Spaces:
Sleeping
Sleeping
Upload folder using huggingface_hub
Browse files- .DS_Store +0 -0
- .gitattributes +1 -0
- .gitignore +2 -0
- README.md +3 -9
- app.py +158 -0
- examples/.DS_Store +0 -0
- examples/bonete.jpg +0 -0
- examples/croissant_baguette.jpg +0 -0
- examples/pandesal.jpg +3 -0
- examples/slices.png +0 -0
- requirements.txt +5 -0
- weights/best.pt +3 -0
.DS_Store
ADDED
Binary file (6.15 kB). View file
|
|
.gitattributes
CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
examples/pandesal.jpg filter=lfs diff=lfs merge=lfs -text
|
.gitignore
ADDED
@@ -0,0 +1,2 @@
|
|
|
|
|
|
|
1 |
+
.DS_Store
|
2 |
+
__pycache__/
|
README.md
CHANGED
@@ -1,12 +1,6 @@
|
|
1 |
---
|
2 |
-
title: Bread
|
3 |
-
emoji: 👁
|
4 |
-
colorFrom: pink
|
5 |
-
colorTo: gray
|
6 |
-
sdk: gradio
|
7 |
-
sdk_version: 3.40.1
|
8 |
app_file: app.py
|
9 |
-
|
|
|
10 |
---
|
11 |
-
|
12 |
-
Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
|
|
|
1 |
---
|
2 |
+
title: Bread-Detector-Gradio
|
|
|
|
|
|
|
|
|
|
|
3 |
app_file: app.py
|
4 |
+
sdk: gradio
|
5 |
+
sdk_version: 3.39.0
|
6 |
---
|
|
|
|
app.py
ADDED
@@ -0,0 +1,158 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import gradio as gr
|
2 |
+
import cv2 as cv2
|
3 |
+
import pandas as pd
|
4 |
+
from sahi.prediction import ObjectPrediction
|
5 |
+
from sahi.utils.cv import visualize_object_predictions, read_image
|
6 |
+
from ultralyticsplus import YOLO
|
7 |
+
|
8 |
+
# Gradio Theme
|
9 |
+
theme = gr.themes.Soft(
|
10 |
+
primary_hue="yellow",
|
11 |
+
secondary_hue="blue",
|
12 |
+
neutral_hue="gray",
|
13 |
+
font=[gr.themes.GoogleFont('Inter'), 'ui-sans-serif', 'system-ui', 'sans-serif'],
|
14 |
+
font_mono=[gr.themes.GoogleFont('Inter'), 'ui-monospace', 'Consolas', 'monospace'],
|
15 |
+
).set(
|
16 |
+
background_fill_primary='*neutral_100',
|
17 |
+
)
|
18 |
+
|
19 |
+
# Bread Prices
|
20 |
+
bread_types = {
|
21 |
+
"baguette": {"name": "Baguette", "price": 108},
|
22 |
+
"binangkal": {"name": "Binangkal", "price": 11},
|
23 |
+
"bonete": {"name": "Bonete", "price": 8},
|
24 |
+
"cornbread": {"name": "Cornbread", "price": 55},
|
25 |
+
"croissant": {"name": "Croissant", "price": 75},
|
26 |
+
"ensaymada": {"name": "Ensaymada", "price": 14},
|
27 |
+
"flatbread": {"name": "Flatbread", "price": 17},
|
28 |
+
"kalihim": {"name": "Kalihim", "price": 15},
|
29 |
+
"monay": {"name": "Monay", "price": 6},
|
30 |
+
"pandesal": {"name": "Pandesal", "price": 3},
|
31 |
+
"sourdough": {"name": "Sourdough", "price": 150},
|
32 |
+
"spanish-bread": {"name": "Spanish Bread", "price": 14},
|
33 |
+
"wheat-bread": {"name": "Wheat Bread", "price": 8},
|
34 |
+
"white-bread": {"name": "White Bread", "price": 4},
|
35 |
+
"whole-grain-bread": {"name": "Whole Grain Bread", "price": 10},
|
36 |
+
}
|
37 |
+
|
38 |
+
# Instantiate the model
|
39 |
+
model = YOLO('best.pt')
|
40 |
+
|
41 |
+
# Bread Prediction function
|
42 |
+
def detect_bread(image):
|
43 |
+
results = model.predict(image, conf=0.4)
|
44 |
+
result = results[0]
|
45 |
+
object_prediction_list = []
|
46 |
+
|
47 |
+
# Image Output function
|
48 |
+
for box in result.boxes:
|
49 |
+
bbox = box.xyxy[0].tolist()
|
50 |
+
score = round(box.conf[0].item(), 2)
|
51 |
+
category_id = box.cls[0]
|
52 |
+
category_name = result.names[box.cls[0].item()]
|
53 |
+
|
54 |
+
object_prediction = ObjectPrediction(
|
55 |
+
bbox=bbox,
|
56 |
+
category_id=int(category_id),
|
57 |
+
score=score,
|
58 |
+
category_name=category_name,
|
59 |
+
)
|
60 |
+
object_prediction_list.append(object_prediction)
|
61 |
+
|
62 |
+
image = read_image(image)
|
63 |
+
output_image = visualize_object_predictions(image=image, object_prediction_list=object_prediction_list)
|
64 |
+
|
65 |
+
# Receipt Output function
|
66 |
+
detected_classes = []
|
67 |
+
detected_items = []
|
68 |
+
counts = {} # Dictionary to store bread type counts
|
69 |
+
|
70 |
+
for cls in result.boxes.cls: # Stores all detected classes in the list
|
71 |
+
detected_classes.append(result.names[int(cls)])
|
72 |
+
|
73 |
+
for item_class in detected_classes: # Counts the quantity of each class
|
74 |
+
counts[item_class] = counts.get(item_class, 0) + 1
|
75 |
+
|
