معرفی شرکت ها
devolearn-0.3.0
تبلیغات ما
مشتریان به طور فزاینده ای آنلاین هستند. تبلیغات می تواند به آنها کمک کند تا کسب و کار شما را پیدا کنند.
مشاهده بیشتر
تبلیغات ما
مشتریان به طور فزاینده ای آنلاین هستند. تبلیغات می تواند به آنها کمک کند تا کسب و کار شما را پیدا کنند.
مشاهده بیشتر
تبلیغات ما
مشتریان به طور فزاینده ای آنلاین هستند. تبلیغات می تواند به آنها کمک کند تا کسب و کار شما را پیدا کنند.
مشاهده بیشتر
تبلیغات ما
مشتریان به طور فزاینده ای آنلاین هستند. تبلیغات می تواند به آنها کمک کند تا کسب و کار شما را پیدا کنند.
مشاهده بیشتر
تبلیغات ما
مشتریان به طور فزاینده ای آنلاین هستند. تبلیغات می تواند به آنها کمک کند تا کسب و کار شما را پیدا کنند.
مشاهده بیشترتوضیحات
Accelerate data driven research in developmental biology with deep learning models
| ویژگی | مقدار |
|---|---|
| سیستم عامل | - |
| نام فایل | devolearn-0.3.0 |
| نام | devolearn |
| نسخه کتابخانه | 0.3.0 |
| نگهدارنده | [] |
| ایمیل نگهدارنده | [] |
| نویسنده | Mayukh Deb, Ujjwal Singh, Bradly Alicea |
| ایمیل نویسنده | mayukhmainak2000@gmail.com, ujjwal18113@iiitd.ac.in, balicea@openworm.org |
| آدرس صفحه اصلی | https://github.com/DevoLearn/devolearn |
| آدرس اینترنتی | https://pypi.org/project/devolearn/ |
| مجوز | - |
<p align="center">
<img src = "https://raw.githubusercontent.com/DevoLearn/devolearn/master/images/banner_1.jpg">
</p>
[](https://travis-ci.org/DevoLearn/devolearn)
[](https://github.com/DevoLearn/devolearn/issues)
[](https://github.com/DevoLearn/devolearn/graphs/contributors)
[](https://github.com/DevoLearn/devolearn/commits/master)
[](https://openworm.slack.com/archives/CMVFU7Q4W)
[](https://colab.research.google.com/github/DevoLearn/data-science-demos/blob/master/devolearn_docs/devolearn_quickstart.ipynb)
## Contents
* [Example notebooks](https://github.com/DevoLearn/devolearn#example-notebooks)
* [Segmenting the C. elegans embryo](https://github.com/DevoLearn/devolearn#segmenting-the-c-elegans-embryo)
* [Generating synthetic images of embryos with a GAN](https://github.com/DevoLearn/devolearn#generating-synthetic-images-of-embryos-with-a-pre-trained-gan)
* [Predicting populations of cells within the C. elegans embryo](https://github.com/DevoLearn/devolearn#predicting-populations-of-cells-within-the-c-elegans-embryo)
* [Contributing to DevoLearn](https://github.com/DevoLearn/devolearn/blob/master/.github/contributing.md#contributing-to-devolearn)
* [Contact us](https://github.com/DevoLearn/devolearn#contact-us)
### Installation
```python
pip install devolearn
```
### Example notebooks
<p align="center">
<img src = "https://raw.githubusercontent.com/DevoLearn/data-science-demos/master/Networks/nodes_matrix_long_smooth.gif" width = "40%">
<img src = "https://raw.githubusercontent.com/DevoLearn/data-science-demos/master/Networks/3d_node_map.gif" width = "40%">
</p>
* [Extracting centroid maps and making 3d centroid models](https://nbviewer.jupyter.org/github/DevoLearn/data-science-demos/blob/master/Networks/experiments_with_devolearn_node_maps.ipynb)
### Segmenting the C. elegans embryo
<p align="center">
<img src = "https://raw.githubusercontent.com/DevoLearn/devolearn/master/images/pred_centroids.gif" width = "80%">
</p>
* Importing the model
```python
from devolearn import embryo_segmentor
segmentor = embryo_segmentor()
```
* Running the model on an image and viewing the prediction
```python
seg_pred = segmentor.predict(image_path = "sample_data/images/seg_sample.jpg")
plt.imshow(seg_pred)
plt.show()
```
* Running the model on a video and saving the predictions into a folder
```python
filenames = segmentor.predict_from_video(video_path = "sample_data/videos/seg_sample.mov", centroid_mode = False, save_folder = "preds")
```
* Finding the centroids of the segmented features
```python
seg_pred, centroids = segmentor.predict(image_path = "sample_data/images/seg_sample.jpg", centroid_mode = True)
plt.imshow(seg_pred)
plt.show()
```
