Robsonfll commited on
Commit
dd0baa6
·
verified ·
1 Parent(s): 1d52c95

Update src/streamlit_app.py

Browse files
Files changed (1) hide show
  1. src/streamlit_app.py +85 -51
src/streamlit_app.py CHANGED
@@ -1,71 +1,105 @@
1
- import streamlit as st
 
2
  import numpy as np
3
  from PIL import Image
4
- import json
5
- import tflite_runtime.interpreter as tflite
6
- import os
7
 
8
- # =============================
9
- # 1. Carregar arquivos
10
- # =============================
11
- MODEL_PATH = "model.tflite"
12
- LABELS_PATH = "labels.txt"
13
- META_PATH = "meta.json"
 
14
 
 
15
  # Carregar labels
 
16
  with open(LABELS_PATH, "r", encoding="utf-8") as f:
17
- class_names = [x.strip() for x in f.readlines()]
18
 
19
- # Carregar metadata
 
 
20
  with open(META_PATH, "r", encoding="utf-8") as f:
21
  meta = json.load(f)
22
 
23
- IMG_SIZE = meta["input_shape"]["height"]
24
 
25
- # Carregar modelo TFLite
26
- interpreter = tflite.Interpreter(model_path=MODEL_PATH)
 
 
27
  interpreter.allocate_tensors()
 
28
  input_details = interpreter.get_input_details()
29
  output_details = interpreter.get_output_details()
30
 
 
 
 
 
 
 
 
31
 
32
- # =============================
33
- # 2. Função de Inferência
34
- # =============================
35
- def predict(img: Image.Image):
36
 
37
- img = img.resize((IMG_SIZE, IMG_SIZE))
38
- img = np.array(img).astype("float32") / 255.0
39
- img = np.expand_dims(img, axis=0)
40
-
41
- interpreter.set_tensor(input_details[0]['index'], img)
42
- interpreter.invoke()
43
 
44
- output = interpreter.get_tensor(output_details[0]['index'])[0]
45
- return output
46
 
47
-
48
- # =============================
49
- # 3. Interface Streamlit
50
- # =============================
51
- st.title("🗿 ArqueoIA – Classificação de Artefatos")
52
- st.write("Envie uma imagem de **cerâmica**, **flecha**, **moeda** ou **osso**.")
53
-
54
- uploaded = st.file_uploader("Envie uma imagem", type=['jpg','jpeg','png'])
55
-
56
- if uploaded:
57
- img = Image.open(uploaded).convert("RGB")
58
- st.image(img, caption="Imagem enviada", use_column_width=True)
59
-
60
- st.write("### 🔍 Analisando...")
61
-
62
- preds = predict(img)
63
- top_id = int(np.argmax(preds))
64
- top_label = class_names[top_id]
65
- top_conf = preds[top_id] * 100
66
-
67
- st.success(f"**Resultado: {top_label} ({top_conf:.1f}% de confiança)**")
68
-
69
- st.write("### 📊 Probabilidades:")
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
70
  for label, prob in zip(class_names, preds):
71
- st.write(f"- **{label}** → {prob*100:.1f}%")
 
 
 
1
+ import os
2
+ import json
3
  import numpy as np
4
  from PIL import Image
5
+ import streamlit as st
6
+ import tensorflow as tf
 
7
 
8
+ # ==========================
9
+ # Caminhos dos arquivos
10
+ # ==========================
11
+ BASE_DIR = os.path.dirname(__file__)
12
+ MODEL_PATH = os.path.join(BASE_DIR, "model.tflite")
13
+ LABELS_PATH = os.path.join(BASE_DIR, "labels.txt")
14
+ META_PATH = os.path.join(BASE_DIR, "meta.json")
15
 
16
+ # ==========================
17
  # Carregar labels
18
+ # ==========================
19
  with open(LABELS_PATH, "r", encoding="utf-8") as f:
20
+ class_names = [line.strip() for line in f if line.strip()]
21
 
22
+ # ==========================
23
+ # Carregar metadados
24
+ # ==========================
25
  with open(META_PATH, "r", encoding="utf-8") as f:
26
  meta = json.load(f)
27
 
28
+ IMG_SIZE = int(meta["input_shape"]["height"])
29
 
30
+ # ==========================
31
+ # Carregar modelo TFLite com TensorFlow
32
+ # ==========================
33
+ interpreter = tf.lite.Interpreter(model_path=MODEL_PATH)
34
  interpreter.allocate_tensors()
35
+
36
  input_details = interpreter.get_input_details()
37
  output_details = interpreter.get_output_details()
38
 
39
+ # ==========================
40
+ # Funções auxiliares
41
+ # ==========================
42
+ def preprocess_image(image: Image.Image) -> np.ndarray:
43
+ # redimensiona
44
+ image = image.resize((IMG_SIZE, IMG_SIZE))
45
+ arr = np.array(image).astype("float32") / 255.0
46
 
47
+ # garante 3 canais (RGB)
48
+ if arr.ndim == 2: # imagem em escala de cinza
49
+ arr = np.stack([arr] * 3, axis=-1)
 
50
 
51
+ # adiciona batch dimension
52
+ arr = np.expand_dims(arr, axis=0)
53
+ return arr
 
 
 
54
 
 
 
55
 
56
+ def predict(image: Image.Image) -> np.ndarray:
57
+ x = preprocess_image(image)
58
+ interpreter.set_tensor(input_details[0]["index"], x)
59
+ interpreter.invoke()
60
+ preds = interpreter.get_tensor(output_details[0]["index"])[0]
61
+ return preds
62
+
63
+ # ==========================
64
+ # Interface Streamlit
65
+ # ==========================
66
+ st.set_page_config(page_title="ArqueoIA", page_icon="🗿", layout="centered")
67
+
68
+ st.markdown(
69
+ "<h1 style='text-align:center; color:#1E88E5;'>🗿 ArqueoIA</h1>",
70
+ unsafe_allow_html=True,
71
+ )
72
+ st.markdown(
73
+ "<h3 style='text-align:center;'>Classificador educativo de artefatos arqueológicos</h3>",
74
+ unsafe_allow_html=True,
75
+ )
76
+ st.write(
77
+ "<p style='text-align:center;'>Envie uma foto de <b>osso</b>, "
78
+ "<b>cerâmica</b>, <b>moeda</b> ou <b>flecha</b>.</p>",
79
+ unsafe_allow_html=True,
80
+ )
81
+ st.write("---")
82
+
83
+ uploaded_file = st.file_uploader(
84
+ "Envie uma imagem do artefato:",
85
+ type=["jpg", "jpeg", "png"],
86
+ )
87
+
88
+ if uploaded_file is not None:
89
+ image = Image.open(uploaded_file).convert("RGB")
90
+ st.image(image, caption="Imagem enviada", use_column_width=True)
91
+
92
+ st.write("### 🔍 Analisando imagem...")
93
+ preds = predict(image)
94
+
95
+ top_idx = int(np.argmax(preds))
96
+ top_label = class_names[top_idx]
97
+ top_conf = float(preds[top_idx]) * 100.0
98
+
99
+ st.success(f"Sugestão da IA: **{top_label}** ({top_conf:.1f}% de confiança)")
100
+
101
+ st.write("### 📊 Detalhamento das classes")
102
  for label, prob in zip(class_names, preds):
103
+ st.write(f"- **{label}**: {prob * 100:.1f}%")
104
+ else:
105
+ st.info("Carregue uma imagem para começar.")