def predict_image():
#file = request.files['image']
#filename = os.path.join('selected', file.filename)
#file.save(filename)
# Load the VGG19 model
# https://keras.io/applications/#VGG19
model = VGG19(include_top=True, weights='imagenet')
# Define default image size for VGG19
image_size = (224, 224)
# initialize the response dictionary that will be returned
message = request.get_json(force=True)
encoded = message['image']
decoded = base64.b64decode(encoded)
img = Image.open(io.BytesIO(decoded))
# if the image mode is not RGB, convert it
if img.mode != "RGB":
img = img.convert("RGB")
# resize the input image and preprocess it
img = img.resize(image_size)
# Preprocess image for model prediction
# This step handles scaling and normalization for VGG19
x = image.img_to_array(img)
x = np.expand_dims(x, axis=0)
x = preprocess_input(x)
# Make predictions
predictions = model.predict(x)
prediction = decode_predictions(predictions, top=1)
print('Predicted:', decode_predictions(predictions, top=3))
response = {
'predictions': {
'label': np.array(prediction[0][0][1]).tolist(),
'probability': np.array(prediction[0][0][2]).tolist()
}
}
print(response)
# return the response dictionary as a JSON response
return jsonify(response)
def get_prediction_list(original_image: np.ndarray,
model) -> List[PredictedObject]:
"""Determines ten most probable image classes.
Determines 10 most probable classes of image. This info is afterwards processed
into user-friendly class PredictedObject (more precisely into list with objects
of this type).
Args:
original_image (np.ndarray): Figure - tensor, which we try to classify.
model (tf.keras.engine.functional.Functional): used ML model.
Returns:
List[PredictedObject]: List of PredictedObject objects.
"""
prediction = model.predict(original_image)
ten_best_classes = decode_predictions(prediction, top=10)[0]
predictions_list = []
for order_number_minus_one, element in enumerate(ten_best_classes):
class_name = element[1]
probability = round(100 * element[2], 2)
class_index = _get_class_index(prediction, order_number_minus_one)
predictions_list.append(
PredictedObject(order_number_minus_one + 1, class_name,
probability, class_index))
return predictions_list
def predict(image_path):
"""Use VGG19 to label image"""
img = image.load_img(image_path, target_size=image_size)
x = image.img_to_array(img)
x = np.expand_dims(x, axis=0)
x = preprocess_input(x)
predictions = model.predict(x)
plt.imshow(img)
print('Predicted:', decode_predictions(predictions, top=3))
def predict(image_path):
"""Use VGG19 to label image"""
pred = []
acc = []
model = VGG19(include_top=True, weights='imagenet')
img = image.load_img(urllib.request.urlopen(image_path),
target_size=(224, 224))
x = image.img_to_array(img)
x = np.expand_dims(x, axis=0)
x = preprocess_input(x)
predictions = model.predict(x)
plt.imshow(img)
for i in range(3):
pred.append(decode_predictions(predictions, top=3)[0][i][1])
acc.append(decode_predictions(predictions, top=3)[0][i][2])
pred_accuracy = {'Predicted': pred, 'Accuracy': acc}
return pred_accuracy
def PredictTop5_VGG19(image_path):
model = VGG19()
img = image.load_img(image_path, target_size=(224, 224))
x = image.img_to_array(img)
x = np.expand_dims(x, axis=0)
x = preprocess_input(x)
preds = model.predict(x)
labels = decode_predictions(preds, top=5)
K.clear_session()
labels = np.array(labels)
labels = np.squeeze(labels)
labels = labels[:, 1:3]
labels = dict(labels)
print(labels)
return labels
def trainer(things):
filename = things
# Load the VGG19 model
# https://keras.io/applications/#VGG19
model = VGG19(include_top=True, weights='imagenet')
