End of training

README.md

@@ -0,0 +1,50 @@
+---
+license: other
+base_model: nvidia/mit-b0
+tags:
+- image-segmentation
+- vision
+- generated_from_trainer
+model-index:
+- name: segformer-cloud
+  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-cloud
+
+This model is a fine-tuned version of [nvidia/mit-b0](https://huggingface.co/nvidia/mit-b0) on the segments/sidewalk-semantic dataset.
+
+## 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: 8
+- eval_batch_size: 8
+- seed: 1337
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- training_steps: 1000
+
+### Framework versions
+
+- Transformers 4.36.0.dev0
+- Pytorch 2.1.1+cu118
+- Datasets 2.15.0
+- Tokenizers 0.15.0

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": "4.36.0.dev0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7cd29b11184fe0930a083076489ccba40d51089aff9d8385355e420d1663bd1
+size 14918708

preprocessor_config.json

@@ -0,0 +1,23 @@
+{
+  "do_normalize": true,
+  "do_reduce_labels": false,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.485,
+    0.456,
+    0.406
+  ],
+  "image_processor_type": "SegformerImageProcessor",
+  "image_std": [
+    0.229,
+    0.224,
+    0.225
+  ],
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 512,
+    "width": 512
+  }
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b7d96006e75d3c6017d6247feba462fd1e8626e159b06864d543abd2970719c
+size 4728