Create Dataset to Detect multiple objects

AI Discussions
1

Hi, I’m trying to create a dataset from a list of images and I’m having issues when create the labels.

My objective is to detect multiple objects in every image so I created something like this:

labels = 
    # Image 1
    [
        [100, 50],  # Object 1 attributes (x, y)
        [250, 100],  # Object 2 attributes
    ],  
    # Image 2
    [
        [50, 60],  # Object 1 attributes
        [200, 70],  # Object 2 attributes
        [450, 40],  # Object 3 attributes
    ],
]

I have successfully trained a model when there is just one object to be detected. But when I try multiple objects it doesn’t, I have tried multiple approaches to use this label, but none have worked.

dataset = tf.data.Dataset.from_tensor_slices((X, tf.ragged.constant(y)))
model = tf.keras.Sequential([
    tfl.ZeroPadding2D(padding=(10, 10), input_shape=(535, 535, 4)),
    tfl.Conv2D(32, (7, 7)),
    tfl.BatchNormalization(axis=-1),
    tfl.ReLU(),
    tfl.MaxPool2D(),
    tfl.Flatten(),
    tfl.Dense(2, activation='linear')
])
model.compile(optimizer='adam', loss='mae', metrics=['mse', 'mae'])

Error:
TypeError: Some of the inputs are not tf.RaggedTensor. Input received: [tf.RaggedTensor(values=tf.RaggedTensor(values=Tensor("Cast_20:0", shape=(None,), dtype=float32), row_splits=Tensor("RaggedFromVariant/RaggedTensorFromVariant:1", shape=(None,), dtype=int64)), row_splits=Tensor("RaggedFromVariant/RaggedTensorFromVariant:0", shape=(None,), dtype=int64)), <tf.Tensor 'sequential_24/dense_24/BiasAdd:0' shape=(None, 2) dtype=float32>]

Please help =)