Model save

README.md

@@ -0,0 +1,126 @@
+---
+license: apache-2.0
+base_model: google/vit-base-patch16-224-in21k
+tags:
+- generated_from_trainer
+datasets:
+- imagefolder
+metrics:
+- accuracy
+- f1
+- precision
+- recall
+model-index:
+- name: vit-base-patch16-224-in21k-FINALAsphaltLaneClassifier-detectorVIT30epochs
+  results:
+  - task:
+      name: Image Classification
+      type: image-classification
+    dataset:
+      name: imagefolder
+      type: imagefolder
+      config: default
+      split: train
+      args: default
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value:
+        accuracy: 0.9566563467492261
+    - name: F1
+      type: f1
+      value:
+        f1: 0.9461566578410928
+    - name: Precision
+      type: precision
+      value:
+        precision: 0.9423611549883112
+    - name: Recall
+      type: recall
+      value:
+        recall: 0.9539001371299508
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# vit-base-patch16-224-in21k-FINALAsphaltLaneClassifier-detectorVIT30epochs
+
+This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the imagefolder dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0975
+- Accuracy: {'accuracy': 0.9566563467492261}
+- F1: {'f1': 0.9461566578410928}
+- Precision: {'precision': 0.9423611549883112}
+- Recall: {'recall': 0.9539001371299508}
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-05
+- train_batch_size: 4
+- eval_batch_size: 4
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 16
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 30
+
+### Training results
+
+| Training Loss | Epoch   | Step | Validation Loss | Accuracy                         | F1                         | Precision                         | Recall                         |
+|:-------------:|:-------:|:----:|:---------------:|:--------------------------------:|:--------------------------:|:---------------------------------:|:------------------------------:|
+| 1.5913        | 0.9907  | 80   | 1.5129          | {'accuracy': 0.7461300309597523} | {'f1': 0.4885568839223056} | {'precision': 0.4547963454156366} | {'recall': 0.5477280156914024} |
+| 0.7749        | 1.9938  | 161  | 0.6719          | {'accuracy': 0.9009287925696594} | {'f1': 0.6806448452120003} | {'precision': 0.7905629458261038} | {'recall': 0.7018633540372671} |
+| 0.5529        | 2.9969  | 242  | 0.3765          | {'accuracy': 0.9318885448916409} | {'f1': 0.7729713140316855} | {'precision': 0.8042461260433723} | {'recall': 0.7677395068699416} |
+| 0.3601        | 4.0     | 323  | 0.3341          | {'accuracy': 0.9164086687306502} | {'f1': 0.9093567346926615} | {'precision': 0.915458654820357}  | {'recall': 0.9270074301130202} |
+| 0.3851        | 4.9907  | 403  | 0.2551          | {'accuracy': 0.934984520123839}  | {'f1': 0.926734220728561}  | {'precision': 0.9242424242424241} | {'recall': 0.9466851299149436} |
+| 0.2516        | 5.9938  | 484  | 0.1777          | {'accuracy': 0.9566563467492261} | {'f1': 0.9489876384049758} | {'precision': 0.9485110663983903} | {'recall': 0.9513860880320507} |
+| 0.3202        | 6.9969  | 565  | 0.1609          | {'accuracy': 0.9535603715170279} | {'f1': 0.9443998949860868} | {'precision': 0.940001409828996}  | {'recall': 0.9518387064970916} |
+| 0.1857        | 8.0     | 646  | 0.1253          | {'accuracy': 0.9752321981424149} | {'f1': 0.9704532058943071} | {'precision': 0.9726055258065137} | {'recall': 0.9685497387360742} |
+| 0.1644        | 8.9907  | 726  | 0.1459          | {'accuracy': 0.9628482972136223} | {'f1': 0.9542014027428277} | {'precision': 0.9523602484472049} | {'recall': 0.9575972681562742} |
+| 0.2962        | 9.9938  | 807  | 0.1678          | {'accuracy': 0.9411764705882353} | {'f1': 0.9353845975481633} | {'precision': 0.9327564716246771} | {'recall': 0.9513233488388769} |
+| 0.2872        | 10.9969 | 888  | 0.1710          | {'accuracy': 0.9318885448916409} | {'f1': 0.9062805146820121} | {'precision': 0.9236623237302658} | {'recall': 0.9092948114687246} |
