DazMashaly/swin-finetuned-food101

README.md

@@ -0,0 +1,60 @@
+---
+tags:
+- image-classification
+- generated_from_trainer
+datasets:
+- image_folder
+model-index:
+- name: swin_cont
+  results: []
+---
+
+<!-- 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. -->
+
+# swin_cont
+
+This model was trained from scratch on the zindi dataset.
+It achieves the following results on the evaluation set:
+- eval_loss: 0.4766
+- eval_accuracy: 0.7545
+- eval_runtime: 236.8539
+- eval_samples_per_second: 16.352
+- eval_steps_per_second: 0.515
+- epoch: 2.0
+- step: 347
+
+## 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: 50
+
+### Framework versions
+
+- Transformers 4.36.0
+- Pytorch 2.0.0
+- Datasets 2.1.0
+- Tokenizers 0.15.0

config.json

@@ -0,0 +1,66 @@
+{
+  "_name_or_path": "/kaggle/working/bi-tempered-loss-pytorch/swin_larger/checkpoint-1041",
+  "architectures": [
+    "SwinForImageClassification"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "depths": [
+    2,
+    2,
+    18,
+    2
+  ],
+  "drop_path_rate": 0.1,
+  "embed_dim": 192,
+  "encoder_stride": 32,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 1536,
+  "id2label": {
+    "0": "DR",
+    "1": "G",
+    "2": "ND",
+    "3": "WD",
+    "4": "other"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "label2id": {
+    "DR": "0",
+    "G": "1",
+    "ND": "2",
+    "WD": "3",
+    "other": "4"
+  },
+  "layer_norm_eps": 1e-05,
+  "mlp_ratio": 4.0,
+  "model_type": "swin",
+  "num_channels": 3,
+  "num_heads": [
+    6,
+    12,
+    24,
+    48
+  ],
+  "num_layers": 4,
+  "out_features": [
+    "stage4"
+  ],
+  "out_indices": [
+    4
+  ],
+  "patch_size": 4,
+  "path_norm": true,
+  "qkv_bias": true,
+  "stage_names": [
+    "stem",
+    "stage1",
+    "stage2",
+    "stage3",
+    "stage4"
+  ],
+  "torch_dtype": "float32",
+  "transformers_version": "4.36.0",
+  "use_absolute_embeddings": false,
+  "window_size": 7
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3fe32e8263df4af16d2e8a9d77f15d0965199ea8c1327f27540b18ca67bdd05
+size 780530556

preprocessor_config.json

@@ -0,0 +1,23 @@
+{
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "feature_extractor_type": "ViTFeatureExtractor",
+  "image_mean": [
+    0.485,
+    0.456,
+    0.406
+  ],
+  "image_processor_type": "ViTFeatureExtractor",
+  "image_std": [
+    0.229,
+    0.224,
+    0.225
+  ],
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 224,
+    "width": 224
+  }
+}

runs/Jan13_14-01-18_2ba83b92b5c6/events.out.tfevents.1705154479.2ba83b92b5c6.5020.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1d87fd4749abe97ce803a11eda3a11edc0f8841403171fe2930760512b200ba
+size 10936

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:303733be6ceda5a8bc193474c4d058624b265a0020923805e515b98ec9166c8c
+size 4283