Training in progress, epoch 0

config.json

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

preprocessor_config.json

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

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:71675667fdd760caf18a957b1871af51577947a93a0f52aafd02f0e8dd7a59eb
-size 110401009
+oid sha256:6ccae1a0ed0d435860c3574be677905136d84bfb486eb182b6fc5a37a6db5c27
+size 343274861

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e61dcb445d6bce9e66f7df662f16d2f6466b183978c3f3bad51cf69d199bd47e
+oid sha256:c928809b4084c7862bc6a3098a8471852d09b1021b4bd122939ae88dbfa6ca05
 size 4091