Model save

README.md

@@ -0,0 +1,109 @@
+---
+library_name: transformers
+license: other
+base_model: nvidia/segformer-b2-finetuned-cityscapes-1024-1024
+tags:
+- generated_from_trainer
+model-index:
+- name: SegFormer_b2_mappillary_
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# SegFormer_b2_mappillary_
+
+This model is a fine-tuned version of [nvidia/segformer-b2-finetuned-cityscapes-1024-1024](https://huggingface.co/nvidia/segformer-b2-finetuned-cityscapes-1024-1024) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- epoch: 7.1111
+- eval_accuracy_construction--barrier--fence: 0.6884
+- eval_accuracy_construction--barrier--guard-rail: 0.8285
+- eval_accuracy_construction--barrier--other-barrier: 0.6796
+- eval_accuracy_construction--barrier--wall: 0.6617
+- eval_accuracy_construction--flat--road: 0.9450
+- eval_accuracy_construction--flat--service-lane: 0.6045
+- eval_accuracy_construction--flat--sidewalk: 0.9036
+- eval_accuracy_construction--structure--building: 0.9448
+- eval_accuracy_human--person: 0.8152
+- eval_accuracy_human--rider--bicyclist: 0.7298
+- eval_accuracy_marking--crosswalk-zebra: 0.8040
+- eval_accuracy_marking--general: 0.6630
+- eval_accuracy_nature--sky: 0.9894
+- eval_accuracy_nature--terrain: 0.7920
+- eval_accuracy_nature--vegetation: 0.9467
+- eval_accuracy_object--support--pole: 0.5267
+- eval_accuracy_object--support--traffic-sign-frame: 0.6493
+- eval_accuracy_object--traffic-light: 0.7177
+- eval_accuracy_object--traffic-sign--front: 0.7995
+- eval_accuracy_object--vehicle--bicycle: 0.7409
+- eval_accuracy_object--vehicle--bus: 0.8505
+- eval_accuracy_object--vehicle--car: 0.9596
+- eval_accuracy_object--vehicle--truck: 0.7913
+- eval_iou_construction--barrier--fence: 0.5326
+- eval_iou_construction--barrier--guard-rail: 0.6142
+- eval_iou_construction--barrier--other-barrier: 0.5604
+- eval_iou_construction--barrier--wall: 0.5195
+- eval_iou_construction--flat--road: 0.9074
+- eval_iou_construction--flat--service-lane: 0.4444
+- eval_iou_construction--flat--sidewalk: 0.7564
+- eval_iou_construction--structure--building: 0.8785
+- eval_iou_human--person: 0.6633
+- eval_iou_human--rider--bicyclist: 0.5386
+- eval_iou_marking--crosswalk-zebra: 0.6628
+- eval_iou_marking--general: 0.5555
+- eval_iou_nature--sky: 0.9801
+- eval_iou_nature--terrain: 0.6805
+- eval_iou_nature--vegetation: 0.8897
+- eval_iou_object--support--pole: 0.4260
+- eval_iou_object--support--traffic-sign-frame: 0.5314
+- eval_iou_object--traffic-light: 0.5586
+- eval_iou_object--traffic-sign--front: 0.6967
+- eval_iou_object--vehicle--bicycle: 0.5583
+- eval_iou_object--vehicle--bus: 0.7226
+- eval_iou_object--vehicle--car: 0.8913
+- eval_iou_object--vehicle--truck: 0.6813
+- eval_loss: 0.9738
+- eval_mean_accuracy: 0.7840
+- eval_mean_iou: 0.6630
+- eval_overall_accuracy: 0.9356
+- eval_runtime: 1231.0899
+- eval_samples_per_second: 1.625
+- eval_steps_per_second: 0.812
+- step: 16000
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-05
+- train_batch_size: 2
+- eval_batch_size: 2
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 8
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 1000
+- num_epochs: 30
+- mixed_precision_training: Native AMP
+
+### Framework versions
+
+- Transformers 4.48.1
+- Pytorch 2.1.2+cu121
+- Datasets 3.2.0
+- Tokenizers 0.21.0

config.json

@@ -0,0 +1,120 @@
+{
+  "_name_or_path": "nvidia/segformer-b2-finetuned-cityscapes-1024-1024",
+  "architectures": [
+    "SegformerForSemanticSegmentation"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "classifier_dropout_prob": 0.1,
+  "decoder_hidden_size": 768,
+  "depths": [
+    3,
+    4,
+    6,
+    3
+  ],
+  "downsampling_rates": [
+    1,
+    4,
+    8,
+    16
+  ],
+  "drop_path_rate": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_sizes": [
+    64,
+    128,
+    320,
+    512
+  ],
+  "id2label": {
+    "0": "construction--barrier--fence",
+    "1": "construction--barrier--guard-rail",
+    "2": "construction--barrier--other-barrier",
+    "3": "construction--barrier--wall",
+    "4": "construction--flat--road",
+    "5": "construction--flat--service-lane",
+    "6": "construction--flat--sidewalk",
+    "7": "construction--structure--building",
+    "8": "human--person",
+    "9": "human--rider--bicyclist",
+    "10": "marking--crosswalk-zebra",
+    "11": "marking--general",
+    "12": "nature--sky",
+    "13": "nature--terrain",
+    "14": "nature--vegetation",
+    "15": "object--support--pole",
+    "16": "object--support--traffic-sign-frame",
+    "17": "object--traffic-light",
+    "18": "object--traffic-sign--front",
+    "19": "object--vehicle--bicycle",
+    "20": "object--vehicle--bus",
+    "21": "object--vehicle--car",
+    "22": "object--vehicle--truck"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "label2id": {
+    "construction--barrier--fence": 0,
+    "construction--barrier--guard-rail": 1,
+    "construction--barrier--other-barrier": 2,
+    "construction--barrier--wall": 3,
+    "construction--flat--road": 4,
+    "construction--flat--service-lane": 5,
+    "construction--flat--sidewalk": 6,
+    "construction--structure--building": 7,
+    "human--person": 8,
+    "human--rider--bicyclist": 9,
+    "marking--crosswalk-zebra": 10,
+    "marking--general": 11,
+    "nature--sky": 12,
+    "nature--terrain": 13,
+    "nature--vegetation": 14,
+    "object--support--pole": 15,
+    "object--support--traffic-sign-frame": 16,
+    "object--traffic-light": 17,
+    "object--traffic-sign--front": 18,
+    "object--vehicle--bicycle": 19,
+    "object--vehicle--bus": 20,
+    "object--vehicle--car": 21,
+    "object--vehicle--truck": 22
+  },
+  "layer_norm_eps": 1e-06,
+  "mlp_ratios": [
+    4,
+    4,
+    4,
+    4
+  ],
+  "model_type": "segformer",
+  "num_attention_heads": [
+    1,
+    2,
+    5,
+    8
+  ],
+  "num_channels": 3,
+  "num_encoder_blocks": 4,
+  "patch_sizes": [
+    7,
+    3,
+    3,
+    3
+  ],
+  "reshape_last_stage": true,
+  "semantic_loss_ignore_index": 255,
+  "sr_ratios": [
+    8,
+    4,
+    2,
+    1
+  ],
+  "strides": [
+    4,
+    2,
+    2,
+    2
+  ],
+  "torch_dtype": "float32",
+  "transformers_version": "4.48.1"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:399300fce5cbb47bc266d6fcd0b10bcab0bb47337e133da55134d6f7801fd036
+size 109508620

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6813266116a7b2c970f3ff782eac8f17ad32c8559590d1e8ada1857849dba22b
+size 5368