Skip to content
Navigation menu
Search
Powered by Algolia
Search
Log in
Create account
DEV Community
Close
#
computervision
Follow
Hide
Posts
Left menu
đź‘‹
Sign in
for the ability to sort posts by
relevant
,
latest
, or
top
.
Right menu
The Architecture of Generation: Understanding Diffusion Transformers (DiTs)
Mecky Alvin Tanuwidjaya
Mecky Alvin Tanuwidjaya
Mecky Alvin Tanuwidjaya
Follow
Nov 2
The Architecture of Generation: Understanding Diffusion Transformers (DiTs)
#
ai
#
computervision
#
machinelearning
#
deeplearning
Comments
Add Comment
2 min read
Moderation
Serving WeVisOne-VL-4B: two engines, two copies of the weights, one chess piece apart
InferenceKey
InferenceKey
InferenceKey
Follow
for
InferenceKey
Nov 3
Serving WeVisOne-VL-4B: two engines, two copies of the weights, one chess piece apart
#
ai
#
computervision
#
python
#
gpu
4
 reactions
Comments
Add Comment
5 min read
Moderation
Why Does the Wrong Face Show Up in My Multi-Face Tiny Desk AI Video? Identity Bleed, Spot Mapping and a Pre-Upload Check
Peiguan
Peiguan
Peiguan
Follow
Nov 2
Why Does the Wrong Face Show Up in My Multi-Face Tiny Desk AI Video? Identity Bleed, Spot Mapping and a Pre-Upload Check
#
ai
#
python
#
computervision
#
video
Comments
Add Comment
8 min read
Moderation
Turning a 5-minute talk into 7 images for an LLM: picking one sharp frame per scene
Nookforge Studio
Nookforge Studio
Nookforge Studio
Follow
Nov 1
Turning a 5-minute talk into 7 images for an LLM: picking one sharp frame per scene
#
computervision
#
python
#
ffmpeg
#
ai
Comments
Add Comment
4 min read
Moderation
Why object detectors miss small objects in big photos, and how tiling fixes it
Nookforge Studio
Nookforge Studio
Nookforge Studio
Follow
Nov 1
Why object detectors miss small objects in big photos, and how tiling fixes it
#
computervision
#
python
#
machinelearning
#
ai
Comments
Add Comment
3 min read
Moderation
I wanted to 3D-print a fox an AI made from one picture. The fix was to stop looking for its surface
Helgard
Helgard
Helgard
Follow
Nov 1
I wanted to 3D-print a fox an AI made from one picture. The fix was to stop looking for its surface
#
3dprinting
#
ai
#
python
#
computervision
Comments
Add Comment
6 min read
Moderation
Building an ANPR Gate Pipeline: Triggers, Confidence and Events
Suraj Informatics
Suraj Informatics
Suraj Informatics
Follow
Nov 1
Building an ANPR Gate Pipeline: Triggers, Confidence and Events
#
computervision
#
ocr
#
iot
#
architecture
Comments
Add Comment
2 min read
Moderation
Counting people at a bus door: why 98% accuracy is an engineering problem, not a sensor spec
Dimitri Rudenko
Dimitri Rudenko
Dimitri Rudenko
Follow
Nov 4
Counting people at a bus door: why 98% accuracy is an engineering problem, not a sensor spec
#
computervision
#
iot
#
softwareengineering
1
 reaction
Comments
Add Comment
6 min read
Moderation
Fixing 'There are no faces in the image' in Rekognition SearchFacesByImage
Ashish Sikka
Ashish Sikka
Ashish Sikka
Follow
Oct 31
Fixing 'There are no faces in the image' in Rekognition SearchFacesByImage
#
debugging
#
computervision
#
aws
#
python
Comments
Add Comment
7 min read
Moderation
Rekognition ProvisionedThroughputExceededException: TPS limits and backoff that holds up
Ashish Sikka
Ashish Sikka
Ashish Sikka
Follow
Oct 31
Rekognition ProvisionedThroughputExceededException: TPS limits and backoff that holds up
#
aws
#
python
#
performance
#
computervision
Comments
Add Comment
6 min read
Moderation
TensorRT Was Fast. My 1080p RTSP Pipeline Wasn't.
Igor
Igor
Igor
Follow
Oct 30
TensorRT Was Fast. My 1080p RTSP Pipeline Wasn't.
#
computervision
#
cuda
#
gpu
#
performance
Comments
Add Comment
5 min read
Moderation
Teaching a CNN to read hieroglyphs: 96.9% on 59 signs, and why my first model failed
Omar Essam El Sherbiny
Omar Essam El Sherbiny
Omar Essam El Sherbiny
Follow
Oct 30
Teaching a CNN to read hieroglyphs: 96.9% on 59 signs, and why my first model failed
#
machinelearning
#
deeplearning
#
python
#
computervision
Comments
Add Comment
4 min read
Moderation
Spatial Qualimetry: Extracting 3D Depth Profiles in Pure NumPy
Silver Kernel
Silver Kernel
Silver Kernel
Follow
Oct 30
Spatial Qualimetry: Extracting 3D Depth Profiles in Pure NumPy
#
computervision
#
python
#
numpy
#
math
Comments
Add Comment
5 min read
Moderation
How to Run Tencent WeVisOne-VL-4B Locally on 8 GB VRAM (Ollama Drops the Masks)
Alan West
Alan West
Alan West
Follow
Oct 29
How to Run Tencent WeVisOne-VL-4B Locally on 8 GB VRAM (Ollama Drops the Masks)
#
ai
#
machinelearning
#
computervision
#
llm
Comments
Add Comment
8 min read
Moderation
Will This Selfie Make a Good Malfoid AI Portrait? A Pre-Upload Photo Checker in Python (Face Count, Size, Sharpness, Exposure)
Peiguan
Peiguan
Peiguan
Follow
Nov 3
Will This Selfie Make a Good Malfoid AI Portrait? A Pre-Upload Photo Checker in Python (Face Count, Size, Sharpness, Exposure)
#
python
#
opencv
#
computervision
#
ai
1
 reaction
Comments
1
 comment
8 min read
Moderation
đź‘‹
Sign in
for the ability to sort posts by
relevant
,
latest
, or
top
.
We're a place where coders share, stay up-to-date and grow their careers.
Log in
Create account