def save(self, *args, **kwargs):
try:
img = load_img(self.picture, target_size=(299,299))
img_array = img_to_array(img)
## model takes 4D array bcoz it can use multiple images
## but our is only 1 so 1 at the beginning
## we need to convert our 3D array to 4d array (299, 299, 3) -> (1, 299, 299, 3)
## we can do so by using numpy
to_pred = np.expand_dims(img_array, axis=0) #(1,299,299, 3)
# preprocess input
preprocess = preprocess_input(to_pred)
## assign model
model = InceptionResNetV2(weights='imagenet')
prediction = model.predict(preprocess) ## returns large array of 0,0...some number
# this decodes the prediction
decoded = decode_predictions(prediction)[0][0]
thingName = decoded[1]
probab = decoded[2]
#print(decoded)
#print(thingName)
#print(probab)
self.classification = thingName
self.probability = probab
print('success')
except Exception as e:
print('classification failed', e)
super().save(*args, **kwargs)
def saveImg(self, frame, x, y, w, h):
global helmet_count, no_helmet_count, current_video, ref_area, the_line
area = w * h
# ref_area = area if ref_area == 0 else ref_area
# if area < ref_area*0.5:
# return
y0 = y - extra_top if y - extra_top > 0 else 0
bike_img = frame[y0:y + h, x:x + w]
sqr_img = cv2.resize(bike_img, (299, 299))
# img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
sqr_img = image.img_to_array(sqr_img)
imgx = np.expand_dims(sqr_img, axis=0)
preprocess_input(imgx) #may use /255. if something go wrong
preds = general_model.predict(imgx)
top = decode_predictions(preds, top=5)[0]
for result in top:
if result[1] == 'motor_scooter': #and result[2] > 0.1:
self.detectToken = 0
the_line = int(the_line * 0.5 + self.y * 0.5)
img = cv2.resize(bike_img, (299, 299))
img = img / 255.
if not self.rightward:
img = cv2.flip(img, 1)
preds = helmet_model.predict([[img]])
helmet = preds[0][1]
spt = current_video.split('/')
spt = spt[-1]
spt = spt.split('.')
spt = spt[0]
result_path = ''
if helmet > 0.5: #helmet
helmet_count += 1
result_path = "extracted/helmet/" + spt + "#" + str(
helmet_count)
self.status = (0, 255, 0)
else:
helmet = 1 - helmet
no_helmet_count += 1
result_path = "extracted/no_helmet/" + spt + "#" + str(
no_helmet_count)
self.status = (0, 0, 255)
helmet = str(helmet * 100)
helmet = helmet.split('.')
a = helmet[0]
b = helmet[1][:2]
result_path += " [" + a + "." + b + "%].jpg"
cv2.imwrite(result_path, bike_img)
break
def save(self, *args, **kwargs):
try:
img = load_img(self.picture, target_size=(299, 299))
img_array = img_to_array(img)
to_pred = np.expand_dims(img_array, axis=0)
prep = preprocess_input(to_pred)
model = InceptionResNetV2(weights="imagenet")
prediction = model.predict(prep)
decoded = decode_predictions(prediction)[0][0][1]
self.classified = str(decoded)
except Exception as e:
print("error", e)
super().save(*args, **kwargs)
def saveImg(self, frame, x, y, w, h):
global helmet_count, no_helmet_count
global current_video
y0 = y - extra_top if y - extra_top > 0 else 0
bike_img = frame[y0:y + h, x:x + w]
sqr_img = cv2.resize(bike_img, (299, 299))
# img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
sqr_img = image.img_to_array(sqr_img)
imgx = np.expand_dims(sqr_img, axis=0)
preprocess_input(imgx) #may use /255. if something go wrong
preds = general_model.predict(imgx)
top = decode_predictions(preds, top=5)[0]
for result in top:
if result[1] == 'motor_scooter': #and result[2] > 0.1:
img = cv2.resize(bike_img, (299, 299))
img = img / 255.
