Object Detection from a Webcam in Keras using YOLO model
By Nilesh. D. OholHey Everyone,
We will be understanding and implementing Machine learning using Computer Vision in this Tutorial.
The Python Library we are going to use is an Open-source deep learning API called Keras and also going to use the model called YOLO model for object detection task in real-time through the webcam.
What is Computer Vision?
Computer vision (CV) is a field of Artificial Intelligence which is Progressing which each breath we take. The aim of Computer Vision is to provide meaningful information out of an Image, Video, or Camera.
In this article, we will be using a Web Camera of the Laptop.
Yolo (You Only Look Once):
It is a sophisticated real-time object recognition algorithm. The Algorithm makes Object recognition using an efficient CNN(Convolutional Neural Network. The reason behind its name is that it requires only one forward propagation pass through the neural network and make predictions. YOLO’s CNN classifies the image by predicting multiple boxes and predict probabilities for those boxes. It is Extremely for a real-time Environment and outworks all the other Image Recognition algorithms.
Let’s dive into the Implementations!
The Modules required are:
- os
- colorsys
- cv2
- numpy
- keras
- yolo3 (User-defined Module)
In case if you don’t have these Modules you can type command on your virtual environment:
pip install os
pip install colorsys
pip install opencv-python
pip install numpy
pip install keras
Note: The Keras backend which we are using is Tensorflow 1.15 and not Tensorflow 2.0 or above.
To know the version of Tensorflow library in your System type the following in your Virtual Environment:
pip freeze
Incase if the version is 2.0 type the Command, ‘ pip install tensorflow==1.15 ‘
We need to download WEIGHT file into the folder model_data folder which you can download by clicking here
Now, We will convert this WEIGHT file into an H5 for implementing the Keras model.
Enter the following code into your Python Virtual Environment:
python convert.py model_data/yolov3.cfg model_data/yolov3.weights model_data/yolo_weights.h5
We need to add these two text files into the folder name ‘model_data’ :
coco_classes.txt:
person bicycle car motorbike aeroplane bus train truck boat traffic light fire hydrant stop sign parking meter bench bird cat dog horse sheep cow elephant bear zebra giraffe backpack umbrella handbag tie suitcase frisbee skis snowboard sports ball kite baseball bat baseball glove skateboard surfboard tennis racket bottle wine glass cup fork knife spoon bowl banana apple sandwich orange broccoli carrot hot dog pizza donut cake chair sofa pottedplant bed diningtable toilet tvmonitor laptop mouse remote keyboard cell phone microwave oven toaster sink refrigerator book clock vase scissors teddy bear hair drier toothbrush
These are the objects this model can detect.
yolo_anchor.txt:
10,13, 16,30, 33,23, 30,61, 62,45, 59,119, 116,90, 156,198, 373,326
yolo3 (user-defined library):
Now we are going to be ready to use Python code to detect object. So let’s continue…
Following are the Python file saved in the yolo3 folder:
model.py:
"""YOLO_v3 Model Defined in Keras."""
from functools import wraps
import numpy as np
import tensorflow as tf
from keras import backend as K
from keras.layers import Conv2D, Add, ZeroPadding2D, UpSampling2D, Concatenate, MaxPooling2D
from keras.layers.advanced_activations import LeakyReLU
from keras.layers.normalization import BatchNormalization
from keras.models import Model
from keras.regularizers import l2
from yolo3.utils import compose
@wraps(Conv2D)
def DarknetConv2D(*args, **kwargs):
"""Wrapper to set Darknet parameters for Convolution2D."""
darknet_conv_kwargs = {'kernel_regularizer': l2(5e-4)}
darknet_conv_kwargs['padding'] = 'valid' if kwargs.get('strides')==(2,2) else 'same'
darknet_conv_kwargs.update(kwargs)
return Conv2D(*args, **darknet_conv_kwargs)
def DarknetConv2D_BN_Leaky(*args, **kwargs):
"""Darknet Convolution2D followed by BatchNormalization and LeakyReLU."""
