Final product

Dockerfile

@@ -1,3 +0,0 @@
-FROM python
-WORKDIR .
-RUN pip install -r requirements.txt

README.md

@@ -1,27 +1,12 @@
-# zero-to-hero
-Create and deploy to production a simple neural network for Computer Vision
-
-
-# Tools Used
-* JAX Library for computing gradients, performing tensor operations and scheming the segmentation model
-* Wandb for metrics and training tools
-* MLflow for deploying and compiling the model for production
-* Gradio for interactive user-experience platform within an online platform (Data-ICMC Website).
-
-
-## Datasets to consider
-* [LabelMe 12 50k](https://www.kaggle.com/datasets/dschettler8845/labelme-12-50k)
-* [City-Scapes](https://www.cityscapes-dataset.com/dataset-overview/)
-* [CamVid](http://mi.eng.cam.ac.uk/research/projects/VideoRec/CamVid/)
-
-
-## References
-* [DSNet-Fast](https://www.researchgate.net/figure/The-architecture-of-fast-dense-segmentation-network-DSNet-fast-The-encoder-is_fig1_347180093)
-* [DSNet](https://www.researchgate.net/figure/The-architecture-of-dense-segmentation-network-DSNet-The-encoder-is-a-fully-convolutional_fig1_347180092)
-
-
-# First Model
-The first model available and deployed considers a simple 2D image, taken from the MNIST Dataset. Reefer to [_High-Performance Neural Networks
-for Visual Object Classification_](https://arxiv.org/pdf/1102.0183.pdf) for further details on the dataset.
-
-The CI/CD process will use the default Github pipeline using the available [Github Actions features](https://github.blog/2022-02-02-build-ci-cd-pipeline-github-actions-four-steps/). The training process will use the MLFLow framework, to cather and track the necessary metrics and log accordingly. Reefer to the [docs](https://mlflow.org/docs/latest/quickstart.html) for further details.
+---
+title: Lenet Mnist
+emoji: 📉
+colorFrom: purple
+colorTo: red
+sdk: gradio
+sdk_version: 3.15.0
+app_file: app.py
+pinned: false
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -1,3 +1,3 @@
 from src.demo import main
 
-main()
+main("cpu")

docs/README.md

@@ -0,0 +1,27 @@
+# zero-to-hero
+Create and deploy to production a simple neural network for Computer Vision
+
+
+# Tools Used
+* JAX Library for computing gradients, performing tensor operations and scheming the segmentation model
+* Wandb for metrics and training tools
+* MLflow for deploying and compiling the model for production
+* Gradio for interactive user-experience platform within an online platform (Data-ICMC Website).
+
+
+## Datasets to consider
+* [LabelMe 12 50k](https://www.kaggle.com/datasets/dschettler8845/labelme-12-50k)
+* [City-Scapes](https://www.cityscapes-dataset.com/dataset-overview/)
+* [CamVid](http://mi.eng.cam.ac.uk/research/projects/VideoRec/CamVid/)
+
+
+## References
+* [DSNet-Fast](https://www.researchgate.net/figure/The-architecture-of-fast-dense-segmentation-network-DSNet-fast-The-encoder-is_fig1_347180093)
+* [DSNet](https://www.researchgate.net/figure/The-architecture-of-dense-segmentation-network-DSNet-The-encoder-is-a-fully-convolutional_fig1_347180092)
+
+
+# First Model
+The first model available and deployed considers a simple 2D image, taken from the MNIST Dataset. Reefer to [_High-Performance Neural Networks
+for Visual Object Classification_](https://arxiv.org/pdf/1102.0183.pdf) for further details on the dataset.
+
+The CI/CD process will use the default Github pipeline using the available [Github Actions features](https://github.blog/2022-02-02-build-ci-cd-pipeline-github-actions-four-steps/). The training process will use the MLFLow framework, to cather and track the necessary metrics and log accordingly. Reefer to the [docs](https://mlflow.org/docs/latest/quickstart.html) for further details.

main.py

@@ -1,8 +1,8 @@
 import torch
 
-from models import CNN
-from dataset import DatasetMNIST, download_mnist
-from train import get_dataloaders, train_net_manually, train_net_lightning
+from src.models import CNN
+from src.dataset import DatasetMNIST, download_mnist
+from src.train import get_dataloaders, train_net_manually, train_net_lightning
 
 
 def main(device):

src/demo.py

@@ -12,7 +12,7 @@ def predict_gradio_canvas(x, net, device="cuda"):
 
 
 def main(device="cuda"):
-    net = load_torch_net("../checkpoints/pytorch/version_1.pt")
+    net = load_torch_net("checkpoints/pytorch/version_1.pt")
 
     gr.Interface(fn=lambda x: predict_gradio_canvas(x, net, device),
                  inputs="sketchpad",

src/downloader.py

@@ -15,7 +15,7 @@ def download_dataset(name='cityscapes', path='downloads/downloads'):
     if name == 'cityscapes':
         download_cityscapes(path)
     elif name == "mnist":
-        pass
+        download_mnist(path)
     else:
         raise NotImplementedError