# Define default image size for VGG19
image_size = (224, 224)
# Load the image and resize to default image size
image_path = os.path.join("static", "images", filename)
img = image.load_img(image_path, target_size=image_size)
plt.imshow(img)
# Preprocess image for model prediction
# This step handles scaling and normalization for VGG19
x = image.img_to_array(img)
x = np.expand_dims(x, axis=0)
x = preprocess_input(x)
# Make predictions
predictions = model.predict(x)
predictionsforshow = decode_predictions(predictions, top=3)
#print('Predicted:', decode_predictions(predictions, top=3))
plt.imshow(img)
return (predictionsforshow)
# Refactor above steps into reusable function
# def predict(image_path):
# """Use VGG19 to label image"""
# img = image.load_img(image_path, target_size=image_size)
# x = image.img_to_array(img)
# x = np.expand_dims(x, axis=0)
# x = preprocess_input(x)
# predictions = model.predict(x)
# plt.imshow(img)
# print('Predicted:', decode_predictions(predictions, top=3))
# Make predictions on the dog photo
#image_path = os.path.join("..", "images", "dog.jpeg")
#predict(image_path)
def main(myblob: func.InputStream):
logging.info(f"Python blob trigger function processed blob \n"
f"Name: {myblob.name}\n"
f"Blob Size: {myblob.length} bytes")
# Constants
img_width, img_height = 224, 224
# Load image from blob
bytes_image = myblob.read()
raw_image = load_img(io.BytesIO(bytes_image),
target_size=(img_width, img_height))
# Reshape data for the model
image = img_to_array(raw_image)
image = image.reshape((1, image.shape[0], image.shape[1], image.shape[2]))
# Prepare the image for the VGG model
image = preprocess_input(image)
# Load base model
if K.image_data_format() == 'channels_first':
input_shape = (3, img_width, img_height)
else:
input_shape = (img_width, img_height, 3)
test_model = VGG19(input_shape=input_shape, weights='imagenet')
# Perform image classification
prediction = test_model.predict(image)
# Convert the probabilities to class labels
label = decode_predictions(prediction)
# Retrieve the most likely result, e.g. highest probability
label = label[0][0]
logging.info(f"PREDICTION: {label[1]} | {label[2]*100}%")
def get_predictions(self, in_img, network_name, top=3):
# network model selection
model = None
size = (224, 224)
int_model = False
if network_name == 'VGG19':
if self.MODEL_VGG19 is None:
from tensorflow.keras.applications.vgg19 import VGG19
self.MODEL_VGG19 = VGG19(weights='imagenet')
model = self.MODEL_VGG19
int_model = True
from tensorflow.keras.applications.vgg19 import decode_predictions
elif network_name == 'DenseNet201':
if self.MODEL_DENSENET201 is None:
from tensorflow.python.keras.applications.densenet import DenseNet201
self.MODEL_DENSENET201 = DenseNet201(weights='imagenet')
model = self.MODEL_DENSENET201
from tensorflow.keras.applications.densenet import decode_predictions
elif network_name == 'MobileNetV2':
if self.MODEL_MOBILENET is None:
from tensorflow.keras.applications.mobilenet import MobileNet # (244,244)
self.MODEL_MOBILENET = MobileNet(weights='imagenet')
model = self.MODEL_MOBILENET
from tensorflow.keras.applications.mobilenet import decode_predictions
elif network_name == 'InceptionV3':
if self.MODEL_INCEPTIONV3 is None:
from tensorflow.keras.applications.inception_v3 import InceptionV3 # (299,299)
self.MODEL_INCEPTIONV3 = InceptionV3(weights='imagenet')
model = self.MODEL_INCEPTIONV3
size = (299, 299)
from tensorflow.keras.applications.inception_v3 import decode_predictions
elif network_name == 'ResNet50':
if self.MODEL_RESNET50 is None:
from tensorflow.python.keras.applications.resnet import ResNet50 # (244,244)