no_bias_kwargs = {'use_bias': False}
no_bias_kwargs.update(kwargs)
return compose(
DarknetConv2D(*args, **no_bias_kwargs),
BatchNormalization(),
LeakyReLU(alpha=0.1))
def resblock_body(x, num_filters, num_blocks):
'''A series of resblocks starting with a downsampling Convolution2D'''
# Darknet uses left and top padding instead of 'same' mode
x = ZeroPadding2D(((1,0),(1,0)))(x)
x = DarknetConv2D_BN_Leaky(num_filters, (3,3), strides=(2,2))(x)
for i in range(num_blocks):
y = compose(
DarknetConv2D_BN_Leaky(num_filters//2, (1,1)),
DarknetConv2D_BN_Leaky(num_filters, (3,3)))(x)
x = Add()([x,y])
return x
def darknet_body(x):
'''Darknent body having 52 Convolution2D layers'''
x = DarknetConv2D_BN_Leaky(32, (3,3))(x)
x = resblock_body(x, 64, 1)
x = resblock_body(x, 128, 2)
x = resblock_body(x, 256, 8)
x = resblock_body(x, 512, 8)
x = resblock_body(x, 1024, 4)
return x
def make_last_layers(x, num_filters, out_filters):
'''6 Conv2D_BN_Leaky layers followed by a Conv2D_linear layer'''
x = compose(
DarknetConv2D_BN_Leaky(num_filters, (1,1)),
DarknetConv2D_BN_Leaky(num_filters*2, (3,3)),
DarknetConv2D_BN_Leaky(num_filters, (1,1)),
DarknetConv2D_BN_Leaky(num_filters*2, (3,3)),
DarknetConv2D_BN_Leaky(num_filters, (1,1)))(x)
y = compose(
DarknetConv2D_BN_Leaky(num_filters*2, (3,3)),
DarknetConv2D(out_filters, (1,1)))(x)
return x, y
def yolo_body(inputs, num_anchors, num_classes):
"""Create YOLO_V3 model CNN body in Keras."""
darknet = Model(inputs, darknet_body(inputs))
x, y1 = make_last_layers(darknet.output, 512, num_anchors*(num_classes+5))
x = compose(
DarknetConv2D_BN_Leaky(256, (1,1)),
UpSampling2D(2))(x)
x = Concatenate()([x,darknet.layers[152].output])
x, y2 = make_last_layers(x, 256, num_anchors*(num_classes+5))
x = compose(
DarknetConv2D_BN_Leaky(128, (1,1)),
UpSampling2D(2))(x)
x = Concatenate()([x,darknet.layers[92].output])
x, y3 = make_last_layers(x, 128, num_anchors*(num_classes+5))
return Model(inputs, [y1,y2,y3])
def tiny_yolo_body(inputs, num_anchors, num_classes):
'''Create Tiny YOLO_v3 model CNN body in keras.'''
x1 = compose(
DarknetConv2D_BN_Leaky(16, (3,3)),
MaxPooling2D(pool_size=(2,2), strides=(2,2), padding='same'),
DarknetConv2D_BN_Leaky(32, (3,3)),
MaxPooling2D(pool_size=(2,2), strides=(2,2), padding='same'),
DarknetConv2D_BN_Leaky(64, (3,3)),
MaxPooling2D(pool_size=(2,2), strides=(2,2), padding='same'),
DarknetConv2D_BN_Leaky(128, (3,3)),
MaxPooling2D(pool_size=(2,2), strides=(2,2), padding='same'),
DarknetConv2D_BN_Leaky(256, (3,3)))(inputs)
x2 = compose(
MaxPooling2D(pool_size=(2,2), strides=(2,2), padding='same'),
DarknetConv2D_BN_Leaky(512, (3,3)),
MaxPooling2D(pool_size=(2,2), strides=(1,1), padding='same'),
DarknetConv2D_BN_Leaky(1024, (3,3)),
DarknetConv2D_BN_Leaky(256, (1,1)))(x1)
y1 = compose(
DarknetConv2D_BN_Leaky(512, (3,3)),
DarknetConv2D(num_anchors*(num_classes+5), (1,1)))(x2)
x2 = compose(
DarknetConv2D_BN_Leaky(128, (1,1)),
UpSampling2D(2))(x2)
y2 = compose(
Concatenate(),
DarknetConv2D_BN_Leaky(256, (3,3)),
DarknetConv2D(num_anchors*(num_classes+5), (1,1)))([x2,x1])
return Model(inputs, [y1,y2])
def yolo_head(feats, anchors, num_classes, input_shape, calc_loss=False):
"""Convert final layer features to bounding box parameters."""
