paolinox/segformer-FT-food101

README.md

@@ -0,0 +1,107 @@
+---
+license: other
+base_model: nvidia/mit-b0
+tags:
+- generated_from_trainer
+datasets:
+- food101
+metrics:
+- accuracy
+model-index:
+- name: segformer-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: 0.888
+---
+
+<!-- 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. -->
+
+# segformer-finetuned-food101
+
+This model is a fine-tuned version of [nvidia/mit-b0](https://huggingface.co/nvidia/mit-b0) on the food101 dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.3478
+- Accuracy: 0.888
+
+## 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 |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 2.0272        | 0.98  | 23   | 1.8039          | 0.329    |
+| 1.5806        | 2.0   | 47   | 1.2465          | 0.608    |
+| 1.0564        | 2.98  | 70   | 0.7507          | 0.756    |
+| 0.7358        | 4.0   | 94   | 0.6263          | 0.784    |
+| 0.6482        | 4.98  | 117  | 0.5551          | 0.795    |
+| 0.5692        | 6.0   | 141  | 0.5849          | 0.794    |
+| 0.5552        | 6.98  | 164  | 0.4931          | 0.831    |
+| 0.4956        | 8.0   | 188  | 0.5166          | 0.83     |
+| 0.4748        | 8.98  | 211  | 0.4808          | 0.834    |
+| 0.424         | 10.0  | 235  | 0.4238          | 0.852    |
+| 0.4314        | 10.98 | 258  | 0.4858          | 0.838    |
+| 0.4071        | 12.0  | 282  | 0.4304          | 0.858    |
+| 0.3928        | 12.98 | 305  | 0.4621          | 0.851    |
+| 0.3695        | 14.0  | 329  | 0.4398          | 0.859    |
+| 0.3704        | 14.98 | 352  | 0.4172          | 0.855    |
+| 0.3299        | 16.0  | 376  | 0.4225          | 0.856    |
+| 0.3391        | 16.98 | 399  | 0.4165          | 0.855    |
+| 0.3023        | 18.0  | 423  | 0.3828          | 0.869    |
+| 0.3318        | 18.98 | 446  | 0.4190          | 0.861    |
+| 0.2994        | 20.0  | 470  | 0.4190          | 0.861    |
+| 0.323         | 20.98 | 493  | 0.4034          | 0.866    |
+| 0.2883        | 22.0  | 517  | 0.4083          | 0.874    |
+| 0.2959        | 22.98 | 540  | 0.4202          | 0.862    |
+| 0.2665        | 24.0  | 564  | 0.3740          | 0.881    |
+| 0.2765        | 24.98 | 587  | 0.4123          | 0.866    |
+| 0.2728        | 26.0  | 611  | 0.3763          | 0.868    |
+| 0.2817        | 26.98 | 634  | 0.3939          | 0.864    |
+| 0.2467        | 28.0  | 658  | 0.3938          | 0.87     |
+| 0.2772        | 28.98 | 681  | 0.4013          | 0.866    |
+| 0.2243        | 29.36 | 690  | 0.3478          | 0.888    |
+
+
+### Framework versions
+
+- Transformers 4.35.2
+- Pytorch 2.1.0+cu118
+- Datasets 2.15.0
+- Tokenizers 0.15.0

config.json

@@ -0,0 +1,89 @@
+{
+  "_name_or_path": "nvidia/mit-b0",
+  "architectures": [
+    "SegformerForImageClassification"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "classifier_dropout_prob": 0.1,
+  "decoder_hidden_size": 256,
+  "depths": [
+    2,
+    2,
+    2,
+    2
+  ],
+  "downsampling_rates": [
+    1,
+    4,
+    8,
+    16
+  ],
+  "drop_path_rate": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_sizes": [
+    32,
+    64,
+    160,
+    256
+  ],
+  "id2label": {
+    "0": "beignets",
+    "1": "bruschetta",
+    "2": "chicken_wings",
+    "3": "hamburger",
+    "4": "pork_chop",
+    "5": "prime_rib",
+    "6": "ramen"
+  },
+  "image_size": 224,
+  "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-06,
+  "mlp_ratios": [
+    4,
+    4,
+    4,
+    4
+  ],
+  "model_type": "segformer",
+  "num_attention_heads": [
+    1,
+    2,
+    5,
+    8
+  ],
+  "num_channels": 3,
+  "num_encoder_blocks": 4,
+  "patch_sizes": [
+    7,
+    3,
+    3,
+    3
+  ],
+  "problem_type": "single_label_classification",
+  "reshape_last_stage": true,
+  "semantic_loss_ignore_index": 255,
+  "sr_ratios": [
+    8,
+    4,
+    2,
+    1
+  ],
+  "strides": [
+    4,
+    2,
+    2,
+    2
+  ],
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c49bca9090160b8a429d9ba062c0dab48d0bf2d64095bcf85c9429e5a17d39a0
+size 13307316

preprocessor_config.json

@@ -0,0 +1,23 @@
+{
+  "do_normalize": true,
+  "do_reduce_labels": false,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.485,
+    0.456,
+    0.406
+  ],
+  "image_processor_type": "SegformerImageProcessor",
+  "image_std": [
+    0.229,
+    0.224,
+    0.225
+  ],
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 512,
+    "width": 512
+  }
+}

runs/Nov28_16-45-08_9cef718bb6ef/events.out.tfevents.1701189918.9cef718bb6ef.1194.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0095d78931a52ed4be3bdb583644b33cf99adca2a626f9b1cfdcb6ab78bd304
+size 19660

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72c7c78b3b384ffc169efa2416b2824d90f6864cc2e712fcbec5385bd4a301ae
+size 4600