CODEWITHSUNDEEP
pythontensorflowkeras
AME
AME

Reputation: 71

Keras custom loss function for YOLO

I am trying to define a custom loss function in Keras

def yolo_loss(y_true, y_pred):

Here the shape of y_true and y_pred are [batch_size,19,19,5].

for each image in the batch, I want to compute the loss as:

loss =   
square(y_true[:,:,0] - y_pred[:,:,0])  
+ square(y_true[:,:,1] - y_pred[:,:,1])   
+ square(y_true[:,:,2] - y_pred[:,:,2])   
+ (sqrt(y_true[:,:,3]) - sqrt(y_pred[:,:,3]))  
+ (sqrt(y_true[:,:,4]) - sqrt(y_pred[:,:,4]))

I thought of a couple of ways of doing this,

1) using a for loop:

def yolo_loss(y_true, y_pred):
    y_ret = tf.zeros([1,y_true.shape[0]])
    for i in range(0,int(y_true.shape[0])):
        op1 = y_true[i,:,:,:]
        op2 = y_pred[i,:,:,:]
        class_error = tf.reduce_sum(tf.multiply((op1[:,:,0]-op2[:,:,0]),(op1[:,:,0]-op2[:,:,0])))
        row_error = tf.reduce_sum(tf.multiply((op1[:,:,1]-op2[:,:,1]),(op1[:,:,1]-op2[:,:,1])))
        col_error = tf.reduce_sum(tf.multiply((op1[:,:,2]-op2[:,:,2]),(op1[:,:,2]-op2[:,:,2])))
        h_error = tf.reduce_sum(tf.abs(tf.sqrt(op1[:,:,3])-tf.sqrt(op2[:,:,3])))
        w_error = tf.reduce_sum(tf.abs(tf.sqrt(op1[:,:,4])-tf.sqrt(op2[:,:,4])))
        total_error = class_error + row_error + col_error + h_error + w_error
        y_ret[0,i] = total_error
    return y_ret

This however gives me an error:

ValueError: Cannot convert a partially known TensorShape to a Tensor: (1, ?)

This is because I guess the batch size is undefined.

2) Another way is to apply the sqrt transformations to each of the image tensors in the batch and then subtract them and then apply the square transform.

for e.g

1) sqrt(y_true[:,:,:,3])  
2) sqrt(y_pred[:,:,:,3])  
3) sqrt(y_true[:,:,:,4])  
4) sqrt(y_pred[:,:,:,4])  
5) y_new = y_true-y_pred  
6) square(y_new[:,:,:,0])  
7) square(y_new[:,:,:,1])  
8) square(y_new[:,:,:,2])  
9) reduce_sum for each new tensor in the batch and return o/p in shape [1,batch_size]

However I could not find a way to do this in Keras.

Can someone suggest, what would be the best way to implement this loss function. I am using Keras with tensorflow at the backend.

Upvotes: 5

Views: 4778

Answers (1)

H.Bukhari
H.Bukhari

Reputation: 2261

You can have a look in to this git hub page. 

https://github.com/experiencor/keras-yolo2

Upvotes: 3

Related Questions