test

README.md

@@ -1,13 +1,13 @@
----
-title: IMUFLP
-emoji: 🦀
-colorFrom: yellow
-colorTo: gray
-sdk: gradio
-sdk_version: 4.17.0
-app_file: app.py
-pinned: false
-license: mit
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+---
+title: Test
+emoji: 📈
+colorFrom: blue
+colorTo: pink
+sdk: gradio
+sdk_version: 4.15.0
+app_file: app.py
+pinned: false
+license: mit
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -1,7 +1,29 @@
-import gradio as gr
-
-def greet(name):
-    return "Hello " + name + "!!"
-
-iface = gr.Interface(fn=greet, inputs="text", outputs="text")
-iface.launch()
+import gradio as gr
+import numpy as np
+import torch
+from model import Net
+
+
+model = Net(100, 50, 10)
+model.load_state_dict(torch.load('model.pth'))
+model.eval()
+
+def infer(file_obj):
+    results = ""
+    for file in file_obj:
+        data = np.load(file.name)
+        output = model(torch.from_numpy(data).float()).detach().numpy()
+        results += np.array_str(output) + "\n"
+    return results
+
+with gr.Blocks("Test") as demo:
+    gr.Markdown("## Test")
+    output = gr.Textbox(label="Output")
+    data = gr.UploadButton(
+        label="Upload a .npy",
+        file_count="multiple", 
+        file_types=[".npy"])
+    data.upload(fn=infer, inputs=data, outputs=output)
+
+if __name__ == "__main__":
+    demo.launch()

data.py

@@ -0,0 +1,5 @@
+import numpy as np
+
+data = np.arange(100).reshape(1, 100)
+print(np.array_str(data))
+np.save('data.npy', data)

model.py

@@ -0,0 +1,24 @@
+import torch
+import torch.nn as nn
+import torch.nn.functional as F
+
+
+class Net(nn.Module):
+    def __init__(self, input_size, hidden_size, num_classes):
+        super(Net, self).__init__()
+        self.fc1 = nn.Linear(input_size, hidden_size)
+        self.relu = nn.ReLU()
+        self.fc2 = nn.Linear(hidden_size, num_classes)
+        self.softmax = nn.Softmax(dim=1)
+
+    def forward(self, x):
+        out = self.fc1(x)
+        out = self.relu(out)
+        out = self.fc2(out)
+        out = self.softmax(out)
+        return out
+
+
+if __name__ == '__main__':
+    net = Net(100, 50, 10)
+    torch.save(net.state_dict(), 'model.pth')

requirements.txt

@@ -0,0 +1,2 @@
+torch >= 2.1.0
+numpy >= 1.26.1

test_model.py

@@ -0,0 +1,11 @@
+import torch
+import numpy as np
+
+from model import Net
+
+a = np.arange(100).reshape(1, 100)
+model = Net(100, 50, 10)
+model.load_state_dict(torch.load('model.pth'))
+model.eval()
+output = model(torch.from_numpy(a).float())
+print(output)