End of training

README.md

@@ -1,7 +1,7 @@
 ---
 library_name: transformers
-license: apache-2.0
-base_model: google/vit-large-patch16-224
+license: other
+base_model: google/mobilenet_v2_1.4_224
 tags:
 - generated_from_trainer
 metrics:
@@ -19,17 +19,17 @@ should probably proofread and complete it, then remove this comment. -->
 
 # ViT_L16
 
-This model is a fine-tuned version of [google/vit-large-patch16-224](https://huggingface.co/google/vit-large-patch16-224) on an unknown dataset.
+This model is a fine-tuned version of [google/mobilenet_v2_1.4_224](https://huggingface.co/google/mobilenet_v2_1.4_224) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0933
-- Accuracy: 0.9746
-- Precision: 0.9844
-- Recall: 0.9603
-- F1: 0.9722
-- Tp: 1573
-- Tn: 1885
-- Fp: 25
-- Fn: 65
+- Loss: 0.1493
+- Accuracy: 0.9586
+- Precision: 0.9825
+- Recall: 0.9267
+- F1: 0.9538
+- Tp: 1518
+- Tn: 1883
+- Fp: 27
+- Fn: 120
 
 ## Model description
 
@@ -49,26 +49,58 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 5e-06
-- train_batch_size: 32
-- eval_batch_size: 32
+- train_batch_size: 64
+- eval_batch_size: 64
 - seed: 42
 - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
-- lr_scheduler_warmup_steps: 221
-- num_epochs: 2
+- lr_scheduler_warmup_steps: 552
+- num_epochs: 10
 
