add app.py

app.py

@@ -0,0 +1,32 @@
+import gradio as gr
+import torch
+from PIL import Image
+from torchvision import transforms
+
+model = torch.hub.load('nicolalandro/ntsnet-cub200', 'ntsnet', pretrained=True,
+                       **{'topN': 6, 'device': 'cpu', 'num_classes': 200}).eval()
+transform_test = transforms.Compose([
+    transforms.Resize((600, 600), Image.BILINEAR),
+    transforms.CenterCrop((448, 448)),
+    transforms.ToTensor(),
+    transforms.Normalize((0.485, 0.456, 0.406), (0.229, 0.224, 0.225)),
+])
+
+
+def predict(inp):
+    inp = Image.fromarray(inp.astype('uint8'), 'RGB')
+    scaled_img = transform_test(inp)
+    torch_images = scaled_img.unsqueeze(0)
+
+    with torch.no_grad():
+        top_n_coordinates, concat_out, raw_logits, concat_logits, part_logits, top_n_index, top_n_prob = model(
+            torch_images)
+    pred = torch.nn.functional.softmax(concat_logits)
+    return {model.bird_classes[i]: float(p) for i, p in enumerate(pred.squeeze(0))}
+
+
+inputs = gr.inputs.Image()
+outputs = gr.outputs.Label(num_top_classes=10)
+gr.Interface(fn=predict, inputs=inputs, outputs=outputs,
+             title="200 Bird Species Classifications with NTS-NET (From CUB 200)").launch()
+

requirements.txt

@@ -0,0 +1,42 @@
+analytics-python==1.4.0
+backoff==1.10.0
+bcrypt==3.2.0
+certifi==2021.10.8
+cffi==1.15.0
+charset-normalizer==2.0.7
+click==8.0.3
+cryptography==35.0.0
+cycler==0.11.0
+ffmpy==0.3.0
+Flask==2.0.2
+Flask-CacheBuster==1.0.0
+Flask-Cors==3.0.10
+Flask-Login==0.5.0
+gradio==2.4.1
+idna==3.3
+itsdangerous==2.0.1
+Jinja2==3.0.2
+kiwisolver==1.3.2
+markdown2==2.4.1
+MarkupSafe==2.0.1
+matplotlib==3.4.3
+monotonic==1.6
+numpy==1.21.3
+pandas==1.3.4
+paramiko==2.8.0
+Pillow==8.4.0
+pkg_resources==0.0.0
+pycparser==2.20
+pycryptodome==3.11.0
+pydub==0.25.1
+PyNaCl==1.4.0
+pyparsing==3.0.3
+python-dateutil==2.8.2
+pytz==2021.3
+requests==2.26.0
+six==1.16.0
+torch==1.10.0
+torchvision==0.11.1
+typing-extensions==3.10.0.2
+urllib3==1.26.7
+Werkzeug==2.0.2