+| 0.2152        | 12.0    | 969  | 0.1278          | {'accuracy': 0.9659442724458205} | {'f1': 0.9592268907563025} | {'precision': 0.9600795718006697} | {'recall': 0.9590268254864528} |
+| 0.2789        | 12.9907 | 1049 | 0.1574          | {'accuracy': 0.9473684210526315} | {'f1': 0.9401668121351615} | {'precision': 0.9386473340716037} | {'recall': 0.9479712833750101} |
+| 0.0852        | 13.9938 | 1130 | 0.1197          | {'accuracy': 0.9628482972136223} | {'f1': 0.9543105052140121} | {'precision': 0.9504212454212454} | {'recall': 0.9594794439514935} |
+| 0.1408        | 14.9969 | 1211 | 0.0921          | {'accuracy': 0.9690402476780186} | {'f1': 0.9595474426584376} | {'precision': 0.9564392324093817} | {'recall': 0.9638084482804979} |
+| 0.1505        | 16.0    | 1292 | 0.0999          | {'accuracy': 0.9566563467492261} | {'f1': 0.947061703879608}  | {'precision': 0.9442258268685393} | {'recall': 0.953062120763984}  |
+| 0.0824        | 16.9907 | 1372 | 0.1027          | {'accuracy': 0.9597523219814241} | {'f1': 0.9507999691104512} | {'precision': 0.9465755000825951} | {'recall': 0.9603936436234574} |
+| 0.1285        | 17.9938 | 1453 | 0.1084          | {'accuracy': 0.9473684210526315} | {'f1': 0.9384258178429205} | {'precision': 0.9349180559553895} | {'recall': 0.9514264203705197} |
+| 0.1324        | 18.9969 | 1534 | 0.1069          | {'accuracy': 0.9628482972136223} | {'f1': 0.9542723501653}    | {'precision': 0.9523602484472049} | {'recall': 0.9575972681562744} |
+| 0.1132        | 20.0    | 1615 | 0.0916          | {'accuracy': 0.9566563467492261} | {'f1': 0.9461584792019574} | {'precision': 0.941292743433966}  | {'recall': 0.9548412250275603} |
+| 0.1222        | 20.9907 | 1695 | 0.1144          | {'accuracy': 0.9535603715170279} | {'f1': 0.9435095063666493} | {'precision': 0.9403516555363565} | {'recall': 0.9507945470678391} |
+| 0.0937        | 21.9938 | 1776 | 0.1278          | {'accuracy': 0.9504643962848297} | {'f1': 0.9421323702425201} | {'precision': 0.9393214628508746} | {'recall': 0.9519148898030886} |
+| 0.0806        | 22.9969 | 1857 | 0.0985          | {'accuracy': 0.9597523219814241} | {'f1': 0.9496711025800274} | {'precision': 0.9460811144381124} | {'recall': 0.9561677108260959} |
+| 0.0916        | 24.0    | 1938 | 0.1051          | {'accuracy': 0.9566563467492261} | {'f1': 0.9461566578410928} | {'precision': 0.9423611549883112} | {'recall': 0.9539001371299508} |
+| 0.1396        | 24.9907 | 2018 | 0.1085          | {'accuracy': 0.9566563467492261} | {'f1': 0.9461566578410928} | {'precision': 0.9423611549883112} | {'recall': 0.9539001371299508} |
+| 0.0688        | 25.9938 | 2099 | 0.1062          | {'accuracy': 0.9566563467492261} | {'f1': 0.9461566578410928} | {'precision': 0.9423611549883112} | {'recall': 0.9539001371299508} |
+| 0.0807        | 26.9969 | 2180 | 0.1021          | {'accuracy': 0.9566563467492261} | {'f1': 0.9461566578410928} | {'precision': 0.9423611549883112} | {'recall': 0.9539001371299508} |
+| 0.1431        | 28.0    | 2261 | 0.0979          | {'accuracy': 0.9566563467492261} | {'f1': 0.9461566578410928} | {'precision': 0.9423611549883112} | {'recall': 0.9539001371299508} |
+| 0.092         | 28.9907 | 2341 | 0.0970          | {'accuracy': 0.9566563467492261} | {'f1': 0.9461566578410928} | {'precision': 0.9423611549883112} | {'recall': 0.9539001371299508} |
+| 0.0881        | 29.7214 | 2400 | 0.0975          | {'accuracy': 0.9566563467492261} | {'f1': 0.9461566578410928} | {'precision': 0.9423611549883112} | {'recall': 0.9539001371299508} |
+
+
+### Framework versions
+
+- Transformers 4.43.3
+- Pytorch 2.3.1
+- Datasets 2.20.0
+- Tokenizers 0.19.1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:00af360f82abc9b3e016ca2b4bf5244a2f02de732d33d2c123f95f96bdf988dc
+oid sha256:7c92d9338a193b788a492ee5e8769f8a7d2f2af28653a7e8b861f50c57241cfd
 size 343239356

runs/Oct01_10-46-36_CARL-Mechanical-PC/events.out.tfevents.1727750835.CARL-Mechanical-PC.3560.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e3d09d02a1763c896ece8f856105e66a7863884147822a0f017f16cf454eaff6
-size 63786
+oid sha256:5d8c5df4a1db9ccc231055004edf985a6ffe6c8728d6414405fbccb961f4e09f
+size 64411