Instructions to use shkelqim2026/EfficientNet with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Keras
How to use shkelqim2026/EfficientNet 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://shkelqim2026/EfficientNet") - Notebooks
- Google Colab
- Kaggle
Download Output/efficientnet_cpu_latency_results.csv from shkelqim2026/EfficientNet: direct link, hf CLI and curl.
- Browser
- Download file 2.71 kB
-
https://huggingface.co/shkelqim2026/EfficientNet/resolve/main/Output/efficientnet_cpu_latency_results.csv
- Command line
-
hf download hf://shkelqim2026/EfficientNet/Output/efficientnet_cpu_latency_results.csv
-
curl -L -o efficientnet_cpu_latency_results.csv https://huggingface.co/shkelqim2026/EfficientNet/resolve/main/Output/efficientnet_cpu_latency_results.csv
2.71 kB
| timestamp,status,model,model_file,device,operating_system,python_version,tensorflow_version,keras_version,precision_policy,input_height,input_width,input_channels,batch_size,warmup_runs,timed_runs,intra_op_threads,inter_op_threads,mean_latency_ms,median_latency_ms,std_latency_ms,min_latency_ms,max_latency_ms,p05_latency_ms,p95_latency_ms,throughput_images_per_second,total_parameters,total_parameters_millions,error_type,error_message | |
| 8/22/2026 17:39,OK,efficientnet_b0_cpu_ready,efficientnet_b0_cpu_ready.keras,CPU,Windows-10-10.0.26200-SP0,3.11.9,2.20.0,3.13.2,"<DTypePolicy ""float32"">",224,224,1,1,50,200,0,0,407.479107,345.51155,139.1344012,328.153,1102.9921,330.214945,731.39362,2.454113555,4840871,4.840871,, | |
| 8/22/2026 17:41,OK,efficientnet_b1_cpu_ready,efficientnet_b1_cpu_ready.keras,CPU,Windows-10-10.0.26200-SP0,3.11.9,2.20.0,3.13.2,"<DTypePolicy ""float32"">",224,224,1,1,50,200,0,0,512.793599,474.42635,71.43039038,458.4577,889.393,464.227885,655.833345,1.950102345,7366539,7.366539,, | |
| 8/22/2026 17:44,OK,efficientnet_b2_cpu_ready,efficientnet_b2_cpu_ready.keras,CPU,Windows-10-10.0.26200-SP0,3.11.9,2.20.0,3.13.2,"<DTypePolicy ""float32"">",224,224,1,1,50,200,0,0,479.457135,474.47535,23.61584547,467.8686,663.3822,469.17152,491.768415,2.085692186,8625405,8.625405,, | |
| 8/22/2026 17:46,OK,efficientnet_b3_cpu_ready,efficientnet_b3_cpu_ready.keras,CPU,Windows-10-10.0.26200-SP0,3.11.9,2.20.0,3.13.2,"<DTypePolicy ""float32"">",224,224,1,1,50,200,0,0,544.2748765,543.41535,4.999846049,537.461,579.7511,539.2282,550.80612,1.837306926,11705907,11.705907,, | |
| 8/22/2026 17:49,OK,efficientnet_b4_cpu_ready,efficientnet_b4_cpu_ready.keras,CPU,Windows-10-10.0.26200-SP0,3.11.9,2.20.0,3.13.2,"<DTypePolicy ""float32"">",224,224,1,1,50,200,0,0,683.464935,681.19555,11.33894895,674.1176,769.9588,676.244155,695.06645,1.463132853,18727267,18.727267,, | |
| 8/22/2026 17:52,OK,efficientnet_b5_cpu_ready,efficientnet_b5_cpu_ready.keras,CPU,Windows-10-10.0.26200-SP0,3.11.9,2.20.0,3.13.2,"<DTypePolicy ""float32"">",224,224,1,1,50,200,0,0,844.97534,841.36905,27.77398596,816.5467,1099.8512,824.77467,855.242345,1.18346649,29698043,29.698043,, | |
| 8/22/2026 17:56,OK,efficientnet_b6_cpu_ready,efficientnet_b6_cpu_ready.keras,CPU,Windows-10-10.0.26200-SP0,3.11.9,2.20.0,3.13.2,"<DTypePolicy ""float32"">",224,224,1,1,50,200,0,0,971.321268,970.1663,8.652093824,961.5245,1069.388,964.679635,978.081,1.029525485,42275731,42.275731,, | |
| 8/22/2026 18:02,OK,efficientnet_b7_cpu_ready,efficientnet_b7_cpu_ready.keras,CPU,Windows-10-10.0.26200-SP0,3.11.9,2.20.0,3.13.2,"<DTypePolicy ""float32"">",224,224,1,1,50,200,0,0,1247.875996,1232.0482,58.29925594,1209.309,1683.9884,1213.605535,1322.09562,0.801361677,65544347,65.544347,, | |