FastestDet
ssd_keras
FastestDet | ssd_keras | |
---|---|---|
1 | 4 | |
713 | 1,846 | |
- | - | |
0.0 | 0.0 | |
about 1 year ago | about 2 years ago | |
Python | Python | |
BSD 3-clause "New" or "Revised" License | Apache License 2.0 |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
FastestDet
-
FastestDet: a new ultra real-time anchor free target detection algorithm designed for ARM CPU, with only 250K parameters,
The time consumption in the table is measured by ncnn. The test platform is RK3568 ARM CPU. Compared with Yolo-fastest, the time consumption of fastestdet single core is reduced by 50%, and the index of map0.5 is 3.4% higher than Yolo-fastest. In fact, due to the increase of input resolution, the calculation amount of FastestDet is nearly twice that of Yolo-fastest. However, thanks to the minimalist network structure and the reduction of memory access, the actual test time on multiple platforms is greatly reduced, especially on single core or weak performance platforms, and the speed is increased by 50%+
ssd_keras
-
Failed to get convolution algorithm. This is probably because cuDNN failed to initialize,
In Tensorflow/ Keras when running the code from https://github.com/pierluigiferrari/ssd_keras, use the estimator: ssd300_evaluation. I received this error.
-
Shared weights between different implementations
Yeah, the order of axes was different between those 2. Another guy used https://github.com/pierluigiferrari/ssd_keras https://github.com/uhfband/keras2caffe/blob/master/keras2caffe/convert.py probably not much actual use but maybe some more reassurance?
-
Simplest way to deploy Keras NN model into C++?
Don't know about simplest, but we either used caffe or tensorrt, it is maybe a bit difficult to use but I'd actually say simple fast GPU inference is what it's geared towards. There is a keras -> caffe converter https://github.com/pierluigiferrari/ssd_keras here, I think. Caffe is a c++ lib, typical, with dependencies and all. I've never heard anything of tensorflow running on c++. But with tensorrt you should get an "artifact" that you'd load, no matter where it comes from
-
ValueError: Layer model expects 1 input(s), but it received 2 input tensors. Help?
Tensorflow V1 Keras code (original repo): Github Repo
What are some alternatives?
PaddleViT - :robot: PaddleViT: State-of-the-art Visual Transformer and MLP Models for PaddlePaddle 2.0+
layout-parser - A Unified Toolkit for Deep Learning Based Document Image Analysis
cppflow - Run TensorFlow models in C++ without installation and without Bazel
zero-shot-object-tracking - Object tracking implemented with the Roboflow Inference API, DeepSort, and OpenAI CLIP.
efficientnet-lite-keras - Keras reimplementation of EfficientNet Lite.
Mask-RCNN-TF2 - Mask R-CNN for object detection and instance segmentation on Keras and TensorFlow 2.0
a-PyTorch-Tutorial-to-Object-Detection - SSD: Single Shot MultiBox Detector | a PyTorch Tutorial to Object Detection
SSD-pytorch - SSD: Single Shot MultiBox Detector pytorch implementation focusing on simplicity
d2l-en - Interactive deep learning book with multi-framework code, math, and discussions. Adopted at 500 universities from 70 countries including Stanford, MIT, Harvard, and Cambridge.
FastMOT - High-performance multiple object tracking based on YOLO, Deep SORT, and KLT 🚀
keras2caffe - Keras to Caffe model converter tool