diff --git a/zad9_keras.py b/zad9_keras.py
new file mode 100644
index 0000000..baa8c13
--- /dev/null
+++ b/zad9_keras.py
@@ -0,0 +1,35 @@
+import numpy as np
+import tensorflow as tf
+from tensorflow.keras import Sequential
+from tensorflow.keras.layers import Flatten, Dense
+from tensorflow.keras.datasets import fashion_mnist
+
+np.random.seed(10)
+
+device = "gpu" if tf.config.list_physical_devices("GPU") else "cpu"
+print(device)
+
+fashion_mnist = tf.keras.datasets.fashion_mnist
+
+(train_images, train_labels), (test_images, test_labels) = fashion_mnist.load_data()
+
+train_images = train_images / 255.0
+test_images = test_images / 255.0
+
+train_images = train_images.reshape(-1, 28, 28, 1)
+test_images = test_images.reshape(-1, 28, 28, 1)
+
+
+neurons = 300
+
+model = Sequential([
+    Flatten(input_shape=(28, 28)),
+    Dense(neurons, activation='relu'),
+    Dense(10, activation='softmax')
+])
+
+model.compile(optimizer='adam', loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True), metrics=['accuracy'])
+model.fit(train_images, train_labels, epochs=10)
+test_loss, test_acc = model.evaluate(test_images,  test_labels, verbose=2)
+
+print('\naccuracy:', test_acc)
diff --git a/zad9_torch.py b/zad9_torch.py
new file mode 100644
index 0000000..fa08a18
--- /dev/null
+++ b/zad9_torch.py
@@ -0,0 +1,52 @@
+import torch
+import torch.nn as nn
+from torch.utils.data import DataLoader
+from torchvision import datasets
+from torchvision.transforms import Compose, Lambda, ToTensor
+
+torch.manual_seed(10)
+
+device = torch.device('cuda') if torch.cuda.is_available() else torch.device('cpu')
+print(device)
+
+trainset = datasets.FashionMNIST('data', train=True, download=True,
+                          transform=Compose([ToTensor(), Lambda(lambda x: x.flatten())]))
+testset = datasets.FashionMNIST('data', train=False, download=True,
+                         transform=Compose([ToTensor(), Lambda(lambda x: x.flatten())]))
+
+
+def train(model, dataset, n_iter=10, batch_size=256):
+    optimizer = torch.optim.SGD(model.parameters(), lr=0.01)
+    criterion = nn.NLLLoss()
+    dl = DataLoader(dataset, batch_size=batch_size)
+    model.train()
+    for epoch in range(n_iter):
+        for images, targets in dl:
+            optimizer.zero_grad()
+            out = model(images.to(device))
+            loss = criterion(out, targets.to(device))
+            loss.backward()
+            optimizer.step()
+        if epoch % 10 == 0:
+            print('epoch: %3d loss: %.4f' % (epoch, loss))
+
+
+def accuracy(model, dataset):
+    model.eval()
+    correct = sum([(model(images.to(device)).argmax(dim=1) == targets.to(device)).sum()
+                   for images, targets in DataLoader(dataset, batch_size=256)])
+    print(correct.float() / len(dataset))
+
+
+neurons = 300
+
+model = nn.Sequential(
+    nn.Linear(28 * 28, neurons),
+    nn.ReLU(),
+    nn.Linear(neurons, 10),
+    nn.LogSoftmax(dim=-1)
+).to(device)
+
+train(model, trainset)
+
+accuracy(model, testset)