Training in progress, epoch 0

config.json

@@ -1,10 +1,18 @@
 {
-  "_name_or_path": "mansee/vit-base-patch16-224-img_orientation",
+  "_name_or_path": "mansee/swin-tiny-patch4-window7-224",
   "architectures": [
-    "ViTForImageClassification"
+    "SwinForImageClassification"
   ],
   "attention_probs_dropout_prob": 0.0,
-  "encoder_stride": 16,
+  "depths": [
+    2,
+    2,
+    6,
+    2
+  ],
+  "drop_path_rate": 0.1,
+  "embed_dim": 96,
+  "encoder_stride": 32,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.0,
   "hidden_size": 768,
@@ -16,21 +24,42 @@
   },
   "image_size": 224,
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
   "label2id": {
     "0_degree": 0,
     "180_degree": 1,
     "270_degree": 2,
     "90_degree": 3
   },
-  "layer_norm_eps": 1e-12,
-  "model_type": "vit",
-  "num_attention_heads": 12,
+  "layer_norm_eps": 1e-05,
+  "mlp_ratio": 4.0,
+  "model_type": "swin",
   "num_channels": 3,
-  "num_hidden_layers": 12,
-  "patch_size": 16,
+  "num_heads": [
+    3,
+    6,
+    12,
+    24
+  ],
+  "num_layers": 4,
+  "out_features": [
+    "stage4"
+  ],
+  "out_indices": [
+    4
+  ],
+  "patch_size": 4,
+  "path_norm": true,
   "problem_type": "single_label_classification",
   "qkv_bias": true,
+  "stage_names": [
+    "stem",
+    "stage1",
+    "stage2",
+    "stage3",
+    "stage4"
+  ],
   "torch_dtype": "float32",
-  "transformers_version": "4.33.0"
+  "transformers_version": "4.33.0",
+  "use_absolute_embeddings": false,
+  "window_size": 7
 }

preprocessor_config.json

@@ -3,17 +3,17 @@
   "do_rescale": true,
   "do_resize": true,
   "image_mean": [
-    0.5,
-    0.5,
-    0.5
+    0.485,
+    0.456,
+    0.406
   ],
   "image_processor_type": "ViTImageProcessor",
   "image_std": [
-    0.5,
-    0.5,
-    0.5
+    0.229,
+    0.224,
+    0.225
   ],
-  "resample": 2,
+  "resample": 3,
   "rescale_factor": 0.00392156862745098,
   "size": {
     "height": 224,

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c4c37922662794200c57403429baacdb39e17f069544eb1b0eb4416c85360e5a
-size 343274861
+oid sha256:29d9cb7bc776244d128cc22b651da80d239e1889da1a9bda718ee516b0273c38
+size 110401009

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c928809b4084c7862bc6a3098a8471852d09b1021b4bd122939ae88dbfa6ca05
+oid sha256:680b0ee6186f0015a5e2e485f8efc926834139a682b77ed22cabbe20d2f636d3
 size 4091