def get_classification(self, img):
# Bounding Box Detection.
try:
with self.detection_graph.as_default():
category_index = self.labelify()
# Expand dimension since the model expects image to have shape [1, None, None, 3].
img_expanded = np.expand_dims(img, axis=0)
(boxes, scores, classes, num) = self.sess.run(
[self.d_boxes, self.d_scores, self.d_classes, self.num_d],
feed_dict={self.image_tensor: img_expanded})
vis_util.visualize_boxes_and_labels_on_image_array(
img,
np.squeeze(boxes),
np.squeeze(classes).astype(np.int32),
np.squeeze(scores),
category_index,
use_normalized_coordinates=True,
line_thickness=8)
boxes = self.detection_graph.get_tensor_by_name(
'detection_boxes:0')
scores = self.detection_graph.get_tensor_by_name(
'detection_scores:0')
classes = self.detection_graph.get_tensor_by_name(
'detection_classes:0')
num_detections = self.detection_graph.get_tensor_by_name(
'num_detections:0')
return img
except Exception as e:
print("Exception during classification", e)
return
def create(self):
self._ratio = 28
self._input_path = '../dataset/short/00001_00_0.1s.ARW'
self._pattern = 0
def pack_raw(raw):
# pack Bayer image to 4 channels
im = raw.raw_image_visible.astype(np.float32)
im = np.maximum(im - 512, 0) / (16383 - 512) # subtract the black level
im = np.expand_dims(im, axis=2)
img_shape = im.shape
H = img_shape[0]
W = img_shape[1]
out = np.concatenate((im[0:H:2, 0:W:2, :],
im[0:H:2, 1:W:2, :],
im[1:H:2, 1:W:2, :],
im[1:H:2, 0:W:2, :]), axis=2)
return out
# 读入图像
raw = rawpy.imread(self._input_path)
input_full = np.expand_dims(pack_raw(raw), axis=0) * self._ratio
input_full = np.minimum(input_full, 1.0)
self._pattern = input_full
return self._pattern
def load_raw(img_path):
ratio = 300
raw = rawpy.imread(img_path)
input_full = np.expand_dims(pack_raw(raw), axis=0) * ratio
input_full = np.minimum(input_full, 1.0)
return input_full
def load_raw2(in_name, input_dir, ratio):
img_path = os.path.join(input_dir, in_name)
raw = rawpy.imread(img_path)
input_full = np.expand_dims(pack_raw(raw), axis=0) * ratio
input_full = np.minimum(input_full, 1.0)
# # keras 中是CHWN
# channel_fist_img = covnert_to_channel_first(input_full)
return input_full
def load_raw(in_name, gt_dir, input_dir):
ratio, img_path, = get_ratio(in_name, gt_dir, input_dir)
raw = rawpy.imread(img_path)
input_full = np.expand_dims(pack_raw(raw), axis=0) * ratio
input_full = np.minimum(input_full, 1.0)
# # keras 中是CHWN
# channel_fist_img = covnert_to_channel_first(input_full)
return input_full
def pack_raw(raw):
# pack Bayer image to 4 channels
im = raw.raw_image_visible.astype(np.float32)
im = np.maximum(im - 512, 0) / (16383 - 512) # subtract the black level
im = np.expand_dims(im, axis=2)
img_shape = im.shape
H = img_shape[0]
W = img_shape[1]
out = np.concatenate((im[0:H:2, 0:W:2, :], im[0:H:2, 1:W:2, :],
im[1:H:2, 1:W:2, :], im[1:H:2, 0:W:2, :]),
axis=2)
return out
def unit_vector(data, axis=None, out=None):
"""Return ndarray normalized by length,
i.e. Euclidean norm, along axis.
>>> v0 = np.random.random(3)
>>> v1 = unit_vector(v0)
>>> np.allclose(v1, v0 / np.linalg.norm(v0))
True
>>> v0 = np.random.rand(5, 4, 3)
>>> v1 = unit_vector(v0, axis=-1)
>>> v2 = v0 / np.expand_dims(np.sqrt(np.sum(v0*v0, axis=2)), 2)
>>> np.allclose(v1, v2)
True
>>> v1 = unit_vector(v0, axis=1)
>>> v2 = v0 / np.expand_dims(np.sqrt(np.sum(v0*v0, axis=1)), 1)
>>> np.allclose(v1, v2)
True
>>> v1 = np.empty((5, 4, 3))
>>> unit_vector(v0, axis=1, out=v1)
>>> np.allclose(v1, v2)
True
>>> list(unit_vector([]))
[]
>>> list(unit_vector([1]))
[1.0]
"""
if out is None:
data = np.array(data, dtype=np.float64, copy=True)
if data.ndim == 1:
data /= np.sqrt(np.dot(data, data))
return data
else:
if out is not data:
out[:] = np.array(data, copy=False)
data = out
length = np.atleast_1d(np.sum(data * data, axis))
np.sqrt(length, length)
if axis is not None:
length = np.expand_dims(length, axis)
data /= length
if out is None:
return data
import np as np
from keras.preprocessing import image
import numpy as np
import matplotlib.pyplot as plt
from keras.models import load_model
from keras.applications.vgg16 import VGG16, decode_predictions
img = image.load_img("VGG16-asphalt_crack_detector/image_cat.jpeg",
target_size=(224, 224))
img = np.asarray(img)
plt.imshow(img)
img = np.expand_dims(img, axis=0)
saved_model = VGG16()
output = saved_model.predict(img)
print('Predicted:', decode_predictions(output, top=1)[0])
if output[0][0] > output[0][1]:
print("dog")
else:
print('cat')