Training in progress, epoch 0

config.json

@@ -1,10 +1,18 @@
 {
-  "_name_or_path": "google/vit-base-patch16-224-in21k",
+  "_name_or_path": "microsoft/swinv2-tiny-patch4-window8-256",
   "architectures": [
-    "ViTForImageClassification"
+    "Swinv2ForImageClassification"
   ],
   "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,
@@ -28,9 +36,8 @@
     "8": "\u6708\u4eae",
     "9": "\u72d7"
   },
-  "image_size": 224,
+  "image_size": 256,
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
   "label2id": {
     "\u54ed": "0",
     "\u5750": "1",
@@ -51,14 +58,29 @@
     "\u81ea\u884c\u8f66": "16",
     "\u829d\u9ebb": "17"
   },
-  "layer_norm_eps": 1e-12,
-  "model_type": "vit",
-  "num_attention_heads": 12,
+  "layer_norm_eps": 1e-05,
+  "mlp_ratio": 4.0,
+  "model_type": "swinv2",
   "num_channels": 3,
-  "num_hidden_layers": 12,
-  "patch_size": 16,
+  "num_heads": [
+    3,
+    6,
+    12,
+    24
+  ],
+  "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": "4.28.1"
+  "transformers_version": "4.28.1",
+  "use_absolute_embeddings": false,
+  "window_size": 8
 }

preprocessor_config.json

@@ -3,20 +3,20 @@
   "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,
-    "width": 224
+    "height": 256,
+    "width": 256
   }
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f0d8bc144fc95187b59b7d31852469f4a793533b85e829284957bace40863d11
-size 343317933
+oid sha256:910535e82e2466731b4881cb923824ff7e71dd1864fcfb6be7205a6303573e5d
+size 110454369

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:08818a71e86674b571cc4e6edfa120472f9470579211e6659dc9ebe613c5f5d7
+oid sha256:a66eefcbd71bec5aec9d17e31e6da58c63b88728cf97b70418760c53fcae3e00
 size 3579