Spaces:
Runtime error
Runtime error
Update app.py
Browse files
app.py
CHANGED
|
@@ -1,51 +1,78 @@
|
|
| 1 |
from huggingface_hub import hf_hub_download
|
| 2 |
import tensorflow as tf
|
| 3 |
-
from tensorflow.keras.applications.efficientnet import preprocess_input
|
| 4 |
-
from tensorflow.keras import backend as K # not required, but safe
|
| 5 |
import numpy as np
|
| 6 |
-
from PIL import Image
|
| 7 |
import gradio as gr
|
| 8 |
|
| 9 |
-
# ----
|
| 10 |
-
|
| 11 |
-
|
| 12 |
-
# REPLACE YOUR OLD MODEL BUILD + load_weights WITH THIS BLOCK
|
| 13 |
-
# Download and load the FULL saved model (.keras) from your HF Model repo
|
| 14 |
MODEL_REPO_ID = "BunkerMinecraft/neurecaiv2" # <-- change this
|
| 15 |
-
MODEL_FILENAME = "
|
|
|
|
|
|
|
| 16 |
|
|
|
|
|
|
|
|
|
|
| 17 |
model_path = hf_hub_download(
|
| 18 |
repo_id=MODEL_REPO_ID,
|
| 19 |
filename=MODEL_FILENAME,
|
| 20 |
repo_type="model"
|
| 21 |
)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 22 |
model = tf.keras.models.load_model(model_path, compile=False)
|
| 23 |
-
print(f"Loaded
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 24 |
|
| 25 |
|
| 26 |
-
# ----
|
|
|
|
|
|
|
| 27 |
def preprocess(img: Image.Image):
|
| 28 |
-
img = img.convert("RGB")
|
| 29 |
-
|
| 30 |
-
# If you trained with x/255.0, replace next line with: x = x / 255.0
|
| 31 |
-
x = preprocess_input(x) # EfficientNet normalization
|
| 32 |
-
return np.expand_dims(x, 0)
|
| 33 |
|
| 34 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 35 |
def predict(image: Image.Image):
|
| 36 |
x = preprocess(image)
|
| 37 |
-
|
| 38 |
-
|
| 39 |
-
|
|
|
|
|
|
|
| 40 |
return class_names[idx], conf
|
| 41 |
|
| 42 |
-
|
|
|
|
|
|
|
|
|
|
| 43 |
interface = gr.Interface(
|
| 44 |
fn=predict,
|
| 45 |
inputs=gr.Image(type="pil", label="Upload an image"),
|
| 46 |
outputs=[gr.Label(label="Predicted class"), gr.Number(label="Confidence")],
|
| 47 |
-
title="
|
| 48 |
-
description="
|
| 49 |
)
|
| 50 |
|
| 51 |
if __name__ == "__main__":
|
|
|
|
| 1 |
from huggingface_hub import hf_hub_download
|
| 2 |
import tensorflow as tf
|
|
|
|
|
|
|
| 3 |
import numpy as np
|
| 4 |
+
from PIL import Image, ImageOps
|
| 5 |
import gradio as gr
|
| 6 |
|
| 7 |
+
# -----------------------
|
| 8 |
+
# CONFIG
|
| 9 |
+
# -----------------------
|
|
|
|
|
|
|
| 10 |
MODEL_REPO_ID = "BunkerMinecraft/neurecaiv2" # <-- change this
|
| 11 |
+
MODEL_FILENAME = "keras_model.h5"
|
| 12 |
+
LABELS_FILENAME = "labels.txt"
|
| 13 |
+
IMAGE_SIZE = (224, 224) # TM fixed size
|
| 14 |
|
| 15 |
+
# -----------------------
|
| 16 |
+
# DOWNLOAD MODEL + LABELS
|
| 17 |
+
# -----------------------
|
| 18 |
model_path = hf_hub_download(
|
| 19 |
repo_id=MODEL_REPO_ID,
|
| 20 |
filename=MODEL_FILENAME,
|
| 21 |
repo_type="model"
|
| 22 |
)
|
| 23 |
+
|
| 24 |
+
labels_path = hf_hub_download(
|
| 25 |
+
repo_id=MODEL_REPO_ID,
|
| 26 |
+
filename=LABELS_FILENAME,
|
| 27 |
+
repo_type="model"
|
| 28 |
+
)
|
| 29 |
+
|
| 30 |
+
# Load the Teachable Machine Keras .h5 model
|
| 31 |
model = tf.keras.models.load_model(model_path, compile=False)
|
| 32 |
+
print(f"Loaded model: {model_path}")
|
| 33 |
+
|
| 34 |
+
# Load labels
|
| 35 |
+
with open(labels_path, "r") as f:
|
| 36 |
+
class_names = [line.strip() for line in f.readlines()]
|
| 37 |
+
print("Loaded labels:", class_names)
|
| 38 |
|
| 39 |
|
| 40 |
+
# -----------------------
|
| 41 |
+
# PREPROCESS FUNCTION (matches TM)
|
| 42 |
+
# -----------------------
|
| 43 |
def preprocess(img: Image.Image):
|
| 44 |
+
img = img.convert("RGB")
|
| 45 |
+
img = ImageOps.fit(img, IMAGE_SIZE, Image.Resampling.LANCZOS)
|
|
|
|
|
|
|
|
|
|
| 46 |
|
| 47 |
+
image_array = np.asarray(img).astype(np.float32)
|
| 48 |
+
# TM normalization:
|
| 49 |
+
normalized = (image_array / 127.5) - 1.0
|
| 50 |
+
|
| 51 |
+
return np.expand_dims(normalized, axis=0)
|
| 52 |
+
|
| 53 |
+
|
| 54 |
+
# -----------------------
|
| 55 |
+
# PREDICT FUNCTION
|
| 56 |
+
# -----------------------
|
| 57 |
def predict(image: Image.Image):
|
| 58 |
x = preprocess(image)
|
| 59 |
+
preds = model.predict(x, verbose=0)[0]
|
| 60 |
+
|
| 61 |
+
idx = int(np.argmax(preds))
|
| 62 |
+
conf = float(preds[idx])
|
| 63 |
+
|
| 64 |
return class_names[idx], conf
|
| 65 |
|
| 66 |
+
|
| 67 |
+
# -----------------------
|
| 68 |
+
# UI (Gradio)
|
| 69 |
+
# -----------------------
|
| 70 |
interface = gr.Interface(
|
| 71 |
fn=predict,
|
| 72 |
inputs=gr.Image(type="pil", label="Upload an image"),
|
| 73 |
outputs=[gr.Label(label="Predicted class"), gr.Number(label="Confidence")],
|
| 74 |
+
title="Teachable Machine Classifier",
|
| 75 |
+
description="Upload an image to classify using your keras_Model.h5 Teachable Machine model."
|
| 76 |
)
|
| 77 |
|
| 78 |
if __name__ == "__main__":
|