SkalskiP

class FlattenLayer(Layer):

    def __init__(self):
        self._shape = ()

    def forward_pass(self, a_prev: np.array, training: bool) -> np.array:
        self._shape = a_prev.shape
        return np.ravel(a_prev).reshape(a_prev.shape[0], -1)

    def backward_pass(self, da_curr: np.array) -> np.array:

SkalskiP

def plot_shap_top_explanations(
    model: Model, 
    image: np.array, 
    class_names_mapping: Dict[int, str],
    top_preds_count: int = 3,
    fig_name: Optional[str] = None
) -> None:
    
    image_columns = 3
    image_rows = math.ceil(top_preds_count / image_columns)

SkalskiP

def plot_lime_top_explanations(
    model: Model, 
    image: np.array, 
    class_names_mapping: Dict[int, str],
    top_preds_count: int = 3,
    fig_name: Optional[str] = None
) -> None:
    
    image_columns = 3
    image_rows = math.ceil(top_preds_count / image_columns)

SkalskiP

def plot_eli5_top_explanations(
    model: Model, 
    image: np.array, 
    class_names_mapping: Dict[int, str],
    top_preds_count: int = 3,
    fig_name: Optional[str] = None
) -> None:
    
    image_columns = 3
    image_rows = math.ceil(top_preds_count / image_columns)

SkalskiP

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

SkalskiP

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

# 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

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

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)