self.MODEL_RESNET50 = ResNet50(weights='imagenet')
model = self.MODEL_RESNET50
int_model = True
from tensorflow.keras.applications.resnet import decode_predictions
else:
print("no valid model selected")
return
# if input is a numpy image, convert it to a cv image
if (isinstance(in_img, numpy.ndarray)):
in_img = _to_cv_image(in_img)
img = cv2.resize(in_img, dsize=size, interpolation=cv2.INTER_CUBIC)
img = _cv_to_array(img)
if (int_model):
img = img * 255
img = numpy.expand_dims(img, axis=0)
# predict model and return top predictions
features = model.predict(img)
predictions = []
for p in decode_predictions(features, top=top)[0]:
predictions.append([p[0], p[1], float(p[2])])
# get the indexes of the top predictions
class_codes = numpy.flip(numpy.argsort(features[0]))[:top]
return (predictions, class_codes) # ottiene nome della classe predetta
### This is the basic image classifier code using transfer learning in VGG19###
from tensorflow.keras.applications.vgg19 import VGG19, decode_predictions
from tensorflow.keras.applications.imagenet_utils import preprocess_input
from tensorflow.keras.preprocessing import image
from tensorflow.keras.models import load_model
import numpy as np
def test(img, model):
img = image.load_img(img, target_size=(224, 224))
x = image.img_to_array(img)
x = np.expand_dims(x, axis=0)
x = preprocess_input(x)
preds = model.predict(x)
return preds
if __name__ == '__main__':
#model = VGG19(weights='imagenet') # Use this if you don't have model not in your local
model = load_model('pretrained weights/vgg19.h5'
) # use this if you have model in your local
test_image = 'images/2464903-1366x768.jpg' # pass the image you want to predict
prediction = test(test_image, model)
label = decode_predictions(prediction)
label = label[0][0]
print("Predicted object is " + str(label[1]) + " and it's score is " +
str(label[2] * 100))
image_path =IMAGES_DIR / 'rose.jpg'
print (image_path)
# read image in RGB format
image = imageio.imread(str(image_path))
# read image in BGR format
# image = cv2.imread(str(image_path))
print(image.shape)
image = vision.resize(image, 224, 224)
batch = expand_to_batch(image)
#batch = preprocess_input(batch)
batch = preprocess_caffe(batch, color_format="rgb")
a_model = vgg.model_vgg19(weights="imagenet")
b_model = VGG19()
#print(model.summary())
a_y = a_model.predict(batch)
b_y = b_model.predict(batch)
a_label = decode_predictions(a_y)
b_label = decode_predictions(b_y)
a_label = a_label[0][0]
b_label = b_label[0][0]
# print the classification
print('%s (%.2f%%)' % (a_label[1], a_label[2]*100))
print('%s (%.2f%%)' % (b_label[1], b_label[2]*100))
img=tf.io.read_file(img_file)
img=tf.image.decode_image(img,channels=3)
img=tf.image.convert_image_dtype(img,tf.float32)
shape=tf.cast(tf.shape(img)[:-1],tf.float32)
scale=max_img_size/max(shape)
new_shape=tf.cast(shape*scale,tf.int32)
img=tf.image.resize(img,new_shape)
return img[tf.newaxis,:]
def tensor2img(tensor):
if np.ndim(tensor)>int(3):
assert tensor.shape[0]==1; tensor=tensor[0]
pl.figure(figsize=(3,3)); pl.imshow(tensor)
pl.tight_layout(); pl.show()
for f in img_files:
input_file=urllib.request.urlopen(img_path+f)
output_file=open(f,'wb')
output_file.write(input_file.read())
output_file.close(); input_file.close()
for i in range(len(img_files)):
content_img=load_img(img_files[i])
x=vgg19.preprocess_input(content_img*255)
prediction_probabilities=mvgg19(x)
predict_top5=vgg19.decode_predictions(
prediction_probabilities.numpy())[0]
sp.pretty_print('example #%d'%(i+1))
display(pd.DataFrame(
[[class_name,prob]
for (number,class_name,prob) in predict_top5],
columns=['class name','prob']))
