Skip to content

Instantly share code, notes, and snippets.

View nyck33's full-sized avatar
🏠
Working from home

N. YC. Kim nyck33

🏠
Working from home
13 followers · 18 following
View GitHub Profile
@nyck33
nyck33 / buildmodel_tutorial.ipynb
Created May 9, 2023 13:01
buildmodel_tutorial.ipynb
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
@nyck33
nyck33 / images.ipynb
Created May 9, 2023 09:01
images.ipynb
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
@nyck33
nyck33 / adv_viz.ipynb
Last active May 16, 2023 03:36
adv_viz.ipynb
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
@nyck33
nyck33 / gist:4f9b4a02e070de0a9b060f3615c17826
Created May 18, 2023 10:03
ChatGPT tells me it's not the p norm but Euclidean from https://math.stackexchange.com/q/4700997/635903
For a neural network with predicted outputs yhat, I have the ground truth of y.  The error function is defined as the square root of the sum of the squares of the differences between each element of yhat and y. Is this the p norm?  Also, what is the derivative of this?  Please show all the math step-by-step.
ChatGPT
The error function you described is the Euclidean distance between the predicted output yhat and the ground truth label y. This is also known as L2 loss or L2 distance.
The expression for L2 Loss is as follows:
L2 Loss = sqrt((yhat - y)^2)
@nyck33
nyck33 / rapids-pip-colab-template.ipynb
Created May 19, 2023 07:28
rapids-pip-colab-template.ipynb
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
@nyck33
nyck33 / gist:14f952389cbb017973d0c632e358d8bb
Created May 22, 2023 02:41
Solara error
(infosec) nobu@LAPTOP-DNCQ5AAC:/mnt/d/1_gatechspring2023/infosec/showcase/mlonclampnobukim/mycode/solara$ solara run sol.py
Solara server is starting at http://localhost:8765
ERROR: Exception in ASGI application
Traceback (most recent call last):
File "/home/nobu/miniconda3/envs/infosec/lib/python3.8/site-packages/uvicorn/protocols/http/h11_impl.py", line 428, in run_asgi
result = await app( # type: ignore[func-returns-value]
File "/home/nobu/miniconda3/envs/infosec/lib/python3.8/site-packages/uvicorn/middleware/proxy_headers.py", line 78, in __call__
return await self.app(scope, receive, send)
File "/home/nobu/miniconda3/envs/infosec/lib/python3.8/site-packages/starlette/applications.py", line 122, in __call__
await self.middleware_stack(scope, receive, send)
@nyck33
nyck33 / alpaca-loracolab.ipynb
Created July 1, 2023 11:26
Alpaca-LoraColab.ipynb
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
@nyck33
nyck33 / visualPythonDemo.ipynb
Created July 9, 2023 00:56
visualPythonTitanicDemoErrorNumpy
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
@nyck33
nyck33 / kerasOCRKaggle.ipynb
Created July 15, 2023 07:09
Keras OCR uses CRAFT under the hood for bounding boxes but it's not accurate enough to get bounding boxes so I can input single lines to TrOCR
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
@nyck33
nyck33 / keras_ocr_born_digital_public.ipynb
Created July 15, 2023 07:58
keras_ocr_born_digital_public.ipynb
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.