flip = ''
if not self.rightward:
img = cv2.flip(img, 1)
flip = 'flip'
preds = helmet_model.predict([[img]])
helmet = preds[0][1]
spt = current_video.split('/')
spt = spt[-1]
spt = spt.split('.')
spt = spt[0]
result_path = ''
if helmet > 0.5: #helmet
helmet_count += 1
result_path = path + "/helmet/" + spt + "#" + str(
helmet_count)
else:
helmet = 1 - helmet
no_helmet_count += 1
result_path = path + "/no_helmet/" + spt + "#" + str(
no_helmet_count)
helmet = str(helmet * 100)
helmet = helmet.split('.')
a = helmet[0]
b = helmet[1][:2]
result_path += "" + flip + " [" + a + "." + b + "%].jpg"
cv2.imwrite(result_path, bike_img)
break
self.isSaved = True
def save(self, *args, **kwargs):
try:
img = load_img(self.picture.path, target_size=(299, 299))
img_arr = img_to_array(img)
to_pred = np.expand_dims(img_arr, axis=0) # (1,299,299,3)
prep = preprocess_input(to_pred)
model = InceptionResNetV2(weights='imagenet')
prediction = model.predict(prep)
decoded = decode_predictions(prediction)[0][0][1]
self.classified = str(decoded)
print('Success')
except Exception as e:
print(f"Classification Failed {e}")
super().save(*args, **kwargs)
def save(self, *args, **kwargs):
try:
# print(self.picture)
img = load_img(self.picture, target_size=(299, 299))
img_array = img_to_array(img)
to_pred = np.expand_dims(img_array, axis=0)
prep = preprocess_input(to_pred)
model = InceptionResNetV2(weights='imagenet')
prediction = model.predict(prep)
decoded = decode_predictions(prediction)[0][0][1]
self.classified = decoded
print("success")
except:
print('classification failed')
super().save(*args, **kwargs)
def predict(img_path):
img = image.load_img(img_path, target_size=(299, 299))
x = image.img_to_array(img)
x = np.expand_dims(x, axis=0)
x = preprocess_input(x)
preds = model.predict(x)
# decode the results into a list of tuples (class, description, probability)
# (one such list for each sample in the batch)
return [{
'probability': float(p[2]),
'name': p[1],
'categories': synset.tree(p[0])
} for p in decode_predictions(preds, top=2)[0]]
def save(self, *args, **kwargs):
try:
img = load_img(self.picture, target_size=(299, 299))
img_array = img_to_array(img)
to_predict = np.expand_dims(img_array, axis=0)
preprossesing = preprocess_input(to_predict)
model = InceptionResNetV2(weights='imagenet')
prediction = model.predict(preprossesing)
decode = decode_predictions(prediction)[0][0][1]
self.classified = str(decode)
print('success')
except Exception as e:
print("classification failed", e)
super().save(*args, **kwargs)
import matplotlib.pyplot as plt
model = InceptionResNetV2(weights='imagenet')
count = 0
for i in range(60):
img_path = 'crop_image2/bike_'+str(i)+'.jpg'
img = image.load_img(img_path, target_size=(299, 299))
x = image.img_to_array(img)
x = np.expand_dims(x, axis=0)
x = preprocess_input(x)
preds = model.predict(x)
# decode the results into a list of tuples (class, description, probability)
# (one such list for each sample in the batch)
t3 = decode_predictions(preds, top=3)[0]
found = False
for result in t3:
if result[1] == 'motor_scooter':
# plt.imshow(img)
# plt.show()
count+=1
print(i, 'is motor scooter')
found = True
if not found:
print(i, 'is something else', t3)
print('scooter found',count)
# Predicted: [(u'n02504013', u'Indian_elephant', 0.82658225), (u'n01871265', u'tusker', 0.1122357), (u'n02504458', u'African_elephant', 0.061040461)]
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 !!!')