 ### Training results
 
-| Training Loss | Epoch  | Step | Validation Loss | Accuracy | Precision | Recall | F1     | Tp   | Tn   | Fp | Fn  |
-|:-------------:|:------:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|:----:|:----:|:--:|:---:|
-| 0.4292        | 0.2477 | 110  | 0.1793          | 0.9464   | 0.9925    | 0.8907 | 0.9389 | 1459 | 1899 | 11 | 179 |
-| 0.2230        | 0.4955 | 220  | 0.1211          | 0.9651   | 0.9980    | 0.9261 | 0.9607 | 1517 | 1907 | 3  | 121 |
-| 0.1974        | 0.7432 | 330  | 0.1342          | 0.9690   | 0.9811    | 0.9512 | 0.9659 | 1558 | 1880 | 30 | 80  |
-| 0.1879        | 0.9910 | 440  | 0.1397          | 0.9628   | 0.9591    | 0.9603 | 0.9597 | 1573 | 1843 | 67 | 65  |
-| 0.1643        | 1.2387 | 550  | 0.1083          | 0.9741   | 0.9856    | 0.9579 | 0.9715 | 1569 | 1887 | 23 | 69  |
-| 0.1654        | 1.4865 | 660  | 0.0963          | 0.9715   | 0.9936    | 0.9444 | 0.9684 | 1547 | 1900 | 10 | 91  |
-| 0.1664        | 1.7342 | 770  | 0.1130          | 0.9693   | 0.9693    | 0.9640 | 0.9666 | 1579 | 1860 | 50 | 59  |
-| 0.1637        | 1.9820 | 880  | 0.0933          | 0.9746   | 0.9844    | 0.9603 | 0.9722 | 1573 | 1885 | 25 | 65  |
+| Training Loss | Epoch  | Step | Validation Loss | Accuracy | Precision | Recall | F1     | Tp   | Tn   | Fp  | Fn   |
+|:-------------:|:------:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|:----:|:----:|:---:|:----:|
+| 0.6498        | 0.2477 | 55   | 0.6233          | 0.5950   | 0.7445    | 0.1868 | 0.2987 | 306  | 1805 | 105 | 1332 |
+| 0.6063        | 0.4955 | 110  | 0.6222          | 0.6206   | 0.7160    | 0.2955 | 0.4183 | 484  | 1718 | 192 | 1154 |
+| 0.5307        | 0.7432 | 165  | 0.4872          | 0.8120   | 0.9036    | 0.6636 | 0.7652 | 1087 | 1794 | 116 | 551  |
+| 0.4383        | 0.9910 | 220  | 0.4204          | 0.8695   | 0.8808    | 0.8297 | 0.8544 | 1359 | 1726 | 184 | 279  |
+| 0.3821        | 1.2387 | 275  | 0.4293          | 0.8171   | 0.7416    | 0.9267 | 0.8239 | 1518 | 1381 | 529 | 120  |
+| 0.3412        | 1.4865 | 330  | 0.3600          | 0.8763   | 0.8601    | 0.8742 | 0.8671 | 1432 | 1677 | 233 | 206  |
+| 0.3323        | 1.7342 | 385  | 0.5002          | 0.7562   | 0.7125    | 0.7912 | 0.7498 | 1296 | 1387 | 523 | 342  |
+| 0.3128        | 1.9820 | 440  | 0.3087          | 0.9073   | 0.9078    | 0.8895 | 0.8986 | 1457 | 1762 | 148 | 181  |
+| 0.2916        | 2.2297 | 495  | 0.3092          | 0.9005   | 0.8640    | 0.9310 | 0.8963 | 1525 | 1670 | 240 | 113  |
+| 0.2882        | 2.4775 | 550  | 0.4698          | 0.7802   | 0.6864    | 0.9646 | 0.8020 | 1580 | 1188 | 722 | 58   |
+| 0.2775        | 2.7252 | 605  | 0.2448          | 0.9332   | 0.9420    | 0.9115 | 0.9265 | 1493 | 1818 | 92  | 145  |
+| 0.2577        | 2.9730 | 660  | 0.2544          | 0.9239   | 0.9264    | 0.9072 | 0.9167 | 1486 | 1792 | 118 | 152  |
+| 0.2541        | 3.2207 | 715  | 0.2914          | 0.9028   | 0.8542    | 0.9518 | 0.9004 | 1559 | 1644 | 266 | 79   |
+| 0.2499        | 3.4685 | 770  | 0.2302          | 0.9281   | 0.9314    | 0.9115 | 0.9213 | 1493 | 1800 | 110 | 145  |
+| 0.2356        | 3.7162 | 825  | 0.2430          | 0.9284   | 0.9109    | 0.9365 | 0.9235 | 1534 | 1760 | 150 | 104  |
+| 0.2403        | 3.9640 | 880  | 0.2341          | 0.9169   | 0.8929    | 0.9316 | 0.9119 | 1526 | 1727 | 183 | 112  |
+| 0.2454        | 4.2117 | 935  | 0.3786          | 0.8396   | 0.7642    | 0.9438 | 0.8446 | 1546 | 1433 | 477 | 92   |
+| 0.2296        | 4.4595 | 990  | 0.3143          | 0.8591   | 0.8014    | 0.9237 | 0.8582 | 1513 | 1535 | 375 | 125  |
+| 0.2311        | 4.7072 | 1045 | 0.3683          | 0.8238   | 0.7346    | 0.9683 | 0.8354 | 1586 | 1337 | 573 | 52   |
+| 0.2181        | 4.9550 | 1100 | 0.1968          | 0.9380   | 0.9350    | 0.9304 | 0.9327 | 1524 | 1804 | 106 | 114  |
+| 0.2119        | 5.2027 | 1155 | 0.3088          | 0.8661   | 0.7987    | 0.9493 | 0.8675 | 1555 | 1518 | 392 | 83   |
+| 0.2222        | 5.4505 | 1210 | 0.3543          | 0.8503   | 0.7780    | 0.9457 | 0.8537 | 1549 | 1468 | 442 | 89   |
+| 0.2047        | 5.6982 | 1265 | 0.1789          | 0.9462   | 0.9485    | 0.9341 | 0.9412 | 1530 | 1827 | 83  | 108  |
+| 0.2169        | 5.9459 | 1320 | 0.1936          | 0.9414   | 0.9503    | 0.9212 | 0.9355 | 1509 | 1831 | 79  | 129  |
+| 0.2233        | 6.1937 | 1375 | 0.2493          | 0.8949   | 0.8388    | 0.9560 | 0.8936 | 1566 | 1609 | 301 | 72   |
+| 0.2245        | 6.4414 | 1430 | 0.2624          | 0.8797   | 0.8172    | 0.9524 | 0.8796 | 1560 | 1561 | 349 | 78   |
+| 0.2220        | 6.6892 | 1485 | 0.2528          | 0.9101   | 0.8586    | 0.9640 | 0.9083 | 1579 | 1650 | 260 | 59   |
+| 0.2158        | 6.9369 | 1540 | 0.2083          | 0.9290   | 0.9130    | 0.9353 | 0.9240 | 1532 | 1764 | 146 | 106  |
+| 0.2151        | 7.1847 | 1595 | 0.1952          | 0.9394   | 0.9273    | 0.9426 | 0.9349 | 1544 | 1789 | 121 | 94   |
+| 0.2192        | 7.4324 | 1650 | 0.2952          | 0.8670   | 0.7941    | 0.9609 | 0.8696 | 1574 | 1502 | 408 | 64   |
+| 0.2162        | 7.6802 | 1705 | 0.2100          | 0.9247   | 0.9025    | 0.9383 | 0.9201 | 1537 | 1744 | 166 | 101  |
+| 0.1981        | 7.9279 | 1760 | 0.1673          | 0.9487   | 0.9522    | 0.9359 | 0.9440 | 1533 | 1833 | 77  | 105  |
+| 0.2019        | 8.1757 | 1815 | 0.2276          | 0.9146   | 0.8739    | 0.9524 | 0.9115 | 1560 | 1685 | 225 | 78   |
+| 0.2292        | 8.4234 | 1870 | 0.1978          | 0.9377   | 0.9170    | 0.9512 | 0.9338 | 1558 | 1769 | 141 | 80   |
+| 0.2045        | 8.6712 | 1925 | 0.1614          | 0.9546   | 0.9953    | 0.9060 | 0.9485 | 1484 | 1903 | 7   | 154  |
+| 0.2145        | 8.9189 | 1980 | 0.1544          | 0.9580   | 0.9794    | 0.9286 | 0.9533 | 1521 | 1878 | 32  | 117  |
+| 0.1937        | 9.1667 | 2035 | 0.1571          | 0.9515   | 0.9747    | 0.9188 | 0.9459 | 1505 | 1871 | 39  | 133  |
+| 0.2071        | 9.4144 | 2090 | 0.1948          | 0.9374   | 0.9194    | 0.9475 | 0.9333 | 1552 | 1774 | 136 | 86   |
+| 0.2136        | 9.6622 | 2145 | 0.2500          | 0.8861   | 0.8324    | 0.9432 | 0.8844 | 1545 | 1599 | 311 | 93   |
+| 0.1980        | 9.9099 | 2200 | 0.1493          | 0.9586   | 0.9825    | 0.9267 | 0.9538 | 1518 | 1883 | 27  | 120  |
 
