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 quantization_diagnostic.csv from Datadragon110/freshwater-quantization-models: direct link, hf CLI and curl.
- Browser
- Download file 1.45 kB
-
https://huggingface.co/Datadragon110/freshwater-quantization-models/resolve/main/quantization_diagnostic.csv
- Command line
-
hf download hf://Datadragon110/freshwater-quantization-models/quantization_diagnostic.csv
-
curl -L -o quantization_diagnostic.csv https://huggingface.co/Datadragon110/freshwater-quantization-models/resolve/main/quantization_diagnostic.csv
1.45 kB
| arch,variant,acc,agree,size_kib,lat_med_ms,note | |
| effnetb0,keras_fp32,87.11484593837535,100.0,,, | |
| effnetb0,tflite_fp32,87.11484593837535,100.0,15700.1171875,9.382903999949121, | |
| effnetb0,tflite_dynamic,87.39495798319328,98.0392156862745,4454.78125,36.88469200005784, | |
| effnetb0,tflite_fp16,87.39495798319328,99.71988795518207,7915.2578125,9.315814000046885, | |
| effnetb0,int8_floatio_N50,75.35014005602241,80.67226890756302,4808.1171875,9.351804999823798, | |
| effnetb0,int8_uint8io_N50,75.35014005602241,80.67226890756302,4808.125,9.34732299992902,"(1.0, 0.0)" | |
| effnetb0,int8_floatio_N300,74.2296918767507,77.59103641456583,4808.1171875,9.293086000070616, | |
| effnetb0,int8_uint8io_N300,74.2296918767507,77.59103641456583,4808.125,9.837882000056197,"(1.0, 0.0)" | |
| mnv3small,keras_fp32,82.6330532212885,100.0,,, | |
| mnv3small,tflite_fp32,82.6330532212885,100.0,1690.84765625,0.929413999983808, | |
| mnv3small,tflite_dynamic,81.79271708683473,95.7983193277311,535.40625,7.933233999892764, | |
| mnv3small,tflite_fp16,82.35294117647058,99.71988795518207,865.16015625,0.9294010001212882, | |
| mnv3small,int8_floatio_N50,68.62745098039215,73.38935574229691,603.703125,1.3592049999715528, | |
| mnv3small,int8_uint8io_N50,68.62745098039215,73.38935574229691,603.71875,1.681738000115729,"(1.0, 0.0)" | |
| mnv3small,int8_floatio_N300,65.26610644257703,71.42857142857143,603.703125,1.339327999858142, | |
| mnv3small,int8_uint8io_N300,65.26610644257703,71.42857142857143,603.71875,1.7569460001141124,"(1.0, 0.0)" | |