How to predict a single image with Skorch?

Question

I've just created a Neural Network with Skorch to detect aircrafts on a picture and I trained it with a train dataset with the shape (40000, 64, 64, 3).

Then I tested it with a test dataset of (15000, 64, 64, 3).

module = nn.Sequential(
    nn.Conv2d(3, 64, 3),
    nn.BatchNorm2d(64),
    nn.ReLU(),
    nn.MaxPool2d(2),
    nn.Conv2d(64, 64, 3),
    nn.BatchNorm2d(64),
    nn.ReLU(),
    nn.MaxPool2d(2),
    nn.Conv2d(64, 64, 3),
    nn.BatchNorm2d(64),
    nn.ReLU(),
    nn.MaxPool2d(2),
    nn.Flatten(),
    nn.Linear(6 * 6 * 64, 256),
    nn.Linear(256, 256),
    nn.ReLU(),
    nn.Linear(256, 2),
    nn.Softmax(),
)

early_stopping = EarlyStopping(monitor='valid_loss', lower_is_better=True)
net = NeuralNetClassifier(
    module,
    max_epochs=20,
    lr=1e-4,
    callbacks=[early_stopping],
    # Shuffle training data on each epoch
    iterator_train__shuffle=True,
    device="cuda" if torch.cuda.is_available() else "cpu",
    optimizer=optim.Adam
)
net.fit(
    train_images_balanced.transpose((0, 3, 1, 2)).astype(np.float32),
    train_labels_balanced
)

Now I need to test it on 512*512 pictures, so I have a new dataset of (30, 512, 512, 3).
So I took a sliding window code, that allowed me to divide the picture in 64*64 parts.

def sliding_window(image, stepSize, windowSize):
# slide a window across the image
for y in range(0, image.shape[0], stepSize):
    for x in range(0, image.shape[1], stepSize):
        # yield the current window
        yield (x, y, image[y:y + windowSize[1], x:x + windowSize[0]])

Now I wanna be able to predict if every single 64*64 image contains an aircraft, but I don't know how to do it, as net.predict() takes a dataset as an argument (arg : dim 4)

Answer 1

net.predict() takes a dataset as an argument (arg : dim 4)

net.predict accepts a number of data formats, among other things datasets. However, it seems for your case it would be best if it would accept torch tensors or numpy arrays - and it does! Just pass your 64x64 chunks to net.predict, something like this:

# (n, 512, 512, 3)
X = my_data
# (n, 4096, 64, 64, 3)
X = sliding_window(X, 64, 64)
# (n * 4096, 64, 64, 3)
X = X.reshape(-1, 64, 64, 3)
y = net.predict(X)