num_anchors = len(anchors)
# Reshaping to batch, width, height, num_anchors and box_params
anchors_tensor = K.reshape(K.constant(anchors), [1, 1, 1, num_anchors, 2])
grid_shape = K.shape(feats)[1:3] # height, width
grid_y = K.tile(K.reshape(K.arange(0, stop=grid_shape[0]), [-1, 1, 1, 1]),
[1, grid_shape[1], 1, 1])
grid_x = K.tile(K.reshape(K.arange(0, stop=grid_shape[1]), [1, -1, 1, 1]),
[grid_shape[0], 1, 1, 1])
grid = K.concatenate([grid_x, grid_y])
grid = K.cast(grid, K.dtype(feats))
feats = K.reshape(
feats, [-1, grid_shape[0], grid_shape[1], num_anchors, num_classes + 5])
# Adjust preditions to each spatial grid point and anchor size.
box_xy = (K.sigmoid(feats[..., :2]) + grid) / K.cast(grid_shape[::-1], K.dtype(feats))
box_wh = K.exp(feats[..., 2:4]) * anchors_tensor / K.cast(input_shape[::-1], K.dtype(feats))
box_confidence = K.sigmoid(feats[..., 4:5])
box_class_probs = K.sigmoid(feats[..., 5:])
if calc_loss == True:
return grid, feats, box_xy, box_wh
return box_xy, box_wh, box_confidence, box_class_probs
def yolo_correct_boxes(box_xy, box_wh, input_shape, image_shape):
'''Get corrected boxes'''
box_yx = box_xy[..., ::-1]
box_hw = box_wh[..., ::-1]
input_shape = K.cast(input_shape, K.dtype(box_yx))
image_shape = K.cast(image_shape, K.dtype(box_yx))
new_shape = K.round(image_shape * K.min(input_shape/image_shape))
offset = (input_shape-new_shape)/2./input_shape
scale = input_shape/new_shape
box_yx = (box_yx - offset) * scale
box_hw *= scale
box_mins = box_yx - (box_hw / 2.)
box_maxes = box_yx + (box_hw / 2.)
boxes = K.concatenate([
box_mins[..., 0:1], # y_min
box_mins[..., 1:2], # x_min
box_maxes[..., 0:1], # y_max
box_maxes[..., 1:2] # x_max
])
# Now Scale the boxes back to the original image shape
boxes *= K.concatenate([image_shape, image_shape])
return boxes
def yolo_boxes_and_scores(feats, anchors, num_classes, input_shape, image_shape):
'''Process Conv layer output'''
box_xy, box_wh, box_confidence, box_class_probs = yolo_head(feats,
anchors, num_classes, input_shape)
boxes = yolo_correct_boxes(box_xy, box_wh, input_shape, image_shape)
boxes = K.reshape(boxes, [-1, 4])
box_scores = box_confidence * box_class_probs
box_scores = K.reshape(box_scores, [-1, num_classes])
return boxes, box_scores
def yolo_eval(yolo_outputs,
anchors,
num_classes,
image_shape,
max_boxes=20,
score_threshold=.6,
iou_threshold=.5):
"""Evaluate YOLO model on given input and return filtered boxes."""
num_layers = len(yolo_outputs)
anchor_mask = [[6,7,8], [3,4,5], [0,1,2]] if num_layers==3 else [[3,4,5], [1,2,3]] # default setting
input_shape = K.shape(yolo_outputs[0])[1:3] * 32
boxes = []
box_scores = []
for l in range(num_layers):
_boxes, _box_scores = yolo_boxes_and_scores(yolo_outputs[l],
anchors[anchor_mask[l]], num_classes, input_shape, image_shape)
boxes.append(_boxes)
box_scores.append(_box_scores)
boxes = K.concatenate(boxes, axis=0)
box_scores = K.concatenate(box_scores, axis=0)
mask = box_scores >= score_threshold
max_boxes_tensor = K.constant(max_boxes, dtype='int32')
boxes_ = []
scores_ = []
classes_ = []
for c in range(num_classes):
