paolinox/mobilevit-FT-food101

README.md

@@ -0,0 +1,107 @@
+---
+license: other
+base_model: apple/mobilevitv2-1.0-imagenet1k-256
+tags:
+- generated_from_trainer
+datasets:
+- food101
+metrics:
+- accuracy
+model-index:
+- name: mobilevit-finetuned-food101
+  results:
+  - task:
+      name: Image Classification
+      type: image-classification
+    dataset:
+      name: food101
+      type: food101
+      config: default
+      split: train[:5000]
+      args: default
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.874
+---
+
+<!-- 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. -->
+
+# mobilevit-finetuned-food101
+
+This model is a fine-tuned version of [apple/mobilevitv2-1.0-imagenet1k-256](https://huggingface.co/apple/mobilevitv2-1.0-imagenet1k-256) on the food101 dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.4191
+- Accuracy: 0.874
+
+## 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: 32
+- eval_batch_size: 32
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 128
+- 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 |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 1.9487        | 0.98  | 23   | 1.9476          | 0.151    |
+| 1.9273        | 2.0   | 47   | 1.9070          | 0.24     |
+| 1.8561        | 2.98  | 70   | 1.8401          | 0.448    |
+| 1.7788        | 4.0   | 94   | 1.7301          | 0.612    |
+| 1.6586        | 4.98  | 117  | 1.5863          | 0.676    |
+| 1.4603        | 6.0   | 141  | 1.4199          | 0.72     |
+| 1.3027        | 6.98  | 164  | 1.2215          | 0.734    |
+| 1.1717        | 8.0   | 188  | 1.0581          | 0.759    |
+| 0.9601        | 8.98  | 211  | 0.9013          | 0.769    |
+| 0.8482        | 10.0  | 235  | 0.7866          | 0.791    |
+| 0.7276        | 10.98 | 258  | 0.7112          | 0.803    |
+| 0.6449        | 12.0  | 282  | 0.6132          | 0.835    |
+| 0.6279        | 12.98 | 305  | 0.6069          | 0.83     |
+| 0.5982        | 14.0  | 329  | 0.5637          | 0.832    |
+| 0.5766        | 14.98 | 352  | 0.5149          | 0.857    |
+| 0.5345        | 16.0  | 376  | 0.5392          | 0.837    |
+| 0.494         | 16.98 | 399  | 0.5017          | 0.848    |
+| 0.4953        | 18.0  | 423  | 0.5002          | 0.846    |
+| 0.5118        | 18.98 | 446  | 0.4782          | 0.856    |
+| 0.4708        | 20.0  | 470  | 0.4898          | 0.858    |
+| 0.4774        | 20.98 | 493  | 0.4769          | 0.851    |
+| 0.4848        | 22.0  | 517  | 0.4665          | 0.841    |
+| 0.4533        | 22.98 | 540  | 0.4890          | 0.837    |
+| 0.4449        | 24.0  | 564  | 0.4558          | 0.857    |
+| 0.4205        | 24.98 | 587  | 0.4767          | 0.857    |
+| 0.4417        | 26.0  | 611  | 0.4476          | 0.853    |
+| 0.4333        | 26.98 | 634  | 0.4853          | 0.834    |
+| 0.4545        | 28.0  | 658  | 0.4573          | 0.847    |
+| 0.4489        | 28.98 | 681  | 0.4659          | 0.845    |
+| 0.4172        | 29.36 | 690  | 0.4191          | 0.874    |
+
+
+### Framework versions
+
+- Transformers 4.35.2
+- Pytorch 2.1.0+cu118
+- Datasets 2.15.0
+- Tokenizers 0.15.0

config.json

@@ -0,0 +1,61 @@
+{
+  "_name_or_path": "apple/mobilevitv2-1.0-imagenet1k-256",
+  "architectures": [
+    "MobileViTV2ForImageClassification"
+  ],
+  "aspp_dropout_prob": 0.1,
+  "aspp_out_channels": 512,
+  "atrous_rates": [
+    6,
+    12,
+    18
+  ],
+  "attn_dropout": 0.0,
+  "base_attn_unit_dims": [
+    128,
+    192,
+    256
+  ],
+  "classifier_dropout_prob": 0.1,
+  "conv_kernel_size": 3,
+  "expand_ratio": 2.0,
+  "ffn_dropout": 0.0,
+  "ffn_multiplier": 2,
+  "hidden_act": "swish",
+  "id2label": {
+    "0": "beignets",
+    "1": "bruschetta",
+    "2": "chicken_wings",
+    "3": "hamburger",
+    "4": "pork_chop",
+    "5": "prime_rib",
+    "6": "ramen"
+  },
+  "image_size": 256,
+  "initializer_range": 0.02,
+  "label2id": {
+    "beignets": 0,
+    "bruschetta": 1,
+    "chicken_wings": 2,
+    "hamburger": 3,
+    "pork_chop": 4,
+    "prime_rib": 5,
+    "ramen": 6
+  },
+  "layer_norm_eps": 1e-05,
+  "mlp_ratio": 2.0,
+  "model_type": "mobilevitv2",
+  "n_attn_blocks": [
+    2,
+    4,
+    3
+  ],
+  "num_channels": 3,
+  "output_stride": 32,
+  "patch_size": 2,
+  "problem_type": "single_label_classification",
+  "semantic_loss_ignore_index": 255,
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.2",
+  "width_multiplier": 1.0
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:250016110cd75ef795dada56345d97dcc5bacffb2777a16883391b5647bdc64a
+size 17669344

preprocessor_config.json

@@ -0,0 +1,17 @@
+{
+  "crop_size": {
+    "height": 256,
+    "width": 256
+  },
+  "do_center_crop": true,
+  "do_flip_channel_order": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_processor_type": "MobileViTImageProcessor",
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "shortest_edge": 288
+  },
+  "use_square_size": false
+}

runs/Nov28_11-52-58_f71d5d222dbc/events.out.tfevents.1701172379.f71d5d222dbc.15295.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:046766e71836da40311411a26bee2fbabb18169dab91ed48ae53e5dc298c8a53
+size 88

runs/Nov28_11-54-32_f71d5d222dbc/events.out.tfevents.1701172483.f71d5d222dbc.16548.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:286caa6dbd5dc6d7fc331b6df8653ba9b5677adaa4c9f7731b9c4c44c73d1ab2
+size 25601

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0dc3836ce49174d52c62e09cce157e36d8ec85d6f9b9d126bd00187ed165ad09
+size 4600