added the application files

README.md

@@ -1,10 +1,10 @@
 ---
-title: Usk Coffee Convnext Nano
-emoji: 👀
+title: USK-Coffee bean classifer (USK-Coffee|Convnext-nano|fast.ai)
+emoji: ☕️
 colorFrom: purple
 colorTo: green
 sdk: gradio
-sdk_version: 3.17.0
+sdk_version: 3.1.4
 app_file: app.py
 pinned: false
 ---

app.py

@@ -0,0 +1,48 @@
+import gradio
+from fastai.vision.all import *
+
+MODELS_PATH = Path('./models')
+EXAMPLES_PATH = Path('./examples')
+
+# Required function expected by fastai learn object
+# it wasn't exported as a part of the pickle
+# as it was defined externally to the learner object
+# during the training time dataloaders setup
+def label_func(filepath):
+    return filepath.parent.name
+
+LEARN = load_learner(MODELS_PATH/'usk-coffee-convnext_nano_935625.pkl')
+LABELS = LEARN.dls.vocab
+
+def gradio_predict(img):
+    img = PILImage.create(img)
+    _pred, _pred_idx, probs = LEARN.predict(img)
+    labels_probs = {LABELS[i]: float(probs[i]) for i, _ in enumerate(LABELS)}
+    return labels_probs
+
+with open('gradio_article.md') as f:
+    article = f.read()
+
+interface_options = {
+    "title": "USK-Coffee bean classifer (USK-Coffee|Convnext-nano|fast.ai)",
+    "description": "A coffee bean image classifier(ConvNext nano) fine tuned on the USK-Coffee (https://comvis.unsyiah.ac.id/usk-coffee/) dataset using fastai & timm.",
+    "article": article,
+    "examples" : [f'{EXAMPLES_PATH}/{f.name}' for f in EXAMPLES_PATH.iterdir()],
+    "interpretation": "default",
+    "layout": "horizontal",
+    "allow_flagging": "never",
+    "enable_queue": True 
+}
+
+demo = gradio.Interface(fn=gradio_predict,
+                      inputs=gradio.inputs.Image(shape=(512, 512)),
+                      outputs=gradio.outputs.Label(num_top_classes=5),
+                      **interface_options)
+
+launch_options = {
+    "enable_queue": True,
+    "share": False, 
+}
+
+demo.launch(**launch_options)
+

gradio_article.md

@@ -0,0 +1,27 @@
+## Dataset
+
+The USK-Coffee dataset, made available at https://comvis.unsyiah.ac.id/usk-coffee/ is multi class image dataset derived from a coffee bean collection that includes 4 classes: peaberry, longberry, defect, and premium.
+
+## Training
+
+Fast.ai was used to train this classifier with a Timm ConvNext nano vision learner, without heavy customization. The training was performed on the provided `train` split, and validation on the `val` split. 
+
+The final fine tuning of the training loop resulted in the following losses.
+
+| epoch | train_loss | valid_loss | accuracy |  time |
+|-------|------------|------------|----------|-------|
+|     0 |   0.238523 |   0.383621 | 0.869375 | 00:25 |
+|     1 |   0.257938 |   0.293417 | 0.907500 | 00:25 |
+|     2 |   0.205048 |   0.412420 | 0.847500 | 00:25 |
+|     3 |   0.170284 |   0.308219 | 0.901875 | 00:25 |
+|     4 |   0.154471 |   0.308811 | 0.894375 | 00:26 |
+|     5 |   0.107862 |   0.480474 | 0.874375 | 00:26 |
+|     6 |   0.075452 |   0.506489 | 0.843125 | 00:26 |
+|     7 |   0.060802 |   0.317052 | 0.906875 | 00:26 |
+|     8 |   0.049216 |   0.242317 | 0.932500 | 00:26 |
+|     9 |   0.040890 |   0.233353 | 0.935625 | 00:26 |
+
+
+## Examples
+
+The example images provided in the demo are from the `test` split in the dataset, which was never made available to the model in the training process.

requirements.txt

@@ -0,0 +1,2 @@
+fastai==2.7.9
+gradio==3.1.4