# TODO: use keras backend instead of tf.
class_boxes = tf.boolean_mask(boxes, mask[:, c])
class_box_scores = tf.boolean_mask(box_scores[:, c], mask[:, c])
nms_index = tf.image.non_max_suppression(
class_boxes, class_box_scores, max_boxes_tensor, iou_threshold=iou_threshold)
class_boxes = K.gather(class_boxes, nms_index)
class_box_scores = K.gather(class_box_scores, nms_index)
classes = K.ones_like(class_box_scores, 'int32') * c
boxes_.append(class_boxes)
scores_.append(class_box_scores)
classes_.append(classes)
boxes_ = K.concatenate(boxes_, axis=0)
scores_ = K.concatenate(scores_, axis=0)
classes_ = K.concatenate(classes_, axis=0)
return boxes_, scores_, classes_
def preprocess_true_boxes(true_boxes, input_shape, anchors, num_classes):
'''Preprocess true boxes to training input format
Parameters
----------
true_boxes: array, shape=(m, T, 5)
Absolute x_min, y_min, x_max, y_max, class_id relative to input_shape.
input_shape: array-like, hw, multiples of 32
anchors: array, shape=(N, 2), wh
num_classes: integer
Returns
-------
y_true: list of array, shape like yolo_outputs, xywh are reletive value
'''
assert (true_boxes[..., 4]<num_classes).all(), 'class id must be less than num_classes'
num_layers = len(anchors)//3 # default setting
anchor_mask = [[6,7,8], [3,4,5], [0,1,2]] if num_layers==3 else [[3,4,5], [1,2,3]]
true_boxes = np.array(true_boxes, dtype='float32')
input_shape = np.array(input_shape, dtype='int32')
boxes_xy = (true_boxes[..., 0:2] + true_boxes[..., 2:4]) // 2
boxes_wh = true_boxes[..., 2:4] - true_boxes[..., 0:2]
true_boxes[..., 0:2] = boxes_xy/input_shape[::-1]
true_boxes[..., 2:4] = boxes_wh/input_shape[::-1]
m = true_boxes.shape[0]
grid_shapes = [input_shape//{0:32, 1:16, 2:8}[l] for l in range(num_layers)]
y_true = [np.zeros((m,grid_shapes[l][0],grid_shapes[l][1],len(anchor_mask[l]),5+num_classes),
dtype='float32') for l in range(num_layers)]
# Expanding the dim for applying the broadcasting
anchors = np.expand_dims(anchors, 0)
anchor_maxes = anchors / 2.
anchor_mins = -anchor_maxes
valid_mask = boxes_wh[..., 0]>0
for b in range(m):
# Discard zero rows.
wh = boxes_wh[b, valid_mask[b]]
if len(wh)==0: continue
# Expand dim to apply broadcasting.
wh = np.expand_dims(wh, -2)
box_maxes = wh / 2.
box_mins = -box_maxes
intersect_mins = np.maximum(box_mins, anchor_mins)
intersect_maxes = np.minimum(box_maxes, anchor_maxes)
intersect_wh = np.maximum(intersect_maxes - intersect_mins, 0.)
intersect_area = intersect_wh[..., 0] * intersect_wh[..., 1]
box_area = wh[..., 0] * wh[..., 1]
anchor_area = anchors[..., 0] * anchors[..., 1]
iou = intersect_area / (box_area + anchor_area - intersect_area)
# Find best anchor for each true box
best_anchor = np.argmax(iou, axis=-1)
for t, n in enumerate(best_anchor):
for l in range(num_layers):
if n in anchor_mask[l]:
i = np.floor(true_boxes[b,t,0]*grid_shapes[l][1]).astype('int32')
j = np.floor(true_boxes[b,t,1]*grid_shapes[l][0]).astype('int32')
k = anchor_mask[l].index(n)
c = true_boxes[b,t, 4].astype('int32')
y_true[l][b, j, i, k, 0:4] = true_boxes[b,t, 0:4]
y_true[l][b, j, i, k, 4] = 1
y_true[l][b, j, i, k, 5+c] = 1
return y_true
def box_iou(b1, b2):
'''Return iou tensor
Parameters
----------
b1: tensor, shape=(i1,...,iN, 4), xywh
b2: tensor, shape=(j, 4), xywh
Returns
-------
iou: tensor, shape=(i1,...,iN, j)
'''
# Expanding the dim to apply broadcasting.
b1 = K.expand_dims(b1, -2)
b1_xy = b1[..., :2]
b1_wh = b1[..., 2:4]
b1_wh_half = b1_wh/2.
