Upload folder using huggingface_hub

README.md

@@ -0,0 +1,93 @@
+---
+library_name: segmentation-models-pytorch
+license: mit
+pipeline_tag: image-segmentation
+tags:
+- model_hub_mixin
+- pytorch_model_hub_mixin
+- segmentation-models-pytorch
+- semantic-segmentation
+- pytorch
+- upernet
+languages:
+- python
+---
+# UPerNet Model Card
+
+Table of Contents:
+- [Load trained model](#load-trained-model)
+- [Model init parameters](#model-init-parameters)
+- [Dataset](#dataset)
+
+## Load trained model
+
+[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/qubvel/segmentation_models.pytorch/blob/main/examples/upernet_inference_pretrained.ipynb)
+
+1. Install requirements.
+
+```bash
+pip install -U segmentation_models_pytorch albumentations
+```
+
+2. Run inference.
+
+```python
+import torch
+import requests
+import numpy as np
+import albumentations as A
+import segmentation_models_pytorch as smp
+
+from PIL import Image
+
+device = "cuda" if torch.cuda.is_available() else "cpu"
+
+# Load pretrained model and preprocessing function
+checkpoint = "smp-hub/upernet-swin-large"
+model = smp.from_pretrained(checkpoint).eval().to(device)
+preprocessing = A.Compose.from_pretrained(checkpoint)
+
+# Load image
+url = "https://huggingface.co/datasets/hf-internal-testing/fixtures_ade20k/resolve/main/ADE_val_00000001.jpg"
+image = Image.open(requests.get(url, stream=True).raw)
+
+# Preprocess image
+np_image = np.array(image)
+normalized_image = preprocessing(image=np_image)["image"]
+input_tensor = torch.as_tensor(normalized_image)
+input_tensor = input_tensor.permute(2, 0, 1).unsqueeze(0)  # HWC -> BCHW
+input_tensor = input_tensor.to(device)
+
+# Perform inference
+with torch.no_grad():
+    output_mask = model(input_tensor)
+
+# Postprocess mask
+mask = mask.argmax(1).cpu().numpy()  # argmax over predicted classes (channels dim)
+```
+
+## Model init parameters
+```python
+model_init_params = {
+    "encoder_name": "tu-swin_large_patch4_window12_384",
+    "encoder_depth": 5,
+    "encoder_weights": None,
+    "decoder_channels": 512,
+    "decoder_use_norm": "batchnorm",
+    "in_channels": 3,
+    "classes": 150,
+    "activation": None,
+    "upsampling": 4,
+    "aux_params": None,
+    "img_size": 512
+}
+```
+
+## Dataset
+Dataset name: [ADE20K](https://ade20k.csail.mit.edu/)
+
+## More Information
+- Library: https://github.com/qubvel/segmentation_models.pytorch
+- Docs: https://smp.readthedocs.io/en/latest/
+
+This model has been pushed to the Hub using the [PytorchModelHubMixin](https://huggingface.co/docs/huggingface_hub/package_reference/mixins#huggingface_hub.PyTorchModelHubMixin)

albumentations_config_eval.json

@@ -0,0 +1 @@
+{"__version__": "2.0.5", "transform": {"__class_fullname__": "Compose", "p": 1.0, "transforms": [{"__class_fullname__": "Resize", "p": 1.0, "height": 512, "width": 512, "interpolation": 1, "mask_interpolation": 0}, {"__class_fullname__": "Normalize", "p": 1.0, "mean": [123.675, 116.28, 103.53], "std": [58.395, 57.12, 57.375], "max_pixel_value": 1.0, "normalization": "standard"}], "bbox_params": null, "keypoint_params": null, "additional_targets": {}, "is_check_shapes": true}}

config.json

@@ -0,0 +1,14 @@
+{
+  "_model_class": "UPerNet",
+  "activation": null,
+  "aux_params": null,
+  "classes": 150,
+  "decoder_channels": 512,
+  "decoder_use_norm": "batchnorm",
+  "encoder_depth": 5,
+  "encoder_name": "tu-swin_large_patch4_window12_384",
+  "encoder_weights": null,
+  "img_size": 512,
+  "in_channels": 3,
+  "upsampling": 4
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82d354d6d37e814fe58d07e6572aa67e72a78fe44332e489f805ae7131eda506
+size 928714152