SkalskiP

def get_cost_value(Y_hat, Y):
    m = Y_hat.shape[1]
    cost = -1 / m * (np.dot(Y, np.log(Y_hat).T) + np.dot(1 - Y, np.log(1 - Y_hat).T))
    return np.squeeze(cost)

def get_accuracy_value(Y_hat, Y):
    Y_hat_ = convert_prob_into_class(Y_hat)
    return (Y_hat_ == Y).all(axis=0).mean()

SkalskiP

def single_layer_backward_propagation(dA_curr, W_curr, b_curr, Z_curr, A_prev, activation="relu"):
    m = A_prev.shape[1]
    
    if activation is "relu":
        backward_activation_func = relu_backward
    elif activation is "sigmoid":
        backward_activation_func = sigmoid_backward
    else:
        raise Exception('Non-supported activation function')
    

SkalskiP

def full_backward_propagation(Y_hat, Y, memory, params_values, nn_architecture):
    grads_values = {}
    m = Y.shape[1]
    Y = Y.reshape(Y_hat.shape)
   
    dA_prev = - (np.divide(Y, Y_hat) - np.divide(1 - Y, 1 - Y_hat));
    
    for layer_idx_prev, layer in reversed(list(enumerate(nn_architecture))):
        layer_idx_curr = layer_idx_prev + 1
        activ_function_curr = layer["activation"]

SkalskiP

def update(params_values, grads_values, nn_architecture, learning_rate):
    for layer_idx, layer in enumerate(nn_architecture):
        params_values["W" + str(layer_idx)] -= learning_rate * grads_values["dW" + str(layer_idx)]        
        params_values["b" + str(layer_idx)] -= learning_rate * grads_values["db" + str(layer_idx)]

    return params_values;

SkalskiP

def train(X, Y, nn_architecture, epochs, learning_rate):
    params_values = init_layers(nn_architecture, 2)
    cost_history = []
    accuracy_history = []
    
    for i in range(epochs):
        Y_hat, cashe = full_forward_propagation(X, params_values, nn_architecture)
        cost = get_cost_value(Y_hat, Y)
        cost_history.append(cost)
        accuracy = get_accuracy_value(Y_hat, Y)

SkalskiP

def train_batch(X, Y, nn_architecture, epochs, learning_rate, batch_size = 64, verbose=False, callback=None):
    params_values = init_layers(nn_architecture, 2)
    cost_history = []
    accuracy_history = []
    
    # Beginning of additional code snippet
    batch_number = X.shape[1] // batch_size
    # Ending of additional code snippet
    
    for i in range(epochs):

SkalskiP

# Clone framework
git clone https://github.com/ultralytics/yolov3.git
# Enter framework catalogue [Linux/MacOS]
cd ./yolov3
# Enter framework catalogue [Windows]
dir ./yolov3
# Setup Python environment
pip install -U -r requirements.txt

SkalskiP

4 0.360558 0.439186 0.068327 0.250741
7 0.697519 0.701205 0.078643 0.228243
3 0.198589 0.683692 0.076613 0.263441

SkalskiP

dataset
├── class_names.txt
├── images
│   ├── image_1.png
│   ├── image_2.png
│   └── image_3.png
│       ...
└── labels
    ├── image_1.txt
    ├── image_2.txt

SkalskiP

python3 detect.py 
  --source <test_sample_path>
  --cfg <configuration_file_path>
  --weights weights/best.py