b1_mins = b1_xy - b1_wh_half
b1_maxes = b1_xy + b1_wh_half
# Expand the dim so that we can apply broadcasting
b2 = K.expand_dims(b2, 0)
b2_xy = b2[..., :2]
b2_wh = b2[..., 2:4]
b2_wh_half = b2_wh/2.
b2_mins = b2_xy - b2_wh_half
b2_maxes = b2_xy + b2_wh_half
intersect_mins = K.maximum(b1_mins, b2_mins)
intersect_maxes = K.minimum(b1_maxes, b2_maxes)
intersect_wh = K.maximum(intersect_maxes - intersect_mins, 0.)
intersect_area = intersect_wh[..., 0] * intersect_wh[..., 1]
b1_area = b1_wh[..., 0] * b1_wh[..., 1]
b2_area = b2_wh[..., 0] * b2_wh[..., 1]
iou = intersect_area / (b1_area + b2_area - intersect_area)
return iou
def yolo_loss(args, anchors, num_classes, ignore_thresh=.5, print_loss=False):
'''Return yolo_loss tensor
Parameters
----------
yolo_outputs: list of tensor, the output of yolo_body or tiny_yolo_body
y_true: list of array, the output of preprocess_true_boxes
anchors: array, shape=(N, 2), wh
num_classes: integer
ignore_thresh: float, the iou threshold whether to ignore object confidence loss
Returns
-------
loss: tensor, shape=(1,)
'''
num_layers = len(anchors)//3 # default setting
yolo_outputs = args[:num_layers]
y_true = args[num_layers:]
anchor_mask = [[6,7,8], [3,4,5], [0,1,2]] if num_layers==3 else [[3,4,5], [1,2,3]]
input_shape = K.cast(K.shape(yolo_outputs[0])[1:3] * 32, K.dtype(y_true[0]))
grid_shapes = [K.cast(K.shape(yolo_outputs[l])[1:3], K.dtype(y_true[0])) for l in range(num_layers)]
loss = 0
m = K.shape(yolo_outputs[0])[0] # batch size, tensor
mf = K.cast(m, K.dtype(yolo_outputs[0]))
for l in range(num_layers):
object_mask = y_true[l][..., 4:5]
true_class_probs = y_true[l][..., 5:]
grid, raw_pred, pred_xy, pred_wh = yolo_head(yolo_outputs[l],
anchors[anchor_mask[l]], num_classes, input_shape, calc_loss=True)
pred_box = K.concatenate([pred_xy, pred_wh])
# Darknet raw box to calculate loss.
raw_true_xy = y_true[l][..., :2]*grid_shapes[l][::-1] - grid
raw_true_wh = K.log(y_true[l][..., 2:4] / anchors[anchor_mask[l]] * input_shape[::-1])
raw_true_wh = K.switch(object_mask, raw_true_wh, K.zeros_like(raw_true_wh)) # avoid log(0)=-inf
box_loss_scale = 2 - y_true[l][...,2:3]*y_true[l][...,3:4]
# Find ignore mask, iterate over each of batch.
ignore_mask = tf.TensorArray(K.dtype(y_true[0]), size=1, dynamic_size=True)
object_mask_bool = K.cast(object_mask, 'bool')
def loop_body(b, ignore_mask):
true_box = tf.boolean_mask(y_true[l][b,...,0:4], object_mask_bool[b,...,0])
iou = box_iou(pred_box[b], true_box)
best_iou = K.max(iou, axis=-1)
ignore_mask = ignore_mask.write(b, K.cast(best_iou<ignore_thresh, K.dtype(true_box)))
return b+1, ignore_mask
_, ignore_mask = K.control_flow_ops.while_loop(lambda b,*args: b<m, loop_body, [0, ignore_mask])
ignore_mask = ignore_mask.stack()
ignore_mask = K.expand_dims(ignore_mask, -1)
