Skip to content

Instantly share code, notes, and snippets.

Avatar
💭
The Consciousness Has Shifted...The Awakening Has Begun

Rafal W. kenorb

💭
The Consciousness Has Shifted...The Awakening Has Begun
View GitHub Profile
@kenorb
kenorb / torch-relu-simple-sorting-example.ipynb
Created Jul 20, 2022
Torch-relu-simple-sorting-example.ipynb
View torch-relu-simple-sorting-example.ipynb
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
@kenorb
kenorb / syslog-gdm-errors.log
Created Dec 18, 2021
Setting a mode on head 0 failed: Insufficient permissions
View syslog-gdm-errors.log
==> auth.log <==
Dec 18 13:37:48 Ubuntu-ROG polkitd(authority=local): Unregistered Authentication Agent for unix-session:c14 (system bus name :1.628, object path /org/freedesktop/PolicyKit1/AuthenticationAgent, locale en_GB.UTF-8) (disconnected from bus)
==> gpu-manager-switch.log <==
==> kern.log <==
Dec 18 13:37:48 Ubuntu-ROG kernel: [ 7673.827587] [drm:nv_drm_master_set [nvidia_drm]] *ERROR* [nvidia-drm] [GPU ID 0x0000b400] Failed to grab modeset ownership
Dec 18 13:37:48 Ubuntu-ROG kernel: [ 7673.827750] [drm:nv_drm_master_set [nvidia_drm]] *ERROR* [nvidia-drm] [GPU ID 0x00006500] Failed to grab modeset ownership
Dec 18 13:37:48 Ubuntu-ROG kernel: [ 7673.827848] [drm:nv_drm_master_set [nvidia_drm]] *ERROR* [nvidia-drm] [GPU ID 0x00001800] Failed to grab modeset ownership
Dec 18 13:37:48 Ubuntu-ROG kernel: [ 7673.827940] [drm:nv_drm_master_set [nvidia_drm]] *ERROR* [nvidia-drm] [GPU ID 0x00001700] Failed to grab modeset ownership
View show_tensor_images.py
# Show Tensor Images utility function
from torchvision.utils import make_grid
import matplotlib.pyplot as plt
def show_tensor_images(image_tensor, num_images=25, size=(1, 28, 28)):
'''
Function for visualizing images: Given a tensor of images, number of images, and
size per image, plots and prints the images in a uniform grid.
'''
View backward_pass.py
def conv_backward(dH, cache):
'''
The backward computation for a convolution function
Arguments:
dH -- gradient of the cost with respect to output of the conv layer (H), numpy array of shape (n_H, n_W) assuming channels = 1
cache -- cache of values needed for the conv_backward(), output of conv_forward()
Returns:
dX -- gradient of the cost with respect to input of the conv layer (X), numpy array of shape (n_H_prev, n_W_prev) assuming channels = 1
View forward_pass.py
def conv_forward(X, W):
'''
The forward computation for a convolution function
Arguments:
X -- output activations of the previous layer, numpy array of shape (n_H_prev, n_W_prev) assuming input channels = 1
W -- Weights, numpy array of size (f, f) assuming number of filters = 1
Returns:
H -- conv output, numpy array of size (n_H, n_W)
View forward_pass.py
def conv_forward(X, W):
'''
The forward computation for a convolution function
Arguments:
X -- output activations of the previous layer, numpy array of shape (n_H_prev, n_W_prev) assuming input channels = 1
W -- Weights, numpy array of size (f, f) assuming number of filters = 1
Returns:
H -- conv output, numpy array of size (n_H, n_W)
View IRS 990 e-File Data (7) -- Generate Data Dictionary.ipynb
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.