Training in progress, epoch 1

config.json

@@ -1,21 +1,13 @@
 {
-  "_name_or_path": "microsoft/swin-base-patch4-window7-224",
+  "_name_or_path": "google/vit-base-patch16-224-in21k",
   "architectures": [
-    "SwinForImageClassification"
+    "ViTForImageClassification"
   ],
   "attention_probs_dropout_prob": 0.0,
-  "depths": [
-    2,
-    2,
-    18,
-    2
-  ],
-  "drop_path_rate": 0.1,
-  "embed_dim": 128,
-  "encoder_stride": 32,
+  "encoder_stride": 16,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.0,
-  "hidden_size": 1024,
+  "hidden_size": 768,
   "id2label": {
     "0": "Apple Braeburn",
     "1": "Apple Crimson Snow",
@@ -133,6 +125,7 @@
   },
   "image_size": 224,
   "initializer_range": 0.02,
+  "intermediate_size": 3072,
   "label2id": {
     "Apple Braeburn": 0,
     "Apple Crimson Snow": 1,
@@ -248,36 +241,14 @@
     "Walnut": 111,
     "Watermelon": 112
   },
-  "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": [
-    4,
-    8,
-    16,
-    32
-  ],
-  "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": "4.34.1",
-  "use_absolute_embeddings": false,
-  "window_size": 7
+  "transformers_version": "4.34.1"
 }

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 sha256:988eb090a6060594f3d4d9a856d34360e3bac5e304d27ab367dc348ca94a5dbc
-size 348055374
+oid sha256:1cec28c9b79f14b0e9700a09a1171cb1dba6e11e9fb169c658fc03f9db8762c8
+size 343610602

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69f50f482dc64e2ebb8dd618b53371a4c8bdfad03b2a0811701c67546b5bdb9a
+oid sha256:45b502d8a8729f313ae9c091160349d19ea2098b0828cbcb8d6a9f9d44d1ca9d
 size 4600