I'm following this Repo on creating Yolo v3 model from scratch in PyTorch. The only problem is that the bounding boxes are not as tight (close to the objects) in most images I tried. I compared them to the tutorial on creating Yolo v3 model but using TensorFlow. The tensorflow model produces excellent bounding boxed that are as tight as possible to the objects.
I tried to understand how the calculations are different between the two, but I'm finding myself getting stuck with the differences between torch and tf.
I believe the code for the bounding boxes in the tf tutorial comes from here:
def yolo_layer(inputs, n_classes, anchors, img_size, data_format):
"""Creates Yolo final detection layer.
Detects boxes with respect to anchors.
Args:
inputs: Tensor input.
n_classes: Number of labels.
anchors: A list of anchor sizes.
img_size: The input size of the model.
data_format: The input format.
Returns:
Tensor output.
"""
n_anchors = len(anchors)
inputs = tf.layers.conv2d(inputs, filters=n_anchors * (5 + n_classes),
kernel_size=1, strides=1, use_bias=True,
data_format=data_format)
shape = inputs.get_shape().as_list()
grid_shape = shape[2:4] if data_format == 'channels_first' else shape[1:3]
if data_format == 'channels_first':
inputs = tf.transpose(inputs, [0, 2, 3, 1])
inputs = tf.reshape(inputs, [-1, n_anchors * grid_shape[0] * grid_shape[1],
5 + n_classes])
strides = (img_size[0] // grid_shape[0], img_size[1] // grid_shape[1])
box_centers, box_shapes, confidence, classes = \
tf.split(inputs, [2, 2, 1, n_classes], axis=-1)
x = tf.range(grid_shape[0], dtype=tf.float32)
y = tf.range(grid_shape[1], dtype=tf.float32)
x_offset, y_offset = tf.meshgrid(x, y)
x_offset = tf.reshape(x_offset, (-1, 1))
y_offset = tf.reshape(y_offset, (-1, 1))
x_y_offset = tf.concat([x_offset, y_offset], axis=-1)
x_y_offset = tf.tile(x_y_offset, [1, n_anchors])
x_y_offset = tf.reshape(x_y_offset, [1, -1, 2])
box_centers = tf.nn.sigmoid(box_centers)
box_centers = (box_centers + x_y_offset) * strides
anchors = tf.tile(anchors, [grid_shape[0] * grid_shape[1], 1])
box_shapes = tf.exp(box_shapes) * tf.to_float(anchors)
confidence = tf.nn.sigmoid(confidence)
classes = tf.nn.sigmoid(classes)
inputs = tf.concat([box_centers, box_shapes,
confidence, classes], axis=-1)
return inputs
While the code for the bounding boxes for the pytorch model comes from here, and the explanation:
def bbox_iou(box1, box2):
"""
Returns the IoU of two bounding boxes
"""
#Get the coordinates of bounding boxes
b1_x1, b1_y1, b1_x2, b1_y2 = box1[:,0], box1[:,1], box1[:,2], box1[:,3]
b2_x1, b2_y1, b2_x2, b2_y2 = box2[:,0], box2[:,1], box2[:,2], box2[:,3]
#get the corrdinates of the intersection rectangle
inter_rect_x1 = torch.max(b1_x1, b2_x1)
inter_rect_y1 = torch.max(b1_y1, b2_y1)
inter_rect_x2 = torch.min(b1_x2, b2_x2)
inter_rect_y2 = torch.min(b1_y2, b2_y2)
#Intersection area
inter_area = torch.clamp(inter_rect_x2 - inter_rect_x1 + 1, min=0) * torch.clamp(inter_rect_y2 - inter_rect_y1 + 1, min=0)
#Union Area
b1_area = (b1_x2 - b1_x1 + 1)*(b1_y2 - b1_y1 + 1)
b2_area = (b2_x2 - b2_x1 + 1)*(b2_y2 - b2_y1 + 1)
iou = inter_area / (b1_area + b2_area - inter_area)
return iou
def predict_transform(prediction, inp_dim, anchors, num_classes, CUDA = True):
batch_size = prediction.size(0)
stride = inp_dim // prediction.size(2)
grid_size = inp_dim // stride
bbox_attrs = 5 + num_classes
num_anchors = len(anchors)
prediction = prediction.view(batch_size, bbox_attrs*num_anchors, grid_size*grid_size)
prediction = prediction.transpose(1,2).contiguous()
prediction = prediction.view(batch_size, grid_size*grid_size*num_anchors, bbox_attrs)
anchors = [(a[0]/stride, a[1]/stride) for a in anchors]
#Sigmoid the centre_X, centre_Y. and object confidencce
prediction[:,:,0] = torch.sigmoid(prediction[:,:,0])
prediction[:,:,1] = torch.sigmoid(prediction[:,:,1])
prediction[:,:,4] = torch.sigmoid(prediction[:,:,4])
#Add the center offsets
grid = np.arange(grid_size)
a,b = np.meshgrid(grid, grid)
x_offset = torch.FloatTensor(a).view(-1,1)
y_offset = torch.FloatTensor(b).view(-1,1)
if CUDA:
x_offset = x_offset.cuda()
y_offset = y_offset.cuda()
x_y_offset = torch.cat((x_offset, y_offset), 1).repeat(1,num_anchors).view(-1,2).unsqueeze(0)
prediction[:,:,:2] += x_y_offset
#log space transform height and the width
anchors = torch.FloatTensor(anchors)
if CUDA:
anchors = anchors.cuda()
anchors = anchors.repeat(grid_size*grid_size, 1).unsqueeze(0)
prediction[:,:,2:4] = torch.exp(prediction[:,:,2:4])*anchors
prediction[:,:,5: 5 + num_classes] = torch.sigmoid((prediction[:,:, 5 : 5 + num_classes]))
prediction[:,:,:4] *= stride
return prediction
