AutoImageProcessor mobilenet

app.py

@@ -3,6 +3,7 @@ import requests
 from PIL import Image
 import torch
 import numpy
+import gradio as gr
 
 from transformers import DetrImageProcessor, DetrForSegmentation, AutoImageProcessor, AutoModelForImageClassification
 from transformers.models.detr.feature_extraction_detr import rgb_to_id
@@ -10,29 +11,36 @@ from transformers.models.detr.feature_extraction_detr import rgb_to_id
 url = "http://images.cocodataset.org/val2017/000000039769.jpg"
 image = Image.open(requests.get(url, stream=True).raw)
 
-feature_extractor = DetrImageProcessor.from_pretrained("facebook/detr-resnet-50-panoptic")
-model = DetrForSegmentation.from_pretrained("facebook/detr-resnet-50-panoptic")
+# feature_extractor = DetrImageProcessor.from_pretrained("facebook/post_process_panoptic_segmentation")
+# model = DetrForSegmentation.from_pretrained("facebook/post_process_panoptic_segmentation")
+#
+# # prepare image for the model
+# inputs = feature_extractor(images=image, return_tensors="pt")
+#
+# # forward pass
+# outputs = model(**inputs)
+#
+# # use the `post_process_panoptic` method of `DetrFeatureExtractor` to convert to COCO format
+# processed_sizes = torch.as_tensor(inputs["pixel_values"].shape[-2:]).unsqueeze(0)
+# result = feature_extractor.post_process_panoptic(outputs, processed_sizes)[0]
+#
+# # the segmentation is stored in a special-format png
+# panoptic_seg = Image.open(io.BytesIO(result["png_string"]))
+# panoptic_seg = numpy.array(panoptic_seg, dtype=numpy.uint8)
+# # retrieve the ids corresponding to each mask
+# panoptic_seg_id = rgb_to_id(panoptic_seg)
+
+
+preprocessor = AutoImageProcessor.from_pretrained("google/mobilenet_v2_1.0_224")
+model = AutoModelForImageClassification.from_pretrained("google/mobilenet_v2_1.0_224")
+
+inputs = preprocessor(images=image, return_tensors="pt")
 
-# prepare image for the model
-inputs = feature_extractor(images=image, return_tensors="pt")
-
-# forward pass
 outputs = model(**inputs)
+logits = outputs.logits
 
-# use the `post_process_panoptic` method of `DetrFeatureExtractor` to convert to COCO format
-processed_sizes = torch.as_tensor(inputs["pixel_values"].shape[-2:]).unsqueeze(0)
-result = feature_extractor.post_process_panoptic(outputs, processed_sizes)[0]
-
-# the segmentation is stored in a special-format png
-panoptic_seg = Image.open(io.BytesIO(result["png_string"]))
-panoptic_seg = numpy.array(panoptic_seg, dtype=numpy.uint8)
-# retrieve the ids corresponding to each mask
-panoptic_seg_id = rgb_to_id(panoptic_seg)
-
-
-
-
-# preprocessor = AutoImageProcessor.from_pretrained("google/mobilenet_v2_1.0_224")
-# model = AutoModelForImageClassification.from_pretrained("google/mobilenet_v2_1.0_224")
+# model predicts one of the 1000 ImageNet classes
+predicted_class_idx = logits.argmax(-1).item()
+print("Predicted class:", model.config.id2label[predicted_class_idx])
 
-# inputs = preprocessor(images=image, return_tensors="pt")
+# gr.Image(image).launch()

requirements.txt

@@ -1,26 +1,74 @@
+aiofiles==23.2.1
+annotated-types==0.7.0
+anyio==4.4.0
 certifi==2024.7.4
 charset-normalizer==3.3.2
+click==8.1.7
+contourpy==1.2.1
+cycler==0.12.1
+dnspython==2.6.1
+email_validator==2.2.0
+fastapi==0.111.1
+fastapi-cli==0.0.4
+ffmpy==0.3.2
 filelock==3.15.4
+fonttools==4.53.1
 fsspec==2024.6.1
+gradio==4.39.0
+gradio_client==1.1.1
+h11==0.14.0
+httpcore==1.0.5
+httptools==0.6.1
+httpx==0.27.0
 huggingface-hub==0.24.2
 idna==3.7
+importlib_resources==6.4.0
 Jinja2==3.1.4
+kiwisolver==1.4.5
+markdown-it-py==3.0.0
 MarkupSafe==2.1.5
+matplotlib==3.9.1
+mdurl==0.1.2
 mpmath==1.3.0
 networkx==3.3
 numpy==2.0.1
+orjson==3.10.6
 packaging==24.1
+pandas==2.2.2
 pillow==10.4.0
+pydantic==2.8.2
+pydantic_core==2.20.1
+pydub==0.25.1
+Pygments==2.18.0
+pyparsing==3.1.2
+python-dateutil==2.9.0.post0
+python-dotenv==1.0.1
+python-multipart==0.0.9
+pytz==2024.1
 PyYAML==6.0.1
 regex==2024.7.24
 requests==2.32.3
+rich==13.7.1
+ruff==0.5.5
 safetensors==0.4.3
+semantic-version==2.10.0
+shellingham==1.5.4
+six==1.16.0
+sniffio==1.3.1
+starlette==0.37.2
 sympy==1.13.1
 timm==1.0.7
 tokenizers==0.19.1
+tomlkit==0.12.0
 torch==2.4.0
 torchvision==0.19.0
 tqdm==4.66.4
 transformers==4.43.3
+typer==0.12.3
 typing_extensions==4.12.2
+tzdata==2024.1
 urllib3==2.2.2
+uvicorn==0.30.3
+uvloop==0.19.0
+watchfiles==0.22.0
+websockets==11.0.3