Training in progress, step 200

config.json

@@ -1,24 +1,53 @@
 {
-  "_name_or_path": "google/vit-large-patch16-224",
+  "_name_or_path": "microsoft/swin-base-patch4-window7-224",
   "architectures": [
-    "ViTForImageClassification"
+    "SwinForImageClassification"
   ],
   "attention_probs_dropout_prob": 0.0,
-  "encoder_stride": 16,
+  "depths": [
+    2,
+    2,
+    18,
+    2
+  ],
+  "drop_path_rate": 0.1,
+  "embed_dim": 128,
+  "encoder_stride": 32,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.0,
   "hidden_size": 1024,
   "image_size": 224,
   "initializer_range": 0.02,
-  "intermediate_size": 4096,
-  "layer_norm_eps": 1e-12,
-  "model_type": "vit",
-  "num_attention_heads": 16,
+  "layer_norm_eps": 1e-05,
+  "mlp_ratio": 4.0,
+  "model_type": "swin",
   "num_channels": 3,
-  "num_hidden_layers": 24,
-  "patch_size": 16,
+  "num_heads": [
+    4,
+    8,
+    16,
+    32
+  ],
+  "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": "4.44.2"
+  "transformers_version": "4.44.2",
+  "use_absolute_embeddings": false,
+  "window_size": 7
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65d5f00091ac9e9097a5efd3d06e4038f1a38dc46d3e4062d7cd323097f1246b
-size 1213261264
+oid sha256:7e1143d8867d85622bf7f19f345576c14ba0590b7038ac820a042dc45b3661f3
+size 347498816

preprocessor_config.json

@@ -1,19 +1,19 @@
 {
   "do_normalize": true,
   "do_rescale": true,
-  "do_resize": "google/vit-large-patch16-224",
+  "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,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a59ef74154ade0ab109507e8d50a5a4ba1e1f41530efe46cd1f011550ac7a32b
-size 5176
+oid sha256:74535994e4fcb24d091b04f1a60a8cee013bf35c0ee77adc057807c31c26955d
+size 5112