daniel dantp-ai

Recently created

Least recently created

Recently updated

Least recently updated

dantp-ai / 2d_convolution.py

Last active March 18, 2023 14:35

2d convolution for stride of one with same output shape

	import numpy as np

	def convolve2D_same_output_shape(input_volume, kernel):

	kernel = np.flipud(np.fliplr(kernel))

	kernel_height = kernel.shape[0]
	kernel_width = kernel.shape[1]

	input_height = input_volume.shape[0]

dantp-ai / delete_all_local_brances_except_master_and_develop.sh

Created October 14, 2021 09:29

delete_all_local_brances_except_master_and_develop.sh

git branch | grep -v "master\|develop" | xargs git branch -D

dantp-ai / d5ae8e68696c00ad53ce60d984e8370d0c1e7b2e45df57530eb4f8596868fce1 ProtonVPN_mac_v2.1.0.dmg.txt.sha256.txt

Last active August 27, 2021 18:42

SHA256 signature for ProtonVPN_mac_v2.1.0.dmg

d5ae8e68696c00ad53ce60d984e8370d0c1e7b2e45df57530eb4f8596868fce1 ProtonVPN_mac_v2.1.0.dmg

dantp-ai / example_google.py

Last active May 21, 2021 08:30

Google Style Docstrings for Python and Numpy

	# -- coding: utf-8 --
	"""Example Google style docstrings.

	This module demonstrates documentation as specified by the `Google Python
	Style Guide`_. Docstrings may extend over multiple lines. Sections are created
	with a section header and a colon followed by a block of indented text.

	Example:
	Examples can be given using either the ``Example`` or ``Examples``
	sections. Sections support any reStructuredText formatting, including

dantp-ai / simple_seed_test.py

Last active October 31, 2020 21:06

A simple test showing that for the same random seed, code, and neural network weight initialization, the updated weights are the same (PyTorch, v1.6.0)

	import torch
	import torch.nn as nn
	from copy import deepcopy

	def trial(seed):
	device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
	torch.manual_seed(seed)
	input_size = 4
	output_size = 1
	step_size = 0.005