# K.binary_crossentropy is helpful to avoid exp overflow.
xy_loss = object_mask * box_loss_scale * K.binary_crossentropy(raw_true_xy, raw_pred[...,0:2], from_logits=True)
wh_loss = object_mask * box_loss_scale * 0.5 * K.square(raw_true_wh-raw_pred[...,2:4])
confidence_loss = object_mask * K.binary_crossentropy(object_mask, raw_pred[...,4:5], from_logits=True)+ \
(1-object_mask) * K.binary_crossentropy(object_mask, raw_pred[...,4:5], from_logits=True) * ignore_mask
class_loss = object_mask * K.binary_crossentropy(true_class_probs, raw_pred[...,5:], from_logits=True)
xy_loss = K.sum(xy_loss) / mf
wh_loss = K.sum(wh_loss) / mf
confidence_loss = K.sum(confidence_loss) / mf
class_loss = K.sum(class_loss) / mf
loss += xy_loss + wh_loss + confidence_loss + class_loss
if print_loss:
loss = tf.Print(loss, [loss, xy_loss, wh_loss, confidence_loss, class_loss, K.sum(ignore_mask)], message='loss: ')
return loss
utils.py:
"""Miscellaneous utility functions."""
from functools import reduce
from PIL import Image
import numpy as np
from matplotlib.colors import rgb_to_hsv, hsv_to_rgb
import cv2
def compose(*funcs):
"""Compose arbitrarily many functions, evaluated left to right.
Reference: https://mathieularose.com/function-composition-in-python/
"""
# return lambda x: reduce(lambda v, f: f(v), funcs, x)
if funcs:
return reduce(lambda f, g: lambda *a, **kw: g(f(*a, **kw)), funcs)
else:
raise ValueError('Composition of empty sequence not supported.')
def image_preporcess(image, target_size, gt_boxes=None):
ih, iw = target_size
h, w, _ = image.shape
scale = min(iw/w, ih/h)
nw = int(scale * w)
nh = int(scale * h)
image_resized = cv2.resize(image, (nw, nh), interpolation=cv2.INTER_CUBIC)
image_paded = np.full(shape=[ih, iw, 3], fill_value=128.0)
dw, dh = (iw - nw) // 2, (ih-nh) // 2
image_paded[dh:nh+dh, dw:nw+dw, :] = image_resized
image_paded = np.array(image_paded, dtype='float32')
image_paded = image_paded / 255.
image_paded = np.expand_dims(image_paded, axis=0)
return image_paded
def rand(a=0, b=1):
return np.random.rand()*(b-a) + a
def get_random_data(annotation_line, input_shape, random=True, max_boxes=20, jitter=.3, hue=.1, sat=1.5, val=1.5, proc_img=True):
'''random preprocessing for real-time data augmentation'''
line = annotation_line.split()
image = Image.open(line[0])
iw, ih = image.size
h, w = input_shape
box = np.array([np.array(list(map(int,box.split(',')))) for box in line[1:]])
if not random:
# resize image
scale = min(w/iw, h/ih)
nw = int(iw*scale)
nh = int(ih*scale)
dx = (w-nw)//2
dy = (h-nh)//2
image_data=0
if proc_img:
image = image.resize((nw,nh), Image.BICUBIC)
new_image = Image.new('RGB', (w,h), (128,128,128))
new_image.paste(image, (dx, dy))
image_data = np.array(new_image)/255.
# correct boxes
box_data = np.zeros((max_boxes,5))
if len(box)>0:
np.random.shuffle(box)
if len(box)>max_boxes: box = box[:max_boxes]
box[:, [0,2]] = box[:, [0,2]]*scale + dx
box[:, [1,3]] = box[:, [1,3]]*scale + dy
box_data[:len(box)] = box
return image_data, box_data
# resize image
new_ar = w/h * rand(1-jitter,1+jitter)/rand(1-jitter,1+jitter)
scale = rand(.25, 2)
if new_ar < 1:
nh = int(scale*h)
nw = int(nh*new_ar)
else:
nw = int(scale*w)
nh = int(nw/new_ar)
image = image.resize((nw,nh), Image.BICUBIC)
# place image
dx = int(rand(0, w-nw))
dy = int(rand(0, h-nh))
new_image = Image.new('RGB', (w,h), (128,128,128))
new_image.paste(image, (dx, dy))
image = new_image
# flip image or not
flip = rand()<.5
if flip: image = image.transpose(Image.FLIP_LEFT_RIGHT)
# distort image
hue = rand(-hue, hue)
sat = rand(1, sat) if rand()<.5 else 1/rand(1, sat)
val = rand(1, val) if rand()<.5 else 1/rand(1, val)
x = rgb_to_hsv(np.array(image)/255.)