76 |
+
for item_class, count in counts.items(): # Gets the name and price of each class
|
77 |
+
bread_info = bread_types.get(item_class, {})
|
78 |
+
item_name = bread_info.get("name", "Unknown Bread")
|
79 |
+
price = bread_info.get("price", 0)
|
80 |
+
detected_items.append({"item": item_name, "quantity": count, "price": price})
|
81 |
+
|
82 |
+
total_amount = sum(item["quantity"] * item["price"] for item in detected_items)
|
83 |
+
|
84 |
+
# Creates the receipt dictionary
|
85 |
+
data = {"Item": [], "Quantity": [], "Price": [], "Amount": []}
|
86 |
+
|
87 |
+
for item_info in detected_items:
|
88 |
+
item = item_info["item"]
|
89 |
+
quantity = item_info["quantity"]
|
90 |
+
price = item_info["price"]
|
91 |
+
total_item_amount = quantity * price
|
92 |
+
|
93 |
+
data["Item"].append(item)
|
94 |
+
data["Quantity"].append(quantity)
|
95 |
+
data["Price"].append(price)
|
96 |
+
data["Amount"].append(total_item_amount)
|
97 |
+
|
98 |
+
# Appends the last row of the dataframe for the total amount
|
99 |
+
data["Item"].append("TOTAL")
|
100 |
+
data["Quantity"].append("")
|
101 |
+
data["Price"].append("")
|
102 |
+
data["Amount"].append(total_amount)
|
103 |
+
|
104 |
+
df = pd.DataFrame(data)
|
105 |
+
|
106 |
+
return output_image['image'], df
|
107 |
+
|
108 |
+
# Export to CSV function
|
109 |
+
def export_csv(df):
|
110 |
+
df.to_csv("receipt.csv", index=False)
|
111 |
+
return gr.File.update(value="receipt.csv", visible=True)
|
112 |
+
|
113 |
+
# Export to JSON function
|
114 |
+
def export_json(df):
|
115 |
+
df.to_json("receipt.json")
|
116 |
+
return gr.File.update(value="receipt.json", visible=True)
|
117 |
+
|
118 |
+
# Gradio Interface
|
119 |
+
with gr.Blocks(theme=theme) as demo:
|
120 |
+
|
121 |
+
gr.Markdown("# Bread Detector w/ POS")
|
122 |
+
gr.Markdown("An application that detects different types of bread and calculates the total price.")
|
123 |
+
gr.Markdown("**Bread types include:** baguette, binangkal, bonete, cornbread, croissant, ensaymada, flatbread, kalihim, monay, pandesal, sourdough, spanish bread, wheat bread, white bread, and whole grain bread.")
|
124 |
+
|
125 |
+
with gr.Row():
|
126 |
+
with gr.Column():
|
127 |
+
fn = detect_bread
|
128 |
+
img_input = gr.Image(type="filepath", label="Input Image")
|
129 |
+
#img_input = gr.Files(file_types=["filepath"], label="Input Image")
|
130 |
+
detect_btn = gr.Button(variant="primary", value="Detect")
|
131 |
+
|
132 |
+
with gr.Column():
|
133 |
+
img_output = gr.Image(type="filepath", label='Output Image')
|
134 |
+
receipt_output = gr.Dataframe(
|
135 |
+
headers=["Item", "Quantity", "Price", "Amount"],
|
136 |
+
datatype=["str", "number", "number", "number"],
|
137 |
+
label="Receipt",
|
138 |
+
interactive=False,
|
139 |
+
)
|
140 |
+
with gr.Row():
|
141 |
+
clear_btn = gr.ClearButton([img_input, img_output, receipt_output])
|
142 |
+
export_btn = gr.Button(variant="primary", value="Export as CSV")
|
143 |
+
export_json_btn = gr.Button(variant="primary", value="Export as JSON")
|
144 |
+
with gr.Row():
|
145 |
+
csv = gr.File(interactive=False, visible=False)
|
146 |
+
|
147 |
+
with gr.Row():
|
148 |
+
gr.Examples(
|
149 |
+
examples = ["examples/bonete.jpg", "examples/pandesal.jpg", "examples/croissant_baguette.jpg", "examples/slices.png"],
|
150 |
+
inputs = img_input,
|
151 |
+
)
|
152 |
+
|
153 |
+
detect_btn.click(detect_bread, inputs=img_input, outputs=[img_output, receipt_output])
|
154 |
+
export_btn.click(export_csv, receipt_output, csv)
|
155 |
+
export_json_btn.click(export_json, receipt_output, csv)
|
156 |
+
|
157 |
+
demo.queue()
|
158 |
+
demo.launch()
|
examples/.DS_Store
ADDED
Binary file (6.15 kB). View file
|
|
examples/bonete.jpg
ADDED
examples/croissant_baguette.jpg
ADDED
examples/pandesal.jpg
ADDED
Git LFS Details
|
examples/slices.png
ADDED
requirements.txt
ADDED
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
gradio==3.40.1
|
2 |
+
opencv_python==4.8.0.74
|
3 |
+
pandas==2.0.3
|
4 |
+
sahi==0.11.14
|
5 |
+
ultralyticsplus==0.0.28
|
weights/best.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3ec84ed70c3f5b739b1aa271b767d6225fb85c0922aa8fb38b01023de24884fc
|
3 |
+
size 22519224
|