tensor2img(content_img)
num_classes = 1
uploaded_file = st.file_uploader("Choose Picture", type="jpg")
if uploaded_file is not None:
image = Image.open(uploaded_file)
st.image(image, caption='Uploaded Picture', use_column_width=True)
# predictions
image = preprocess(image)
#load VGG19 model
with st.spinner('Loading VGG19 Model'):
model = VGG19()
with st.spinner('Predicting Object'):
i_pred = model.predict(image)
label = decode_predictions(i_pred, top=num_classes)
with st.spinner('Confidence'):
# process output
confidence = round(label[0][0][2], 3)
st.write(confidence)
bar = st.progress(0)
prog_sec = 1.0
for b_progress in range(100):
time.sleep(prog_sec / 100.0)
bar.progress(int((b_progress + 1) * confidence))
confidence = round(confidence * 100, 2)
output = "# " + label[0][0][1] + " with " + str(
confidence) + " % confidence"
st.write(output)
image_size = (224, 224)
# Load the image and resize to default image size
image_path = os.path.join("..", "images", "animal1.jpg")
img = image.load_img(image_path, target_size=image_size)
plt.imshow(img)
# Preprocess image for model prediction
# This step handles scaling and normalization for VGG19
x = image.img_to_array(img)
x = np.expand_dims(x, axis=0)
x = preprocess_input(x)
# Make predictions
predictions = model.predict(x)
print('Predicted:', decode_predictions(predictions, top=3))
plt.imshow(img)
# Refactor above steps into reusable function
def predict(image_path):
"""Use VGG19 to label image"""
img = image.load_img(image_path, target_size=image_size)
x = image.img_to_array(img)
x = np.expand_dims(x, axis=0)
x = preprocess_input(x)
predictions = model.predict(x)
plt.imshow(img)
print('Predicted:', decode_predictions(predictions, top=3))
from tensorflow.keras.applications.vgg19 import VGG19
from tensorflow.keras.utils import plot_model
from tensorflow.keras.preprocessing import image
from tensorflow.keras.applications.vgg19 import preprocess_input, decode_predictions
from tensorflow.keras.models import Model
import numpy as np
base_model = VGG19(weights='imagenet', include_top=True)
#model = Model(inputs=base_model.input, outputs=base_model.get_layer('block4_pool').output)
#print(model.summary())
#plot_model(model, to_file='vgg.png')
img_path = 'elephant.jpg'
img = image.load_img(img_path, target_size=(224, 224))
x = image.img_to_array(img)
x = np.expand_dims(x, axis=0)
x = preprocess_input(x)
block4_pool_features = base_model.predict(x)
#print('Predicted:', decode_predictions(block4_pool_features, top=5)[0])
#print out the result of the prediction
# convert the probabilities to class labels
label = decode_predictions(block4_pool_features)
# retrieve the most likely result, e.g. highest probability
label = label[0][0]
# print the classification
print('%s (%.2f%%)' % (label[1], label[2] * 100))
def set_model(self, model_name, top_n=5):
if model_name == 'densenet':
self.model = densenet.DenseNet121(include_top=True,
weights='imagenet',
input_tensor=None,
input_shape=None,
pooling=None,
classes=1000)
self.target_size = (224, 224)
self.decoder = lambda x: densenet.decode_predictions(x, top=top_n)
self.ref = """
<ul>
<li><a href='https://arxiv.org/abs/1608.06993' target='_blank'>
Densely Connected Convolutional Networks</a> (CVPR 2017 Best Paper Award)</li>
</ul>
"""
elif model_name == 'inception_resnet_v2':
self.model = inception_resnet_v2.InceptionResNetV2(
include_top=True,
weights='imagenet',
input_tensor=None,
input_shape=None,
pooling=None,
classes=1000)
self.target_size = (299, 299)
self.decoder = lambda x: inception_resnet_v2.decode_predictions(
x, top=top_n)
self.ref = """
<ul>
