{ "cells": [ { "cell_type": "code", "execution_count": 2, "id": "4ae47336", "metadata": {}, "outputs": [], "source": [ "import torch\n", "B, T, D = 4, 7, 32\n", "x = torch.randn(B, T, D)\n", "attn_mask = torch.triu(torch.ones(T, T, dtype=torch.bool), diagonal=1) # [T,T]\n", "pad_mask = torch.zeros(B, T, dtype=torch.bool) # no pads\n", "mha = torch.nn.MultiheadAttention(D, num_heads=4, batch_first=True)\n", "y, _ = mha(x, x, x, attn_mask=attn_mask, key_padding_mask=pad_mask) # should work\n" ] }, { "cell_type": "code", "execution_count": 6, "id": "e38e3fb5", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "tensor([[[0, 0, 0, 0, 1, 0, 0, 0, 0, 0],\n", " [0, 1, 0, 0, 0, 0, 0, 0, 0, 0],\n", " [0, 0, 0, 0, 0, 0, 0, 0, 0, 1]],\n", "\n", " [[0, 0, 1, 0, 0, 0, 0, 0, 0, 0],\n", " [0, 0, 0, 0, 1, 0, 0, 0, 0, 0],\n", " [0, 0, 0, 0, 0, 1, 0, 0, 0, 0]]])" ] }, "execution_count": 6, "metadata": {}, "output_type": "execute_result" } ], "source": [ "torch.nn.functional.one_hot(torch.tensor([\n", " [4, 1, 9],\n", " [2,4,5]\n", "]))" ] }, { "cell_type": "code", "execution_count": 7, "id": "7119ad53", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "device(type='cpu')" ] }, "execution_count": 7, "metadata": {}, "output_type": "execute_result" } ], "source": [ "torch.get_default_device()" ] }, { "cell_type": "code", "execution_count": 8, "id": "8c95691a", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "xpu\n" ] } ], "source": [ "from Project_Model.Libs.TorchShims import get_default_device\n", "\n", "print(get_default_device())" ] } ], "metadata": { "kernelspec": { "display_name": "deep_learning", "language": "python", "name": "python3" }, "language_info": { "codemirror_mode": { "name": "ipython", "version": 3 }, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", "version": "3.13.7" } }, "nbformat": 4, "nbformat_minor": 5 }