Instructions to use Datadragon110/freshwater-quantization-models with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Keras
How to use Datadragon110/freshwater-quantization-models with Keras:
# !pip install -U keras tensorflow huggingface_hub # Keras needs TensorFlow installed to read "hf://" paths, so the tensorflow backend is selected here; # "jax" and "torch" also work for computation once TensorFlow is installed. import os os.environ["KERAS_BACKEND"] = "tensorflow" import keras model = keras.saving.load_model("hf://Datadragon110/freshwater-quantization-models") - Notebooks
- Google Colab
- Kaggle
Download summary_by_arch_format.csv from Datadragon110/freshwater-quantization-models: direct link, hf CLI and curl.
- Browser
- Download file 1.86 kB
-
https://huggingface.co/Datadragon110/freshwater-quantization-models/resolve/main/summary_by_arch_format.csv
- Command line
-
hf download hf://Datadragon110/freshwater-quantization-models/summary_by_arch_format.csv
-
curl -L -o summary_by_arch_format.csv https://huggingface.co/Datadragon110/freshwater-quantization-models/resolve/main/summary_by_arch_format.csv
1.86 kB
| protocol,arch,fmt,n,acc_mean,acc_std,acc_ci95,acc_min,acc_max,macro_f1,size_kib,lat_med_ms | |
| grouped_cv,effnetb0,keras_fp32,5,88.00414665053687,0.996670209419114,1.2375295171179224,87.11484593837535,89.59537572254335,87.95973586912416,, | |
| grouped_cv,effnetb0,tflite_fp32,5,88.00414665053687,0.996670209419114,1.2375295171179224,87.11484593837535,89.59537572254335,87.95973586912416,15700.115625,9.455779199970493 | |
| grouped_cv,effnetb0,int8_uint8io,5,74.17580478211958,3.104368432345398,3.854582519603546,70.8092485549133,78.77906976744185,74.16202385276188,4808.125,9.49624939999012 | |
| grouped_cv,mnv3small,keras_fp32,5,79.2868943307749,2.255687515805522,2.800805979573406,76.74418604651163,82.6330532212885,79.19899023474002,, | |
| grouped_cv,mnv3small,tflite_fp32,5,79.2868943307749,2.255687515805522,2.800805979573406,76.74418604651163,82.6330532212885,79.19899023474002,1690.84609375,0.921235200121373 | |
| grouped_cv,mnv3small,int8_uint8io,5,60.00659370827513,5.222345227944535,6.484398055729971,53.10734463276836,65.26610644257703,58.82242607406547,603.7171875,1.7197889998897153 | |
| paper_protocol,effnetb0,keras_fp32,1,93.28571428571428,,,93.28571428571428,93.28571428571428,93.2737185059682,, | |
| paper_protocol,effnetb0,tflite_fp32,1,93.28571428571428,,,93.28571428571428,93.28571428571428,93.2737185059682,15700.1171875,9.34867749992918 | |
| paper_protocol,effnetb0,int8_uint8io,1,79.14285714285715,,,79.14285714285715,79.14285714285715,79.11728896448331,4808.125,9.425470999758543 | |
| paper_protocol,mnv3small,keras_fp32,1,83.71428571428572,,,83.71428571428572,83.71428571428572,83.61648850936513,, | |
| paper_protocol,mnv3small,tflite_fp32,1,83.71428571428572,,,83.71428571428572,83.71428571428572,83.61648850936513,1690.84765625,0.9180014999401463 | |
| paper_protocol,mnv3small,int8_uint8io,1,65.71428571428571,,,65.71428571428571,65.71428571428571,65.09150769958242,603.71875,1.6796439999779975 | |