Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+examples/normal/100002.jpg filter=lfs diff=lfs merge=lfs -text

app.py

@@ -1,29 +1,57 @@
 # AUTOGENERATED! DO NOT EDIT! File to edit: app.ipynb.
 
 # %% auto 0
-__all__ = ['learn', 'labels', 'demo', 'predict']
+__all__ = ['vocab', 'img_path', 'dblock', 'dls', 'learn', 'labels', 'example_files', 'demo', 'predict']
 
 # %% app.ipynb 3
 import os
 import gradio as gr
 from fastai.vision.all import *
+import pathlib
 # import dill
 
 # %% app.ipynb 5
-learn = load_learner("mobilenetv4_conv_small.e3600_r256_in1k_v3.pkl"); learn
+vocab = ['bacterial_leaf_blight', 'bacterial_leaf_streak', 'bacterial_panicle_blight', 
+         'blast', 'brown_spot', 'dead_heart', 'downy_mildew', 'hispa', 'normal', 'tungro']
+
+# Dummy image path - replace with your real test image path
+img_path = pathlib.Path("examples/hispa/200999.jpg")
+dblock = DataBlock(
+    blocks=(ImageBlock, CategoryBlock(vocab=vocab)),
+    get_items=lambda x: [img_path],  # x is source, ignored here
+    get_y=lambda x: 'normal',
+    item_tfms=Resize(192)
+)
+
+# Pass a dummy 'source' argument, e.g. '.' or pathlib.Path('.')
+dls = dblock.dataloaders(pathlib.Path('.'), bs=1)
+
+# %% app.ipynb 7
+learn = vision_learner(dls,"mobilenetv4_conv_small.e3600_r256_in1k", metrics=[error_rate, accuracy]); learn
+
+# %% app.ipynb 8
+learn.load("mobilenetv4_conv_small.e3600_r256_in1k_v3"); learn
+# learn.dls.vocab = ['bacterial_leaf_blight', 'bacterial_leaf_streak', 'bacterial_panicle_blight', 'blast', 'brown_spot', 'dead_heart', 'downy_mildew', 'hispa', 'normal', 'tungro']
+# learn.dls.c = len(['bacterial_leaf_blight', 'bacterial_leaf_streak', 'bacterial_panicle_blight', 'blast', 'brown_spot', 'dead_heart', 'downy_mildew', 'hispa', 'normal', 'tungro'])
 labels = learn.dls.vocab; labels
 
-# %% app.ipynb 6
+# %% app.ipynb 10
 def predict(img):
     img = PILImage.create(img)
     pred,pred_idx,probs = learn.predict(img)
     return {labels[i]: float(probs[i]) for i in range(len(labels))}
 
-# %% app.ipynb 7
+# %% app.ipynb 12
+example_files = list(pathlib.Path('./examples').glob("*/*.jpg")); example_files
+
+# %% app.ipynb 15
 demo = gr.Interface(
-    fn=predict, 
+    fn=predict,
     inputs=gr.Image(), 
-    outputs=gr.Label(num_top_classes=3)
+    outputs=gr.Label(num_top_classes=3),
+    examples=[[str(f)] for f in example_files],
+    title="Paddy Disease Classifier",
+    description="Upload an image or select one of the examples to classify rice diseases."
 )
 
 demo.launch(share=True)

models/mobilenetv4_conv_small.e3600_r256_in1k_v3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69e8f4de09ee4fb1557af861d647151616bc478bc562b14824d91dd2cdb10887
+size 32316683