singa] branch dev updated: Create folder and add readme

This is an automated email from the ASF dual-hosted git repository.

zhaojing pushed a commit to branch dev
in repository https://gitbox.apache.org/repos/asf/singa.git


The following commit(s) were added to refs/heads/dev by this push:
     new 0db40cf  Create folder and add readme
     new c8a5c16  Merge pull request #921 from zlheui/bloodmnist-application
0db40cf is described below

commit 0db40cf7120b39eb7b91da31f3b8d098de33ebe3
Author: zhulei <zl...@gmail.com>
AuthorDate: Tue Feb 22 19:42:12 2022 +0800

    Create folder and add readme
---
 examples/demos/Classification/BloodMnist/Readme.md | 31 ++++++++++++++++++++++
 1 file changed, 31 insertions(+)

diff --git a/examples/demos/Classification/BloodMnist/Readme.md b/examples/demos/Classification/BloodMnist/Readme.md
new file mode 100644
index 0000000..b72c7d7
--- /dev/null
+++ b/examples/demos/Classification/BloodMnist/Readme.md
@@ -0,0 +1,31 @@
+# CNN demo model on BloodMnist dataset
+
+## About dataset
+Download address: https://drive.google.com/drive/folders/1Ze9qri1UtAsIRoI0SJ4YRpdt5kUUMBEn?usp=sharing
+
+The BloodMNIST , as a sub set of [MedMNIST](https://medmnist.com/), is based on a dataset of individual normal cells, captured from individuals without infection, hematologic or oncologic disease and free of any pharmacologic treatment at the moment of blood collection. 
+It contains a total of 17,092 images and is organized into 8 classes. 
+it is split with a ratio of 7:1:2 into training, validation and test set. 
+The source images with resolution 3×360×363 pixels are center-cropped into 3×200×200, and then resized into 3×28×28.
+
+8 classes of the dataset: 
+```python
+"0": "basophil",
+"1": "eosinophil",
+"2": "erythroblast",
+"3": "ig (immature granulocytes)",
+"4": "lymphocyte",
+"5": "monocyte",
+"6": "neutrophil",
+"7": "platelet"
+```
+To generate “real” image data, run
+```shell
+python bloodmnist/make_data.py
+```
+
+# Run the demo
+Run
+```
+python ClassDemo.py
+```
\ No newline at end of file