facial-expression-recognition-mmi

README.md

@@ -3,11 +3,26 @@ library_name: transformers
 base_model: carlosleao/vit-Facial-Expression-Recognition
 tags:
 - generated_from_trainer
+datasets:
+- imagefolder
 metrics:
 - accuracy
 model-index:
 - name: vit-Facial-Expression-Recognition
-  results: []
+  results:
+  - task:
+      name: Image Classification
+      type: image-classification
+    dataset:
+      name: imagefolder
+      type: imagefolder
+      config: default
+      split: test
+      args: default
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.789064300530076
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -15,10 +30,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # vit-Facial-Expression-Recognition
 
-This model is a fine-tuned version of [carlosleao/vit-Facial-Expression-Recognition](https://huggingface.co/carlosleao/vit-Facial-Expression-Recognition) on the None dataset.
+This model is a fine-tuned version of [carlosleao/vit-Facial-Expression-Recognition](https://huggingface.co/carlosleao/vit-Facial-Expression-Recognition) on the imagefolder dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.4829
-- Accuracy: 0.8460
+- Loss: 0.6250
+- Accuracy: 0.7891
 
 ## Model description
 
@@ -52,22 +67,47 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss | Accuracy |
 |:-------------:|:------:|:----:|:---------------:|:--------:|
-| 1.2921        | 0.8959 | 100  | 1.3420          | 0.7130   |
-| 0.9341        | 1.7917 | 200  | 1.0525          | 0.7997   |
-| 0.7037        | 2.6876 | 300  | 0.8848          | 0.7994   |
-| 0.6143        | 3.5834 | 400  | 0.7646          | 0.8108   |
-| 0.5353        | 4.4793 | 500  | 0.6962          | 0.8100   |
-| 0.5025        | 5.3751 | 600  | 0.6030          | 0.8368   |
-| 0.4648        | 6.2710 | 700  | 0.5725          | 0.8351   |
-| 0.4365        | 7.1669 | 800  | 0.5417          | 0.8321   |
-| 0.4213        | 8.0627 | 900  | 0.5227          | 0.8293   |
-| 0.3939        | 8.9586 | 1000 | 0.4829          | 0.8460   |
-| 0.3496        | 9.8544 | 1100 | 0.4615          | 0.8539   |
+| 1.6718        | 0.2753 | 100  | 1.5767          | 0.5306   |
+| 1.1709        | 0.5506 | 200  | 1.2371          | 0.6482   |
+| 0.9479        | 0.8259 | 300  | 1.1168          | 0.6897   |
+| 0.8293        | 1.1012 | 400  | 1.0489          | 0.6954   |
+| 0.7735        | 1.3765 | 500  | 0.9967          | 0.7021   |
+| 0.7132        | 1.6518 | 600  | 0.9411          | 0.7188   |
+| 0.6777        | 1.9270 | 700  | 0.9154          | 0.7236   |
+| 0.6216        | 2.2023 | 800  | 0.8650          | 0.7359   |
+| 0.5866        | 2.4776 | 900  | 0.8482          | 0.7344   |
+| 0.5725        | 2.7529 | 1000 | 0.7778          | 0.7487   |
+| 0.5442        | 3.0282 | 1100 | 0.8053          | 0.7383   |
+| 0.4893        | 3.3035 | 1200 | 0.7572          | 0.7531   |
+| 0.4852        | 3.5788 | 1300 | 0.7322          | 0.7588   |
+| 0.4862        | 3.8541 | 1400 | 0.6850          | 0.7734   |
+| 0.4203        | 4.1294 | 1500 | 0.7032          | 0.7612   |
+| 0.4037        | 4.4047 | 1600 | 0.6758          | 0.7670   |
+| 0.4214        | 4.6800 | 1700 | 0.6657          | 0.7732   |
+| 0.4166        | 4.9553 | 1800 | 0.6488          | 0.7788   |
+| 0.3437        | 5.2306 | 1900 | 0.6573          | 0.7754   |
+| 0.3488        | 5.5058 | 2000 | 0.6713          | 0.7695   |
+| 0.3355        | 5.7811 | 2100 | 0.6249          | 0.7853   |
+| 0.3187        | 6.0564 | 2200 | 0.6679          | 0.7715   |
+| 0.2765        | 6.3317 | 2300 | 0.6246          | 0.7872   |
+| 0.2853        | 6.6070 | 2400 | 0.6376          | 0.7830   |
+| 0.2755        | 6.8823 | 2500 | 0.6349          | 0.7813   |
+| 0.2428        | 7.1576 | 2600 | 0.6273          | 0.7860   |
+| 0.2351        | 7.4329 | 2700 | 0.6427          | 0.7804   |
+| 0.2391        | 7.7082 | 2800 | 0.6380          | 0.7827   |
+| 0.2421        | 7.9835 | 2900 | 0.6283          | 0.7868   |
+| 0.2097        | 8.2588 | 3000 | 0.6250          | 0.7891   |
+| 0.2179        | 8.5341 | 3100 | 0.6386          | 0.7863   |
+| 0.214         | 8.8094 | 3200 | 0.6360          | 0.7854   |
+| 0.205         | 9.0847 | 3300 | 0.6244          | 0.7918   |
+| 0.2029        | 9.3599 | 3400 | 0.6333          | 0.7875   |
+| 0.1995        | 9.6352 | 3500 | 0.6340          | 0.7872   |
+| 0.1999        | 9.9105 | 3600 | 0.6332          | 0.7877   |
 
 
 ### Framework versions
 
-- Transformers 4.45.1
-- Pytorch 2.4.1+cu121
+- Transformers 4.45.2
+- Pytorch 2.5.0+cu124
 - Datasets 3.0.1
-- Tokenizers 0.20.0
+- Tokenizers 0.20.1

all_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 9.944008958566629,
-    "eval_accuracy": 0.8460463816708578,
-    "eval_loss": 0.4829452931880951,
-    "eval_runtime": 6.2929,
-    "eval_samples_per_second": 568.737,
-    "eval_steps_per_second": 17.798
+    "epoch": 9.993117687543014,
+    "eval_accuracy": 0.789064300530076,
+    "eval_loss": 0.6250218152999878,
+    "eval_runtime": 811.3981,
+    "eval_samples_per_second": 21.39,
+    "eval_steps_per_second": 0.669
 }

eval_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 9.944008958566629,
-    "eval_accuracy": 0.8460463816708578,
-    "eval_loss": 0.4829452931880951,
-    "eval_runtime": 6.2929,
-    "eval_samples_per_second": 568.737,
-    "eval_steps_per_second": 17.798
+    "epoch": 9.993117687543014,
+    "eval_accuracy": 0.789064300530076,
+    "eval_loss": 0.6250218152999878,
+    "eval_runtime": 811.3981,
+    "eval_samples_per_second": 21.39,
+    "eval_steps_per_second": 0.669
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b5693db22bcb50b9eb315f167352e32bae1f46fe65e579dc783ab3345f9c3ee
+oid sha256:ffa9be9f9d91b4004635c2003dd0403fdbd8c6008eabf035444c5c34daf4973f
 size 343239356