<li><a href='https://arxiv.org/abs/1602.07261' target='_blank'>
Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning</a></li>
</ul>
"""
elif model_name == 'inception_v3':
self.model = inception_v3.InceptionV3(include_top=True,
weights='imagenet',
input_tensor=None,
input_shape=None,
pooling=None,
classes=1000)
self.target_size = (299, 299)
self.decoder = lambda x: inception_v3.decode_predictions(x,
top=top_n)
self.ref = """<ul>
<li><a href='https://arxiv.org/abs/1512.00567' target='_blank'>
Rethinking the Inception Architecture for Computer Vision</a></li>
</ul>
"""
elif model_name == 'mobilenet':
self.model = mobilenet.MobileNet(input_shape=None,
alpha=1.0,
depth_multiplier=1,
dropout=1e-3,
include_top=True,
weights='imagenet',
input_tensor=None,
pooling=None,
classes=1000)
self.target_size = (224, 224)
self.decoder = lambda x: mobilenet.decode_predictions(x, top=top_n)
self.ref = """<ul>
<li><a href='https://arxiv.org/abs/1704.04861' target='_blank'>
MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications</a></li>
</ul>
"""
elif model_name == 'mobilenet_v2':
self.model = mobilenet_v2.MobileNetV2(input_shape=None,
alpha=1.0,
include_top=True,
weights='imagenet',
input_tensor=None,
pooling=None,
classes=1000)
self.target_size = (224, 224)
self.decoder = lambda x: mobilenet_v2.decode_predictions(x,
top=top_n)
self.ref = """<ul>
<li><a href='https://arxiv.org/abs/1801.04381' target='_blank'>
MobileNetV2: Inverted Residuals and Linear Bottlenecks</a></li>
</ul>
"""
elif model_name == 'nasnet':
self.model = nasnet.NASNetLarge(input_shape=None,
include_top=True,
weights='imagenet',
input_tensor=None,
pooling=None,
classes=1000)
self.target_size = (224, 224)
self.decoder = lambda x: nasnet.decode_predictions(x, top=top_n)
self.ref = """<ul>
<li><a href='https://arxiv.org/abs/1707.07012' target='_blank'>
Learning Transferable Architectures for Scalable Image Recognition</a></li>
</ul>
"""
elif model_name == 'resnet50':
self.model = resnet50.ResNet50(include_top=True,
weights='imagenet',
input_tensor=None,
input_shape=None,
pooling=None,
classes=1000)
self.target_size = (224, 224)
self.decoder = lambda x: resnet50.decode_predictions(x, top=top_n)
self.ref = """<ul>
<li>ResNet :
<a href='https://arxiv.org/abs/1512.03385' target='_blank'>Deep Residual Learning for Image Recognition
</a></li>
</ul>
"""
elif model_name == 'vgg16':
self.model = vgg16.VGG16(include_top=True,
weights='imagenet',
input_tensor=None,
input_shape=None,
pooling=None,
classes=1000)
self.target_size = (224, 224)
self.decoder = lambda x: vgg16.decode_predictions(x, top=top_n)
self.ref = """<ul>
<li><a href='https://arxiv.org/abs/1409.1556' target='_blank'>
Very Deep Convolutional Networks for Large-Scale Image Recognition</a></li>
</ul>"""
elif model_name == 'vgg19':
self.model = vgg19.VGG19(include_top=True,
weights='imagenet',
input_tensor=None,
input_shape=None,
pooling=None,
classes=1000)
self.target_size = (224, 224)
self.decoder = lambda x: vgg19.decode_predictions(x, top=top_n)
self.ref = """<ul>
<li><a href='https://arxiv.org/abs/1409.1556' target='_blank'>Very Deep Convolutional Networks for Large-Scale Image Recognition</a></li>
</ul>"""
elif model_name == 'xception':
self.model = xception.Xception(include_top=True,
weights='imagenet',
input_tensor=None,
input_shape=None,
pooling=None,
classes=1000)
self.target_size = (299, 299)
self.decoder = lambda x: xception.decode_predictions(x, top=top_n)
self.ref = """<ul>
<li><a href='https://arxiv.org/abs/1610.02357' target='_blank'>Xception: Deep Learning with Depthwise Separable Convolutions</a></li>
</ul>"""
else:
logger.ERROR('There has no model name !!!')