Upload 3 files

README.md

@@ -0,0 +1,66 @@
+---
+license: other
+tags:
+- vision
+- image-segmentation
+- generated_from_trainer
+model-index:
+- name: segformer-b0-finetuned-segments-sidewalk-2
+  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-b0-finetuned-segments-sidewalk-2
+
+This model is a fine-tuned version of [nvidia/mit-b0](https://huggingface.co/nvidia/mit-b0) on the segments/sidewalk-semantic dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.9042
+- Mean Iou: 0.1600
+- Mean Accuracy: 0.1997
+- Overall Accuracy: 0.7338
+- Per Category Iou: [nan, 0.27359520957005035, 0.6563592089876799, 0.0, 0.23344374046535918, 0.0, nan, 0.0, 0.0, 0.0, 0.5539341917024321, nan, nan, nan, nan, 0.0, 0.0, nan, 0.6213519498256361, 0.0, 0.0, 0.0, nan, nan, 0.0, 0.0, 0.0, 0.0, 0.8012808797206368, 0.0, 0.8609473035107046, nan, 0.0, 0.0, 0.0]
+- Per Category Accuracy: [nan, 0.38598740280061317, 0.9344800917343116, 0.0, 0.23402267811135147, 0.0, nan, 0.0, 0.0, 0.0, 0.6574569071869553, nan, nan, nan, nan, 0.0, 0.0, nan, 0.889953470705536, 0.0, 0.0, 0.0, nan, nan, 0.0, 0.0, 0.0, 0.0, 0.9339123774958169, 0.0, 0.9562267789312698, nan, 0.0, 0.0, 0.0]
+
+## 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: 6e-05
+- train_batch_size: 2
+- eval_batch_size: 2
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 2
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Mean Iou | Mean Accuracy | Overall Accuracy | Per Category Iou                                                                                                                                                                                                                                                                                                                               | Per Category Accuracy                                                                                                                                                                                                                                                                                                                         |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:-------------:|:----------------:|:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------:|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------:|
+| 2.8419        | 0.42  | 20   | 3.2243          | 0.1239   | 0.1973        | 0.6992           | [0.0, 0.221283072298205, 0.6482498250140304, 0.0, 0.36607695456244177, 0.013827775204570018, nan, 1.0254201659129828e-05, 0.0, 0.0, 0.5416500682753081, nan, 0.0, 0.0, nan, 0.0, 0.0, 0.0, 0.5339731316050166, 0.0, 0.0006440571922786744, 0.0, nan, 0.0, 0.0, 0.0, 0.0, 0.0, 0.7498440701547007, 0.0, 0.7659222854515146, 0.0, 0.0, 0.0, 0.0] | [nan, 0.3346613609105567, 0.8582083544770268, 0.0, 0.5101472837243907, 0.015482685970504024, nan, 1.0366454154356502e-05, 0.0, 0.0, 0.6745826026281508, nan, nan, nan, nan, 0.0, 0.0, nan, 0.8093545247364923, 0.0, 0.0006458279514337381, 0.0, nan, nan, 0.0, 0.0, 0.0, 0.0, 0.9324806212895075, 0.0, 0.797418357423677, nan, 0.0, 0.0, 0.0] |
+| 2.3662        | 0.83  | 40   | 2.5147          | 0.1402   | 0.1798        | 0.6989           | [nan, 0.19549119549985344, 0.6036027201962391, 0.0, 0.0019222772099991463, 0.000300503343099692, nan, 0.0, 0.0, 0.0, 0.47853978429259575, nan, nan, nan, nan, 0.0, 0.0, nan, 0.5820555774612892, 0.0, 0.0, 0.0, nan, nan, 0.0, 0.0, 0.0, 0.0, 0.7898452112422248, 0.0, 0.8521568687502872, nan, 0.0, 0.0, 0.0]                                 | [nan, 0.25107981668136076, 0.9396577375184628, 0.0, 0.0019233683746435017, 0.0003025228242666523, nan, 0.0, 0.0, 0.0, 0.5513810659584686, nan, nan, nan, nan, 0.0, 0.0, nan, 0.8953553793561865, 0.0, 0.0, 0.0, nan, nan, 0.0, 0.0, 0.0, 0.0, 0.9300976130892274, 0.0, 0.9250758451014455, nan, 0.0, 0.0, 0.0]                                |
+| 2.1745        | 1.25  | 60   | 2.0428          | 0.1485   | 0.1882        | 0.7162           | [nan, 0.24240648716131, 0.6262941164542789, 0.0, 0.04440846090507781, 0.0, nan, 0.0, 0.0, 0.0, 0.522913696330921, nan, nan, nan, nan, 0.0, 0.0, nan, 0.6194890050543631, 0.0, 0.0, 0.0, nan, nan, 0.0, 0.0, 0.0, 0.0, 0.7947837731119848, 0.0, 0.8609570537373858, nan, 0.0, 0.0, 0.0]                                                         | [nan, 0.3318909301752965, 0.9392945927202885, 0.0, 0.04443587164684973, 0.0, nan, 0.0, 0.0, 0.0, 0.6149676720993105, nan, nan, nan, nan, 0.0, 0.0, nan, 0.8836542113759377, 0.0, 0.0, 0.0, nan, nan, 0.0, 0.0, 0.0, 0.0, 0.9409947331534898, 0.0, 0.9509521157666382, nan, 0.0, 0.0, 0.0]                                                     |
+| 1.986         | 1.67  | 80   | 1.9042          | 0.1600   | 0.1997        | 0.7338           | [nan, 0.27359520957005035, 0.6563592089876799, 0.0, 0.23344374046535918, 0.0, nan, 0.0, 0.0, 0.0, 0.5539341917024321, nan, nan, nan, nan, 0.0, 0.0, nan, 0.6213519498256361, 0.0, 0.0, 0.0, nan, nan, 0.0, 0.0, 0.0, 0.0, 0.8012808797206368, 0.0, 0.8609473035107046, nan, 0.0, 0.0, 0.0]                                                     | [nan, 0.38598740280061317, 0.9344800917343116, 0.0, 0.23402267811135147, 0.0, nan, 0.0, 0.0, 0.0, 0.6574569071869553, nan, nan, nan, nan, 0.0, 0.0, nan, 0.889953470705536, 0.0, 0.0, 0.0, nan, nan, 0.0, 0.0, 0.0, 0.0, 0.9339123774958169, 0.0, 0.9562267789312698, nan, 0.0, 0.0, 0.0]                                                     |
+
+
+### Framework versions
+
+- Transformers 4.23.1
+- Pytorch 1.12.1+cu113
+- Datasets 2.5.2
+- Tokenizers 0.13.1