* Saving the centroids from each frame into a CSV
```python
df = segmentor.predict_from_video(video_path = "sample_data/videos/seg_sample.mov", centroid_mode = True, save_folder = "preds")
df.to_csv("centroids.csv")
```
### Generating synthetic images of embryos with a Pre-trained GAN
<p align="center">
<img src = "https://raw.githubusercontent.com/devoworm/GSoC-2020/master/Pre-trained%20Models%20(DevLearning)/images/generated_embryos_3.gif" width = "30%">
</p>
* Importing the model
```python
from devolearn import Generator, embryo_generator_model
generator = embryo_generator_model()
```
* Generating a picture and viewing it with [matplotlib](https://matplotlib.org/)
```python
gen_image = generator.generate()
plt.imshow(gen_image)
plt.show()
```
* Generating n images and saving them into `foldername` with a custom size
```python
generator.generate_n_images(n = 5, foldername= "generated_images", image_size= (700,500))
```
---
### Predicting populations of cells within the C. elegans embryo
<p align="center">
<img src = "https://raw.githubusercontent.com/devoworm/GSoC-2020/master/Pre-trained%20Models%20(DevLearning)/images/resnet_preds_with_input.gif" width = "60%">
</p>
* Importing the population model for inferences
```python
from devolearn import lineage_population_model
```
* Loading a model instance to be used to estimate lineage populations of embryos from videos/photos.
```python
model = lineage_population_model(mode = "cpu")
```
* Making a prediction from an image
```python
print(model.predict(image_path = "sample_data/images/embryo_sample.png"))
```
* Making predictions from a video and saving the predictions into a CSV file
```python
results = model.predict_from_video(video_path = "sample_data/videos/embryo_timelapse.mov", save_csv = True, csv_name = "video_preds.csv", ignore_first_n_frames= 10, ignore_last_n_frames= 10 )
```
* Plotting the model's predictions from a video
```python
plot = model.create_population_plot_from_video(video_path = "sample_data/videos/embryo_timelapse.mov", save_plot= True, plot_name= "plot.png", ignore_last_n_frames= 0 )
plot.show()
```
## Links to Datasets
| **Model** | **Data source** |
|-------------------------------------------------|-------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| Segmenting the C. elegans embryo | [3DMMS: robust 3D Membrane Morphological Segmentation of C. elegans embryo](https://bmcbioinformatics.biomedcentral.com/articles/10.1186/s12859-019-2720-x#Abs1/) |
| Cell lineage population prediction + embryo GAN | [EPIC dataset](https://epic.gs.washington.edu/)
## Authors/maintainers:
* [Mayukh Deb](https://twitter.com/mayukh091)
* [Ujjwal Singh](https://twitter.com/ujjjwalll)
* [Dr. Bradly Alicea](https://twitter.com/balicea1)
Feel free to join our [Slack workspace](https://openworm.slack.com/archives/CMVFU7Q4W)!
نیازمندی
| مقدار | نام |
|---|---|
| ==0.10.0 | cycler |
| ==4.4.2 | decorator |
| ==0.6.3 | efficientnet-pytorch |
| ==0.18.2 | future |
| ==2.9.0 | imageio |
| ==0.2.5 | imgaug |
| ==0.5.3 | imutils |
| ==1.0.0 | joblib |
| ==1.3.1 | kiwisolver |
| - | matplotlib |
| ==2.5.0 | munch |
| ==2.5 | networkx |
| ==1.19.5 | numpy |
| ==4.5.1.48 | opencv-python |
| ==1.1.5 | pandas |
| - | Pillow |
| ==0.7.4 | pretrainedmodels |
| ==2.4.7 | pyparsing |
| ==2.8.1 | python-dateutil |
| - | pytz |
| ==1.1.1 | PyWavelets |
| - | scikit-image |
| ==0.24.0 | scikit-learn |
| ==1.5.4 | scipy |
| ==0.1.3 | segmentation-models-pytorch |
| ==1.15.0 | six |
| ==0.0 | sklearn |
| ==2.1.0 | threadpoolctl |
| - | tifffile |
| ==0.3.2 | timm |
| ==1.7.0 | torch |
| ==0.8.1 | torchvision |
| ==4.56.0 | tqdm |
| ==3.7.4.3 | typing-extensions |
| ==3.2 | wget |
زبان مورد نیاز
| مقدار | نام |
|---|---|
| >=3.6 | Python |
نحوه نصب
نصب پکیج whl devolearn-0.3.0:
pip install devolearn-0.3.0.whl
نصب پکیج tar.gz devolearn-0.3.0:
pip install devolearn-0.3.0.tar.gz