x[..., 0] += hue
x[..., 0][x[..., 0]>1] -= 1
x[..., 0][x[..., 0]<0] += 1
x[..., 1] *= sat
x[..., 2] *= val
x[x>1] = 1
x[x<0] = 0
image_data = hsv_to_rgb(x) # numpy array, 0 to 1
# correct boxes
box_data = np.zeros((max_boxes,5))
if len(box)>0:
np.random.shuffle(box)
box[:, [0,2]] = box[:, [0,2]]*nw/iw + dx
box[:, [1,3]] = box[:, [1,3]]*nh/ih + dy
if flip: box[:, [0,2]] = w - box[:, [2,0]]
box[:, 0:2][box[:, 0:2]<0] = 0
box[:, 2][box[:, 2]>w] = w
box[:, 3][box[:, 3]>h] = h
box_w = box[:, 2] - box[:, 0]
box_h = box[:, 3] - box[:, 1]
box = box[np.logical_and(box_w>1, box_h>1)] # discard invalid box
if len(box)>max_boxes: box = box[:max_boxes]
box_data[:len(box)] = box
return image_data, box_data
After including these python file folders into the folder name ‘yolo3’ and Including the text files into the folder name ‘model_data’.
This is Tree Representation of how your Directory is expected to look like:
Now we will run the following python file.
Webcam_Object_Recognition.py
import colorsys
import colorsys
import os
os.environ['CUDA_VISIBLE_DEVICES'] = '-1'
#if you want to implement on gpu type 0
import cv2
import numpy as np
from keras import backend as K
from keras.models import load_model
from keras.layers import Input
import time
from yolo3.model import yolo_eval, yolo_body, tiny_yolo_body
from yolo3.utils import image_preporcess
class YOLO(object):
_defaults = {
"model_path": 'model_data/yolo_weights.h5',
"anchors_path": 'model_data/yolo_anchors.txt',
"classes_path": 'model_data/coco_classes.txt',
"score" : 0.3,
"iou" : 0.45,
"model_image_size" : (416, 416),
"text_size" : 3,
}
@classmethod
def get_defaults(cls, n):
if n in cls._defaults:
return cls._defaults[n]
else:
return "Unrecognized attribute name '" + n + "'"
def __init__(self, **kwargs):
self.__dict__.update(self._defaults) # set up default values
self.__dict__.update(kwargs) # and update with user overrides
self.class_names = self._get_class()
self.anchors = self._get_anchors()
self.sess = K.get_session()
self.boxes, self.scores, self.classes = self.generate()
def _get_class(self):
classes_path = os.path.expanduser(self.classes_path)
with open(classes_path) as f:
class_names = f.readlines()
class_names = [c.strip() for c in class_names]
return class_names
def _get_anchors(self):
anchors_path = os.path.expanduser(self.anchors_path)
with open(anchors_path) as f:
anchors = f.readline()
anchors = [float(x) for x in anchors.split(',')]
return np.array(anchors).reshape(-1, 2)
def generate(self):
model_path = os.path.expanduser(self.model_path)
assert model_path.endswith('.h5'), 'Keras model or weights must be a .h5 file.'
# Load model, or construct model and load weights.
num_anchors = len(self.anchors)
num_classes = len(self.class_names)
is_tiny_version = num_anchors==6 # default setting
try:
self.yolo_model = load_model(model_path, compile=False)
except:
self.yolo_model = tiny_yolo_body(Input(shape=(None,None,3)), num_anchors//2, num_classes) \
if is_tiny_version else yolo_body(Input(shape=(None,None,3)), num_anchors//3, num_classes)
self.yolo_model.load_weights(self.model_path) # make sure model, anchors and classes match
else:
assert self.yolo_model.layers[-1].output_shape[-1] == \
num_anchors/len(self.yolo_model.output) * (num_classes + 5), \
'Mismatch between model and given anchor and class sizes'
print('{} model, anchors, and classes loaded.'.format(model_path))
# Generate colors for drawing bounding boxes.
hsv_tuples = [(x / len(self.class_names), 1., 1.)
for x in range(len(self.class_names))]
self.colors = list(map(lambda x: colorsys.hsv_to_rgb(*x), hsv_tuples))
self.colors = list(
map(lambda x: (int(x[0] * 255), int(x[1] * 255), int(x[2] * 255)),
self.colors))
np.random.shuffle(self.colors) # Shuffle colors to decorrelate adjacent classes.
