upload

README.md

@@ -0,0 +1,85 @@
+---
+license: apache-2.0
+tags:
+- image-classification
+- vision
+- generated_from_trainer
+datasets:
+- imagefolder
+metrics:
+- accuracy
+model-index:
+- name: pedestrian_age_recognition_local
+  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: 0.8073394495412844
+---
+
+<!-- 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. -->
+
+# pedestrian_age_recognition_local
+
+This model is a fine-tuned version of [microsoft/beit-base-patch16-224-pt22k-ft22k](https://huggingface.co/microsoft/beit-base-patch16-224-pt22k-ft22k) on the imagefolder dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.5004
+- Accuracy: 0.8073
+
+## 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: 2e-05
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 1337
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 10.0
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss | Accuracy |
+|:-------------:|:-----:|:-----:|:---------------:|:--------:|
+| 0.8849        | 1.0   | 2008  | 0.7939          | 0.6807   |
+| 0.9836        | 2.0   | 4016  | 0.6694          | 0.7336   |
+| 0.8128        | 3.0   | 6024  | 0.5768          | 0.7668   |
+| 0.7611        | 4.0   | 8032  | 0.5541          | 0.7833   |
+| 0.6441        | 5.0   | 10040 | 0.5473          | 0.7773   |
+| 0.5696        | 6.0   | 12048 | 0.5187          | 0.7971   |
+| 0.6925        | 7.0   | 14056 | 0.5082          | 0.8038   |
+| 0.5711        | 8.0   | 16064 | 0.5092          | 0.8098   |
+| 0.7741        | 9.0   | 18072 | 0.5026          | 0.8020   |
+| 0.5269        | 10.0  | 20080 | 0.5004          | 0.8073   |
+
+
+### Framework versions
+
+- Transformers 4.24.0.dev0
+- Pytorch 1.12.1+cu113
+- Datasets 2.6.1
+- Tokenizers 0.13.1

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 10.0,
+    "eval_accuracy": 0.8073394495412844,
+    "eval_loss": 0.5004011988639832,
+    "eval_runtime": 12.5118,
+    "eval_samples_per_second": 226.507,
+    "eval_steps_per_second": 28.373,
+    "train_loss": 0.6558418143674197,
+    "train_runtime": 2165.352,
+    "train_samples_per_second": 74.163,
+    "train_steps_per_second": 9.273
+}

config.json

@@ -0,0 +1,63 @@
+{
+  "_name_or_path": "microsoft/beit-base-patch16-224-pt22k-ft22k",
+  "architectures": [
+    "BeitForImageClassification"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "auxiliary_channels": 256,
+  "auxiliary_concat_input": false,
+  "auxiliary_loss_weight": 0.4,
+  "auxiliary_num_convs": 1,
+  "drop_path_rate": 0.1,
+  "finetuning_task": "image-classification",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "Age16-30",
+    "1": "Age31-45",
+    "2": "Age46-60",
+    "3": "AgeAbove60",
+    "4": "AgeLess15"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "Age16-30": "0",
+    "Age31-45": "1",
+    "Age46-60": "2",
+    "AgeAbove60": "3",
+    "AgeLess15": "4"
+  },
+  "layer_norm_eps": 1e-12,
+  "layer_scale_init_value": 0.1,
+  "model_type": "beit",
+  "num_attention_heads": 12,
+  "num_channels": 3,
+  "num_hidden_layers": 12,
+  "out_indices": [
+    3,
+    5,
+    7,
+    11
+  ],
+  "patch_size": 16,
+  "pool_scales": [
+    1,
+    2,
+    3,
+    6
+  ],
+  "problem_type": "single_label_classification",
+  "semantic_loss_ignore_index": 255,
+  "torch_dtype": "float32",
+  "transformers_version": "4.24.0.dev0",
+  "use_absolute_position_embeddings": false,
+  "use_auxiliary_head": true,
+  "use_mask_token": false,
+  "use_mean_pooling": true,
+  "use_relative_position_bias": true,
+  "use_shared_relative_position_bias": false,
+  "vocab_size": 8192
+}

emissions.csv

@@ -0,0 +1,2 @@
+timestamp,experiment_id,project_name,duration,emissions,energy_consumed,country_name,country_iso_code,region,on_cloud,cloud_provider,cloud_region
+2023-01-09T04:16:19,62af6737-a71e-47e2-a59d-8f5e4546552b,codecarbon,2168.368220806122,0.15662584062475365,0.2143468409392291,Vietnam,VNM,hanoi,N,,

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 10.0,
+    "eval_accuracy": 0.8073394495412844,
+    "eval_loss": 0.5004011988639832,
+    "eval_runtime": 12.5118,
+    "eval_samples_per_second": 226.507,
+    "eval_steps_per_second": 28.373
+}

preprocessor_config.json

@@ -0,0 +1,20 @@
+{
+  "crop_size": 224,
+  "do_center_crop": false,
+  "do_normalize": true,
+  "do_resize": true,
+  "feature_extractor_type": "BeitFeatureExtractor",
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "reduce_labels": false,
+  "resample": 2,
+  "size": 224
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82e962817857e71e644953ae8a458db36db31a3d5293289b6acd5b49317524ad
+size 346867691

train_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 10.0,
+    "train_loss": 0.6558418143674197,
+    "train_runtime": 2165.352,
+    "train_samples_per_second": 74.163,
+    "train_steps_per_second": 9.273
+}