initial commit

app.py

@@ -0,0 +1,32 @@
+import datasets
+import gradio as gr
+import torch
+from transformers import AutoFeatureExtractor, SegformerForSemanticSegmentation
+
+extractor = AutoFeatureExtractor.from_pretrained('saved_model_files')
+
+labels = {0: 'road/sidewalk/path', 1: 'human', 2: 'vehicles', 3:'other objects', 4:'nature and background'}
+device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
+model = SegformerForSemanticSegmentation.from_pretrained('saved_model_files',
+                                                         num_labels = len(labels),
+                                                         id2label={str(i) : c for i, c in enumerate(labels)},
+                                                         label2id={c: str(i) for i, c in enumerate(labels)},
+                                                         ignore_mismatched_sizes=True)
+model.eval()
+model.to(device)
+
+def classify(im):
+  inputs = extractor(images=im, return_tensors='pt').to(device)
+  outputs = model(**inputs)
+  logits = outputs.logits
+  classes = logits[0].detach().cpu().numpy().argmax(axis=0)
+  colors = np.array([[128,0,0], [128,128,0], [0,0,128], [128,0,128], [0,0,0]])
+  return colors[classes]
+
+interface = gr.Interface(fn=classify,
+                         inputs='image',
+                         outputs='image')
+
+interface = gr.Interface(fn=classify, inputs='image', outputs='image', examples=['1.png', '2.png', '3.png'], title='Image Segmentation App', description='Perform segmentation on pictures of outdoor scenes', flagging_dir='flagged_examples/') # FILL HERE
+
+interface.launch(debug=True)

requirements.txt

@@ -0,0 +1,3 @@
+gradio
+transformers
+torch

saved_model_files/config.json

@@ -0,0 +1,84 @@
+{
+  "_name_or_path": "nvidia/segformer-b0-finetuned-ade-512-512",
+  "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": 0,
+    "1": 1,
+    "2": 2,
+    "3": 3,
+    "4": 4
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "label2id": {
+    "0": "0",
+    "1": "1",
+    "2": "2",
+    "3": "3",
+    "4": "4"
+  },
+  "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": "4.22.2"
+}

saved_model_files/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": true,
+  "resample": 2,
+  "size": 512
+}

saved_model_files/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7ab4a2411f4ab1d7e7de03fe9cc1a342a251fd60b1b7a9e87a6b4b672cdfe6a
+size 14933025