config.json

@@ -0,0 +1,144 @@
+{
+  "_name_or_path": "nvidia/mit-b0",
+  "architectures": [
+    "SegformerForSemanticSegmentation"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "classifier_dropout_prob": 0.1,
+  "decoder_hidden_size": 256,
+  "depths": [
+    2,
+    2,
+    2,
+    2
+  ],
+  "downsampling_rates": [
+    1,
+    4,
+    8,
+    16
+  ],
+  "drop_path_rate": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_sizes": [
+    32,
+    64,
+    160,
+    256
+  ],
+  "id2label": {
+    "0": "unlabeled",
+    "1": "flat-road",
+    "2": "flat-sidewalk",
+    "3": "flat-crosswalk",
+    "4": "flat-cyclinglane",
+    "5": "flat-parkingdriveway",
+    "6": "flat-railtrack",
+    "7": "flat-curb",
+    "8": "human-person",
+    "9": "human-rider",
+    "10": "vehicle-car",
+    "11": "vehicle-truck",
+    "12": "vehicle-bus",
+    "13": "vehicle-tramtrain",
+    "14": "vehicle-motorcycle",
+    "15": "vehicle-bicycle",
+    "16": "vehicle-caravan",
+    "17": "vehicle-cartrailer",
+    "18": "construction-building",
+    "19": "construction-door",
+    "20": "construction-wall",
+    "21": "construction-fenceguardrail",
+    "22": "construction-bridge",
+    "23": "construction-tunnel",
+    "24": "construction-stairs",
+    "25": "object-pole",
+    "26": "object-trafficsign",
+    "27": "object-trafficlight",
+    "28": "nature-vegetation",
+    "29": "nature-terrain",
+    "30": "sky",
+    "31": "void-ground",
+    "32": "void-dynamic",
+    "33": "void-static",
+    "34": "void-unclear"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "label2id": {
+    "construction-bridge": 22,
+    "construction-building": 18,
+    "construction-door": 19,
+    "construction-fenceguardrail": 21,
+    "construction-stairs": 24,
+    "construction-tunnel": 23,
+    "construction-wall": 20,
+    "flat-crosswalk": 3,
+    "flat-curb": 7,
+    "flat-cyclinglane": 4,
+    "flat-parkingdriveway": 5,
+    "flat-railtrack": 6,
+    "flat-road": 1,
+    "flat-sidewalk": 2,
+    "human-person": 8,
+    "human-rider": 9,
+    "nature-terrain": 29,
+    "nature-vegetation": 28,
+    "object-pole": 25,
+    "object-trafficlight": 27,
+    "object-trafficsign": 26,
+    "sky": 30,
+    "unlabeled": 0,
+    "vehicle-bicycle": 15,
+    "vehicle-bus": 12,
+    "vehicle-car": 10,
+    "vehicle-caravan": 16,
+    "vehicle-cartrailer": 17,
+    "vehicle-motorcycle": 14,
+    "vehicle-tramtrain": 13,
+    "vehicle-truck": 11,
+    "void-dynamic": 32,
+    "void-ground": 31,
+    "void-static": 33,
+    "void-unclear": 34
+  },
+  "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": "4.23.1"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3bee57adcaeb94b6abdb3dcdcb8641f9ccb208c2253aff1a9b0be802d59da305
+size 3439