Building your first Neural Network

Рет қаралды 7,123

Күн бұрын

Пікірлер: 22

@CodeEmporium Жыл бұрын

What other playlists should I make? Also, If you think I deserve it, please consider giving this video a like. Subscribe for more content like this.

@mehedihassan7824 Жыл бұрын

can you make some videos on implementing the transformer models in code?

@joachimguth6226 Жыл бұрын

Impressive the clarity of layout and speech.

@CodeEmporium Жыл бұрын

Thanks for the kind words.

@aligharaeini5971 9 ай бұрын

one of the best videos ever about NN , congrats

@prashlovessamosa 10 ай бұрын

your 101 series are super informative.

@martin3647martin Жыл бұрын

Would be cool if you ran though process of building a Neuron class step by step, to better understand how all parts integrate in code as we go before using more advanced libraries. So more step by step bottom up element by element building. I think it would be good way to practice learners intuition about all this. I found many of your videos highly educational. Great content!

@apollokre1d Жыл бұрын

Love the videos, liked and subscribed, looking forward to the series.

@CodeEmporium Жыл бұрын

Thanks so much! Definitely more to come every week

@rashedulhasanrijul5506 10 ай бұрын

Thanks for such a nice explanation

@katariya608 10 ай бұрын

its the algorithm to recommend me your video

@pradnyakarve6094 10 ай бұрын

Hello, could you please let me know why the following error ? RuntimeError: mat1 and mat2 shapes cannot be multiplied (1x5 and 4x6) code: with torch.no_grad(): model.eval() correct = 0 total = 0 for batch_x, batch_y in test_loader: outputs = model(batch_x) predicted = torch.max(outputs, 1) total += batch_y.size(0) correct += (predicted == batch_y).sum().item() accuracy = correct / total print(f'Test accuracy:{accuracy:.2f}') class NeuralNetwork(nn.Module): def __init__(self, input_size, hidden_size, num_classes): super(NeuralNetwork, self).__init__() self.fc1 = nn.Linear(input_size, hidden_size) self.relu = nn.ReLU() self.fc2 = nn.Linear(hidden_size, num_classes) def forward(self, x): out = self.fc1(x) out = self.relu(out) out = self.fc2(out) return out