# Now Generate the output tensor targets for filtered bounding boxes
self.input_image_shape = K.placeholder(shape=(2, ))
boxes, scores, classes = yolo_eval(self.yolo_model.output, self.anchors,
len(self.class_names), self.input_image_shape,
score_threshold=self.score, iou_threshold=self.iou)
return boxes, scores, classes
def detect_image(self, image):
if self.model_image_size != (None, None):
assert self.model_image_size[0]%32 == 0, 'Multiples of 32 required'
assert self.model_image_size[1]%32 == 0, 'Multiples of 32 required'
boxed_image = image_preporcess(np.copy(image), tuple(reversed(self.model_image_size)))
image_data = boxed_image
out_boxes, out_scores, out_classes = self.sess.run(
[self.boxes, self.scores, self.classes],
feed_dict={
self.yolo_model.input: image_data,
self.input_image_shape: [image.shape[0], image.shape[1]],#[image.size[1], image.size[0]],
K.learning_phase(): 0
})
#print('Found {} boxes for {}'.format(len(out_boxes), 'img'))
thickness = (image.shape[0] + image.shape[1]) // 600
fontScale=1
ObjectsList = []
for i, c in reversed(list(enumerate(out_classes))):
predicted_class = self.class_names[c]
box = out_boxes[i]
score = out_scores[i]
label = '{} {:.2f}'.format(predicted_class, score)
#label = '{}'.format(predicted_class)
scores = '{:.2f}'.format(score)
top, left, bottom, right = box
top = max(0, np.floor(top + 0.5).astype('int32'))
left = max(0, np.floor(left + 0.5).astype('int32'))
bottom = min(image.shape[0], np.floor(bottom + 0.5).astype('int32'))
right = min(image.shape[1], np.floor(right + 0.5).astype('int32'))
mid_h = (bottom-top)/2+top
mid_v = (right-left)/2+left
# put object rectangle
cv2.rectangle(image, (left, top), (right, bottom), self.colors[c], thickness)
# get text size
(test_width, text_height), baseline = cv2.getTextSize(label, cv2.FONT_HERSHEY_SIMPLEX, thickness/self.text_size, 1)
# put text rectangle
cv2.rectangle(image, (left, top), (left + test_width, top - text_height - baseline), self.colors[c], thickness=cv2.FILLED)
# put text above rectangle
cv2.putText(image, label, (left, top-2), cv2.FONT_HERSHEY_SIMPLEX, thickness/self.text_size, (0, 0, 0), 1)
# add everything to list
ObjectsList.append([top, left, bottom, right, mid_v, mid_h, label, scores])
return image, ObjectsList
def close_session(self):
self.sess.close()
def detect_img(self, image):
#image = cv2.imread(image, cv2.IMREAD_COLOR)
original_image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
original_image_color = cv2.cvtColor(original_image, cv2.COLOR_BGR2RGB)
r_image, ObjectsList = self.detect_image(original_image_color)
return r_image, ObjectsList
#Function that runs the Webcam of your Computer or Laptop
if __name__=="__main__":
startTime = time.time()
displayTime =2
fps =0
vid = cv2.VideoCapture(0)
yolo = YOLO()
if not vid.isOpened():
raise IOError("We cannot Open Webcam")
while True:
ret,frame = vid.read()
r_image, ObjectsList = yolo.detect_img(frame)
cv2.imshow("Webcam Over Here", r_image)
if cv2.waitKey(25) & 0xff ==ord("x"): #You may Choose any key to Terminate the Webcam.
cv2.destroyAllWindows()
break
fps +=1
TIME = time.time() - startTime
if TIME > displayTime:
print("FPS",fps/TIME)
fps = 0
startTime = time.time()
vid.release()
cv2.destroyAllWindows()
yolo.close_session()
The output of my program is given below:
You can see that we have successfully able to perform our object detection task in Python using the Keras library and using the popular Yolo model.
Thank you for reaching here.
Note: The Python version I have used is 3.7.4. If the python version is above it might not run.
For Tensorflow 1.15 Documentation: Click Here
Leave a Reply