 
 ### Framework versions

config.json

@@ -1,34 +1,33 @@
 {
   "architectures": [
-    "ViTForImageClassification"
+    "MobileNetV2ForImageClassification"
   ],
-  "attention_probs_dropout_prob": 0.0,
+  "classifier_dropout_prob": 0.2,
+  "depth_divisible_by": 8,
+  "depth_multiplier": 1.4,
   "dtype": "float32",
-  "encoder_stride": 16,
-  "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.0,
-  "hidden_size": 1024,
+  "expand_ratio": 6,
+  "finegrained_output": true,
+  "first_layer_is_expansion": true,
+  "hidden_act": "relu6",
   "id2label": {
     "0": "0",
     "1": "1"
   },
   "image_size": 224,
   "initializer_range": 0.02,
-  "intermediate_size": 4096,
   "label2id": {
     "0": 0,
     "1": 1
   },
-  "layer_norm_eps": 1e-12,
-  "model_type": "vit",
-  "num_attention_heads": 16,
+  "layer_norm_eps": 0.001,
+  "min_depth": 8,
+  "model_type": "mobilenet_v2",
   "num_channels": 3,
-  "num_hidden_layers": 24,
-  "patch_size": 16,
-  "pooler_act": "tanh",
-  "pooler_output_size": 1024,
+  "output_stride": 32,
   "problem_type": "single_label_classification",
-  "qkv_bias": true,
+  "semantic_loss_ignore_index": 255,
+  "tf_padding": true,
   "transformers_version": "5.0.0",
   "use_cache": false
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:779aeafe9a53b2a1b8a4b18e8a6a8bf637f7940dbd277f1883680150cb5fee1e
-size 1213261264
+oid sha256:8c1aac8021df27502e0f28aa91f5fbcb50fcb46ed9637cd52b4ee3c38854b0a9
+size 17507576

preprocessor_config.json

@@ -1,6 +1,12 @@
 {
-  "do_convert_rgb": null,
+  "crop_size": {
+    "height": 224,
+    "width": 224
+  },
+  "data_format": "channels_first",
+  "do_center_crop": true,
   "do_normalize": true,
+  "do_reduce_labels": false,
   "do_rescale": true,
   "do_resize": true,
   "image_mean": [
@@ -8,7 +14,7 @@
     0.5,
     0.5
   ],
-  "image_processor_type": "ViTImageProcessor",
+  "image_processor_type": "MobileNetV2ImageProcessorFast",
   "image_std": [
     0.5,
     0.5,
@@ -17,7 +23,6 @@
   "resample": 2,
   "rescale_factor": 0.00392156862745098,
   "size": {
-    "height": 224,
-    "width": 224
+    "shortest_edge": 256
   }
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a20650d184cd21a5ecf7b63db317856b5992087aa5fe9cbe6ebb9da5ccee247d
+oid sha256:459ae50093485df6de25fbad1d63b321bd8f6f371a46c2f38fdb6d2d902d243a
 size 5137