如何在Keras中使用卷积LSTM实现位置估计?

我在Keras和Tensorflow中使用了LSTM。

我想实现位置估计。

我想输入电影(1个场景是15帧)并估计移动方块在电影中的位置。

输入为15帧。输出为2个变量(x,y)。

在以下代码中,估计精度太差。我该怎么办? 而且,我不理解AveragePoolG3D/重塑(没有这个,它将无法执行)。

# We create a layer which take as input movies of shape
# (n_frames, width, height, channels) and returns a movie
# of identical shape.

seq = Sequential()
seq.add(ConvLSTM2D(filters=40, kernel_size=(3, 3),
                   input_shape=(None, 80, 80, 1),
                   padding='same', return_sequences=True))
seq.add(BatchNormalization())

seq.add(ConvLSTM2D(filters=40, kernel_size=(3, 3),
                   padding='same', return_sequences=True))
seq.add(BatchNormalization())

seq.add(ConvLSTM2D(filters=40, kernel_size=(3, 3),
                   padding='same', return_sequences=True))
seq.add(BatchNormalization())

seq.add(ConvLSTM2D(filters=40, kernel_size=(3, 3),
                   padding='same', return_sequences=True))
seq.add(BatchNormalization())

#seq.add(Flatten())
seq.add(AveragePooling3D((1, 80, 80)))

seq.add(Reshape((-1, 40)))

seq.add(Dense(2))

#seq.add(Conv3D(filters=1, kernel_size=(3, 3, 3),
#               activation='sigmoid',
#               padding='same', data_format='channels_last'))

seq.compile(loss='mean_squared_error', optimizer='adam')
def generate_movies(n_samples=1200, n_frames=15):
    row = 80
    col = 80
    noisy_movies = np.zeros((n_samples, n_frames, row, col, 1), dtype=np.float)
    shifted_movies = np.zeros((n_samples, n_frames, row, col, 1),
                              dtype=np.float)
    square_x_y = np.zeros((n_samples, n_frames, 2), dtype=np.float)

    for i in range(n_samples):
        for j in range(1):
            # Initial position
            xstart = np.random.randint(20, 60)
            ystart = np.random.randint(20, 60)
            # Direction of motion
            directionx = np.random.randint(0, 3) - 1
            directiony = np.random.randint(0, 3) - 1

            # Size of the square
            w = np.random.randint(2, 4)

            for t in range(n_frames):
                x_shift = xstart + directionx * t
                y_shift = ystart + directiony * t
                noisy_movies[i, t, x_shift - w: x_shift + w,
                             y_shift - w: y_shift + w, 0] += 1

                # Make it more robust by adding noise.
                # The idea is that if during inference,
                # the value of the pixel is not exactly one,
                # we need to train the network to be robust and still
                # consider it as a pixel belonging to a square.
                if np.random.randint(0, 2):
                    noise_f = (-1)**np.random.randint(0, 2)
                    noisy_movies[i, t,
                                 x_shift - w - 1: x_shift + w + 1,
                                 y_shift - w - 1: y_shift + w + 1,
                                 0] += noise_f * 0.1

                # Shift the ground truth by 1
                x_shift = xstart + directionx * (t + 1)
                y_shift = ystart + directiony * (t + 1)
                shifted_movies[i, t, x_shift - w: x_shift + w,
                               y_shift - w: y_shift + w, 0] += 1

                square_x_y[i, t, 0] = x_shift/row
                square_x_y[i, t, 1] = y_shift/col

    # Cut to a 40x40 window
    #noisy_movies = noisy_movies[::, ::, 20:60, 20:60, ::]
    #shifted_movies = shifted_movies[::, ::, 20:60, 20:60, ::]
    #noisy_movies[noisy_movies >= 1] = 1
    #shifted_movies[shifted_movies >= 1] = 1
    return noisy_movies, shifted_movies, square_x_y

# Train the network
noisy_movies, shifted_movies, sq_x_y = generate_movies(n_samples = 1200)
seq.fit(noisy_movies[:1000], sq_x_y[:1000], batch_size=10,
        epochs=1, validation_split=0.05)