chore: setting

app.py

@@ -0,0 +1,15 @@
+from transformers import SegformerFeatureExtractor, SegformerForSemanticSegmentation
+from PIL import Image
+import requests
+
+feature_extractor = SegformerFeatureExtractor.from_pretrained("nvidia/segformer-b0-finetuned-cityscapes-1024-1024")
+model = SegformerForSemanticSegmentation.from_pretrained("nvidia/segformer-b0-finetuned-cityscapes-1024-1024")
+
+url = "http://images.cocodataset.org/val2017/000000039769.jpg"
+image = Image.open(requests.get(url, stream=True).raw)
+
+inputs = feature_extractor(images=image, return_tensors="pt")
+outputs = model(**inputs)
+logits = outputs.logits  # shape (batch_size, num_labels, height/4, width/4)
+
+

config.json

@@ -0,0 +1,110 @@
+{
+  "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": "road",
+    "1": "sidewalk",
+    "2": "building",
+    "3": "wall",
+    "4": "fence",
+    "5": "pole",
+    "6": "traffic light",
+    "7": "traffic sign",
+    "8": "vegetation",
+    "9": "terrain",
+    "10": "sky",
+    "11": "person",
+    "12": "rider",
+    "13": "car",
+    "14": "truck",
+    "15": "bus",
+    "16": "train",
+    "17": "motorcycle",
+    "18": "bicycle"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "label2id": {
+    "bicycle": 18,
+    "building": 2,
+    "bus": 15,
+    "car": 13,
+    "fence": 4,
+    "motorcycle": 17,
+    "person": 11,
+    "pole": 5,
+    "rider": 12,
+    "road": 0,
+    "sidewalk": 1,
+    "sky": 10,
+    "terrain": 9,
+    "traffic light": 6,
+    "traffic sign": 7,
+    "train": 16,
+    "truck": 14,
+    "vegetation": 8,
+    "wall": 3
+  },
+  "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,
+  "sr_ratios": [
+    8,
+    4,
+    2,
+    1
+  ],
+  "strides": [
+    4,
+    2,
+    2,
+    2
+  ],
+  "torch_dtype": "float32",
+  "transformers_version": "4.12.0.dev0"
+}

preprocessor_config.json

@@ -0,0 +1,18 @@
+{
+  "do_normalize": true,
+  "do_resize": true,
+  "feature_extractor_type": "SegformerFeatureExtractor",
+  "image_mean": [
+    0.485,
+    0.456,
+    0.406
+  ],
+  "image_std": [
+    0.229,
+    0.224,
+    0.225
+  ],
+  "reduce_labels": false,
+  "resample": 2,
+  "size": 512
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:027ed78d8ff9c535df5a66361c92b9673cca3cb923cbeb8c5802385b6b93194c
+size 14957601

tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc6105da7857b3c35b7e9032f008177840ea16a8ed36c08a2a51b094a41b3b49
+size 15151028