Update app.py
Browse files
app.py
CHANGED
|
@@ -29,7 +29,7 @@ transform = transforms.Compose([
|
|
| 29 |
])
|
| 30 |
|
| 31 |
def classify_crop(crop_img):
|
| 32 |
-
"""
|
| 33 |
image = transform(crop_img).unsqueeze(0).to(device)
|
| 34 |
with torch.no_grad():
|
| 35 |
output = resnet(image)
|
|
@@ -37,23 +37,19 @@ def classify_crop(crop_img):
|
|
| 37 |
return class_labels[predicted.item()]
|
| 38 |
|
| 39 |
def detect_and_classify(input_image):
|
| 40 |
-
"""
|
| 41 |
-
# Convert Gradio Image to OpenCV format
|
| 42 |
image = np.array(input_image)
|
| 43 |
image = cv2.cvtColor(image, cv2.COLOR_RGB2BGR)
|
| 44 |
-
|
| 45 |
-
# YOLO Detection
|
| 46 |
results = yolo_model(image)[0]
|
| 47 |
boxes = results.boxes.xyxy.cpu().numpy()
|
| 48 |
-
|
| 49 |
-
# Process each detection
|
| 50 |
for box in boxes:
|
| 51 |
x1, y1, x2, y2 = map(int, box[:4])
|
| 52 |
crop = image[y1:y2, x1:x2]
|
| 53 |
crop_pil = Image.fromarray(cv2.cvtColor(crop, cv2.COLOR_BGR2RGB))
|
| 54 |
predicted_label = classify_crop(crop_pil)
|
| 55 |
|
| 56 |
-
# Draw bounding box and label
|
| 57 |
cv2.rectangle(image, (x1, y1), (x2, y2), (0, 255, 0), 2)
|
| 58 |
cv2.putText(image,
|
| 59 |
predicted_label,
|
|
@@ -63,22 +59,22 @@ def detect_and_classify(input_image):
|
|
| 63 |
(36, 255, 12),
|
| 64 |
2)
|
| 65 |
|
| 66 |
-
# Convert back to RGB for Gradio
|
| 67 |
return Image.fromarray(cv2.cvtColor(image, cv2.COLOR_BGR2RGB))
|
| 68 |
|
| 69 |
-
#
|
| 70 |
-
with gr.Blocks(title="
|
| 71 |
gr.Markdown("""
|
| 72 |
-
## 🍚
|
| 73 |
-
|
|
|
|
| 74 |
""")
|
| 75 |
|
| 76 |
with gr.Row():
|
| 77 |
with gr.Column():
|
| 78 |
-
image_input = gr.Image(type="pil", label="
|
| 79 |
-
submit_btn = gr.Button("
|
| 80 |
with gr.Column():
|
| 81 |
-
output_image = gr.Image(label="
|
| 82 |
|
| 83 |
submit_btn.click(
|
| 84 |
fn=detect_and_classify,
|
|
@@ -86,5 +82,5 @@ with gr.Blocks(title="Rice Classification") as demo:
|
|
| 86 |
outputs=output_image
|
| 87 |
)
|
| 88 |
|
| 89 |
-
#
|
| 90 |
-
demo.launch()
|
|
|
|
| 29 |
])
|
| 30 |
|
| 31 |
def classify_crop(crop_img):
|
| 32 |
+
"""ایک چاول کے دانے کو درجہ بند کریں"""
|
| 33 |
image = transform(crop_img).unsqueeze(0).to(device)
|
| 34 |
with torch.no_grad():
|
| 35 |
output = resnet(image)
|
|
|
|
| 37 |
return class_labels[predicted.item()]
|
| 38 |
|
| 39 |
def detect_and_classify(input_image):
|
| 40 |
+
"""تصویر پر کارروائی کریں اور ہر دانے کو شناخت کریں"""
|
|
|
|
| 41 |
image = np.array(input_image)
|
| 42 |
image = cv2.cvtColor(image, cv2.COLOR_RGB2BGR)
|
| 43 |
+
|
|
|
|
| 44 |
results = yolo_model(image)[0]
|
| 45 |
boxes = results.boxes.xyxy.cpu().numpy()
|
| 46 |
+
|
|
|
|
| 47 |
for box in boxes:
|
| 48 |
x1, y1, x2, y2 = map(int, box[:4])
|
| 49 |
crop = image[y1:y2, x1:x2]
|
| 50 |
crop_pil = Image.fromarray(cv2.cvtColor(crop, cv2.COLOR_BGR2RGB))
|
| 51 |
predicted_label = classify_crop(crop_pil)
|
| 52 |
|
|
|
|
| 53 |
cv2.rectangle(image, (x1, y1), (x2, y2), (0, 255, 0), 2)
|
| 54 |
cv2.putText(image,
|
| 55 |
predicted_label,
|
|
|
|
| 59 |
(36, 255, 12),
|
| 60 |
2)
|
| 61 |
|
|
|
|
| 62 |
return Image.fromarray(cv2.cvtColor(image, cv2.COLOR_BGR2RGB))
|
| 63 |
|
| 64 |
+
# Gradio انٹرفیس بنائیں
|
| 65 |
+
with gr.Blocks(title="چاول کی اقسام کی درجہ بندی") as demo:
|
| 66 |
gr.Markdown("""
|
| 67 |
+
## 🍚 چاول کی اقسام کی شناخت کا نظام
|
| 68 |
+
ایک تصویر اپ لوڈ کریں جس میں چاول کے دانے ہوں۔
|
| 69 |
+
سسٹم ہر دانے کو شناخت اور درجہ بند کرے گا۔
|
| 70 |
""")
|
| 71 |
|
| 72 |
with gr.Row():
|
| 73 |
with gr.Column():
|
| 74 |
+
image_input = gr.Image(type="pil", label="چاول کی تصویر اپ لوڈ کریں")
|
| 75 |
+
submit_btn = gr.Button("تجزیہ شروع کریں", variant="primary")
|
| 76 |
with gr.Column():
|
| 77 |
+
output_image = gr.Image(label="نتائج", interactive=False)
|
| 78 |
|
| 79 |
submit_btn.click(
|
| 80 |
fn=detect_and_classify,
|
|
|
|
| 82 |
outputs=output_image
|
| 83 |
)
|
| 84 |
|
| 85 |
+
# ایپ لانچ کریں
|
| 86 |
+
demo.launch()
|