def preprocess_image(image, image_size):
image = io.imread(image)
x = center_crop_and_resize(image, image_size=image_size)
x = preprocess_input(x)
x = np.expand_dims(x, 0)
return x
def read_image(path):
try:
return preprocess_input(
center_crop_and_resize(imread(path)[:, :, :3],
image_size=image_size))
except:
return None
def __image_classifier(response): """ Generates an EfficientNetB4 model and classifies images. Args: response (dict): Query response to send to API. Should be of itemDataType image. """ # Process images for index, item in enumerate(response['data']): image_base64 = item['itemData'] if image_base64 in cache: print(cache[image_base64]) response['data'][index]['ml_suggest'] = cache[image_base64][0][0][1] else: print(response['data'][index]['filename']) image = __image_decoder(image_base64) image = efn.center_crop_and_resize(image=image, image_size=IMG_SIZE) image = efn.preprocess_input(image) img_array = tf.keras.preprocessing.image.img_to_array(image) img_array = tf.expand_dims(img_array, 0) # Predict prediction = model.predict(img_array) prediction = tf.keras.applications.imagenet_utils.decode_predictions(prediction) # Append prediction to response print(prediction) response['data'][index]['ml_suggest'] = prediction[0][0][1] cache[image_base64] = prediction print(response['data'][index]['ml_suggest']) return response
def infer(model, image_path):
image = imread(image_path)
image_size = model.input_shape[1]
x = center_crop_and_resize(image, image_size=image_size)
x = preprocess_input(x)
x = np.expand_dims(x, 0)
predictions = model.predict(x)
predictions_with_labels = decode_predictions(predictions)
return {t[1]: t[2] for t in predictions_with_labels[0]}
def vstack_patch(img, coords): patches = [] for c in coords: patch = center_crop_and_resize(img[c[0][1]:c[1][1], c[0][0]:c[1][0]], image_size=224) patch = np.expand_dims(patch, axis=0) temp = np.array(patch, dtype="float") patches.append(temp) return np.vstack(patches)
def predict(image):
x = center_crop_and_resize(image, image_size=image_size)
image_modified = x
x = preprocess_input(x)
x = np.expand_dims(x, 0)
# make prediction and decode
tb._SYMBOLIC_SCOPE.value = True
y = model.predict(x)
res = decode_predictions(y)
# collect result and the modified image
data = {'res': res[0][0], 'new_image': image_modified}
return data
def predict(img, model): try: image_size = model.input_shape[1] x = center_crop_and_resize(img, image_size=image_size) x = np.expand_dims(x, 0) preds = model.predict(x) prob = np.max(preds) cid = np.unravel_index(preds.argmax(), preds.shape)[1] return cid, prob, x except: return 0, 0, 0
def load_img_imagenet(img_path, args):
"""Process the image of ImageNet data
Args:
img_path (string): Path of image
Returns:
x (array): array of the image
"""
if args.model == 'vgg16' or args.model == 'densenet201':
img = image.load_img(img_path, target_size=(224, 224))
x = image.img_to_array(img)
x = np.expand_dims(x, axis=0)
if args.model == 'vgg16':
from keras.applications.vgg16 import preprocess_input
elif args.model == 'densenet201':
from keras.applications.densenet import preprocess_input
x = preprocess_input(x)
return x
elif args.model == 'efficientnetb0' or args.model == 'efficientnetb7':
from efficientnet.keras import center_crop_and_resize, preprocess_input
from skimage.io import imread
image = imread(img_path)
image_size = args.image_size
x = center_crop_and_resize(image, image_size=image_size)
x = preprocess_input(x)
x = np.expand_dims(x, 0)
return x
elif args.model == 'efficientnet-b7':
from efficientnet.keras import center_crop_and_resize, preprocess_input
from skimage.io import imread
image = imread(img_path)
image_size = args.image_size
x = center_crop_and_resize(image, image_size=image_size)
x = preprocess_input(x)
x = np.expand_dims(x, 0)
return x
#name: Image Classification
#description: Image classification based of Efficientnet model
#language: python
#input: file file
#output: map classes [Detected classes with probabilities]
#tags: demo, panel, files, efficientnet
#condition: file.isFile && file.size < 1e6 && (file.name.endsWith("jpg") || file.name.endsWith("jpeg") || file.name.endsWith("png"))
#help-url: https://github.com/qubvel/efficientnet
import numpy as np
from skimage.io import imread
from efficientnet.keras import EfficientNetB0
from keras.applications.imagenet_utils import decode_predictions
from efficientnet.keras import center_crop_and_resize, preprocess_input
image = imread(file)
model = EfficientNetB0(weights='imagenet')
image_size = model.input_shape[1]
_image = center_crop_and_resize(image, image_size=image_size)
_image = preprocess_input(_image)
_image = np.expand_dims(_image, 0)
predicted = model.predict(_image)
predicted = decode_predictions(predicted)[0]
classes = {}
for p in predicted:
classes[p[1]] = float(p[2])
| +-- run_efficient_net.py
"""
frame_folder = os.path.join(os.getcwd(), 'frames') #if only the file is uploaded
final_predictions = list()
for video_folder in os.listdir('frames'):
media_id = video_folder
for frame in os.listdir(os.path.join(frame_folder, video_folder)):
frame_nr = frame[frame.rfind('_')+1:-4]
img_name = os.path.join(frame_folder, video_folder, frame)
img = imread(img_name)
# preprocess input
image_size = model.input_shape[1]
x = center_crop_and_resize(img, image_size=image_size)
x = preprocess_input(x)
x = np.expand_dims(x, 0)
y = model.predict(x)
prediction = decode_predictions(y, top=nr_classes)
pred_as_list = list()
for sublist in prediction:
for pred in sublist:
pred_as_list.append(pred[1])
pred_as_list.append(pred[2])
final_predictions.append([media_id, frame_nr] + pred_as_list)
df = pd.DataFrame(final_predictions, columns=df_colnames)
