Training in progress, epoch 0

config.json

@@ -1,51 +1,18 @@
 {
-  "_name_or_path": "openmmlab/upernet-convnext-tiny",
+  "_name_or_path": "microsoft/beit-base-finetuned-ade-640-640",
+  "add_fpn": false,
   "architectures": [
-    "UperNetForSemanticSegmentation"
+    "BeitForSemanticSegmentation"
   ],
+  "attention_probs_dropout_prob": 0.0,
   "auxiliary_channels": 256,
   "auxiliary_concat_input": false,
-  "auxiliary_in_channels": 384,
   "auxiliary_loss_weight": 0.4,
   "auxiliary_num_convs": 1,
-  "backbone": null,
-  "backbone_config": {
-    "depths": [
-      3,
-      3,
-      9,
-      3
-    ],
-    "drop_path_rate": 0.0,
-    "hidden_act": "gelu",
-    "hidden_sizes": [
-      96,
-      192,
-      384,
-      768
-    ],
-    "image_size": 224,
-    "initializer_range": 0.02,
-    "layer_norm_eps": 1e-12,
-    "layer_scale_init_value": 1e-06,
-    "model_type": "convnext",
-    "num_stages": 4,
-    "out_features": [
-      "stage1",
-      "stage2",
-      "stage3",
-      "stage4"
-    ],
-    "out_indices": [
-      1,
-      2,
-      3,
-      4
-    ],
-    "patch_size": 4
-  },
-  "backbone_kwargs": null,
-  "hidden_size": 512,
+  "drop_path_rate": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 768,
   "id2label": {
     "0": "unlabeled",
     "1": "flat-road",
@@ -83,7 +50,9 @@
     "33": "void-static",
     "34": "void-unclear"
   },
+  "image_size": 640,
   "initializer_range": 0.02,
+  "intermediate_size": 3072,
   "label2id": {
     "construction-bridge": "22",
     "construction-building": "18",
@@ -121,17 +90,61 @@
     "void-static": "33",
     "void-unclear": "34"
   },
-  "loss_ignore_index": 255,
-  "model_type": "upernet",
+  "layer_norm_eps": 1e-12,
+  "layer_scale_init_value": 0.1,
+  "model_type": "beit",
+  "num_attention_heads": 12,
+  "num_channels": 3,
+  "num_hidden_layers": 12,
+  "out_features": [
+    "stage3",
+    "stage5",
+    "stage7",
+    "stage11"
+  ],
+  "out_indices": [
+    3,
+    5,
+    7,
+    11
+  ],
+  "patch_size": 16,
   "pool_scales": [
     1,
     2,
     3,
     6
   ],
+  "reshape_hidden_states": true,
+  "segmentation_indices": [
+    3,
+    5,
+    7,
+    11
+  ],
+  "semantic_loss_ignore_index": 255,
+  "stage_names": [
+    "stem",
+    "stage1",
+    "stage2",
+    "stage3",
+    "stage4",
+    "stage5",
+    "stage6",
+    "stage7",
+    "stage8",
+    "stage9",
+    "stage10",
+    "stage11",
+    "stage12"
+  ],
   "torch_dtype": "float32",
   "transformers_version": "4.47.0.dev0",
+  "use_absolute_position_embeddings": false,
   "use_auxiliary_head": true,
-  "use_pretrained_backbone": false,
-  "use_timm_backbone": false
+  "use_mask_token": false,
+  "use_mean_pooling": true,
+  "use_relative_position_bias": true,
+  "use_shared_relative_position_bias": false,
+  "vocab_size": 8192
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dda8d0e048cbb8250a035977c7be04ba9620c96aa73dd4f446143a1344e890dd
-size 240698832
+oid sha256:c2efb78642487771d13d7454b3f449da0c60f8e68ee25095854871d8bdf350fd
+size 653277616

preprocessor_config.json

@@ -1,23 +1,28 @@
 {
+  "crop_size": {
+    "height": 224,
+    "width": 224
+  },
+  "do_center_crop": false,
   "do_normalize": true,
   "do_reduce_labels": false,
   "do_rescale": true,
   "do_resize": true,
   "image_mean": [
-    0.485,
-    0.456,
-    0.406
+    0.5,
+    0.5,
+    0.5
   ],
-  "image_processor_type": "SegformerImageProcessor",
+  "image_processor_type": "BeitImageProcessor",
   "image_std": [
-    0.229,
-    0.224,
-    0.225
+    0.5,
+    0.5,
+    0.5
   ],
-  "resample": 2,
+  "resample": 3,
   "rescale_factor": 0.00392156862745098,
   "size": {
-    "height": 512,
-    "width": 512
+    "height": 640,
+    "width": 640
   }
 }

runs/Nov28_08-59-28_d2a3b59c97a0/events.out.tfevents.1732784374.d2a3b59c97a0.7158.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ed4259641788ea1b518aa8ada7c26b7aa0f1593924341a6472785e361ca43f1
+size 8031

runs/Nov28_09-00-26_d2a3b59c97a0/events.out.tfevents.1732784432.d2a3b59c97a0.7435.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aad06344311da7e8ea87994ef6c5841c813cc32820cf969666a3948d22199259
+size 4184

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:19f60e1a08e003b6989ffa925f65ebf7f9e8faf099a992949baf1d0cf81f5f03
+oid sha256:5e598f8900f748cdbc0082169b119617a55e1016ff805e27d8e9dc78ec453b4e
 size 5432