DazMashaly/swinv2

README.md

@@ -0,0 +1,62 @@
+---
+license: apache-2.0
+base_model: microsoft/swinv2-large-patch4-window12-192-22k
+tags:
+- image-classification
+- generated_from_trainer
+datasets:
+- imagefolder
+model-index:
+- name: swinv2_zindi
+  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. -->
+
+# swinv2_zindi
+
+This model is a fine-tuned version of [microsoft/swinv2-large-patch4-window12-192-22k](https://huggingface.co/microsoft/swinv2-large-patch4-window12-192-22k) on the zindi dataset.
+It achieves the following results on the evaluation set:
+- eval_loss: 0.6328
+- eval_accuracy: 0.7434
+- eval_runtime: 234.8425
+- eval_samples_per_second: 16.492
+- eval_steps_per_second: 0.519
+- epoch: 3.0
+- step: 520
+
+## 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: 5
+
+### Framework versions
+
+- Transformers 4.35.2
+- Pytorch 2.1.0+cu121
+- Datasets 2.16.0
+- Tokenizers 0.15.0

config.json

@@ -0,0 +1,60 @@
+{
+  "_name_or_path": "microsoft/swinv2-large-patch4-window12-192-22k",
+  "architectures": [
+    "Swinv2ForImageClassification"
+  ],
+  "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": 192,
+  "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": "swinv2",
+  "num_channels": 3,
+  "num_heads": [
+    6,
+    12,
+    24,
+    48
+  ],
+  "num_layers": 4,
+  "patch_size": 4,
+  "path_norm": true,
+  "pretrained_window_sizes": [
+    0,
+    0,
+    0,
+    0
+  ],
+  "problem_type": "single_label_classification",
+  "qkv_bias": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.2",
+  "use_absolute_embeddings": false,
+  "window_size": 12
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:380c59b40b677549a32e38a93a3973a41b5a694555d9bd6eb27b9ed3bd7d4ede
+size 780904732

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": 192,
+    "width": 192
+  }
+}

runs/Dec24_14-50-34_32f206771588/events.out.tfevents.1703429435.32f206771588.2559.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f03f34e6ae374d45be911c7cb072b9c684613001dd32aa2fcf8b9ca07eff69ab
+size 4886

runs/Dec24_14-53-52_32f206771588/events.out.tfevents.1703429632.32f206771588.6192.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f70e28e467f8175d56ae4d10e3ca28e81f068b268a75b5e9c4e51c9434881347
+size 4184

runs/Dec24_14-56-26_32f206771588/events.out.tfevents.1703429787.32f206771588.7069.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ff5ea2112e88916ec50926f6c81b54bbcf122b3af26d7108fd089c81dea58c1
+size 13675

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29369c0a1a72ef678203b1023ae59e0b19043bfce8dd4a3f0d610f6976d7ba49
+size 4600