Instructions to use basant18/Smoking-detection-MobileNet with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Keras
How to use basant18/Smoking-detection-MobileNet 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://basant18/Smoking-detection-MobileNet") - Notebooks
- Google Colab
- Kaggle
Upload training_stats.json with huggingface_hub
Browse files- training_stats.json +7 -3
training_stats.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
| 1 |
{
|
| 2 |
"phase": 2,
|
| 3 |
-
"epoch_global":
|
| 4 |
"best_val_acc": 0.9777777791023254,
|
| 5 |
"best_val_loss": 0.11201294511556625,
|
| 6 |
"history": {
|
|
@@ -31,7 +31,8 @@
|
|
| 31 |
0.22409576177597046,
|
| 32 |
0.22456999123096466,
|
| 33 |
0.22122134268283844,
|
| 34 |
-
0.2199689745903015
|
|
|
|
| 35 |
],
|
| 36 |
"accuracy": [
|
| 37 |
0.7721806168556213,
|
|
@@ -60,6 +61,7 @@
|
|
| 60 |
0.9084032773971558,
|
| 61 |
0.907344400882721,
|
| 62 |
0.9115800857543945,
|
|
|
|
| 63 |
0.9094622135162354
|
| 64 |
],
|
| 65 |
"val_loss": [
|
|
@@ -89,7 +91,8 @@
|
|
| 89 |
0.1027996689081192,
|
| 90 |
0.10608465224504471,
|
| 91 |
0.10064270347356796,
|
| 92 |
-
0.08973866701126099
|
|
|
|
| 93 |
],
|
| 94 |
"val_accuracy": [
|
| 95 |
0.9222221970558167,
|
|
@@ -118,6 +121,7 @@
|
|
| 118 |
0.9722222089767456,
|
| 119 |
0.9722222089767456,
|
| 120 |
0.9722222089767456,
|
|
|
|
| 121 |
0.9722222089767456
|
| 122 |
]
|
| 123 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"phase": 2,
|
| 3 |
+
"epoch_global": 28,
|
| 4 |
"best_val_acc": 0.9777777791023254,
|
| 5 |
"best_val_loss": 0.11201294511556625,
|
| 6 |
"history": {
|
|
|
|
| 31 |
0.22409576177597046,
|
| 32 |
0.22456999123096466,
|
| 33 |
0.22122134268283844,
|
| 34 |
+
0.2199689745903015,
|
| 35 |
+
0.2189551740884781
|
| 36 |
],
|
| 37 |
"accuracy": [
|
| 38 |
0.7721806168556213,
|
|
|
|
| 61 |
0.9084032773971558,
|
| 62 |
0.907344400882721,
|
| 63 |
0.9115800857543945,
|
| 64 |
+
0.9094622135162354,
|
| 65 |
0.9094622135162354
|
| 66 |
],
|
| 67 |
"val_loss": [
|
|
|
|
| 91 |
0.1027996689081192,
|
| 92 |
0.10608465224504471,
|
| 93 |
0.10064270347356796,
|
| 94 |
+
0.08973866701126099,
|
| 95 |
+
0.09406672418117523
|
| 96 |
],
|
| 97 |
"val_accuracy": [
|
| 98 |
0.9222221970558167,
|
|
|
|
| 121 |
0.9722222089767456,
|
| 122 |
0.9722222089767456,
|
| 123 |
0.9722222089767456,
|
| 124 |
+
0.9722222089767456,
|
| 125 |
0.9722222089767456
|
| 126 |
]
|
| 127 |
}
|