ChandraPrakashBathula commited on
Commit
2d41719
Β·
verified Β·
1 Parent(s): a36ad62

Create app.py

Browse files
Files changed (1) hide show
  1. app.py +115 -0
app.py ADDED
@@ -0,0 +1,115 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ import json
2
+ from pathlib import Path
3
+
4
+ import numpy as np
5
+ import torch
6
+ import torchvision.transforms as T
7
+ import gradio as gr
8
+ from PIL import Image
9
+ from matplotlib import colormaps
10
+
11
+ from model import SceneCNN, grad_cam
12
+
13
+ ROOT = Path(__file__).parent
14
+
15
+ # ---------- load model ----------
16
+ meta = json.loads((ROOT / "cnn_intel_meta.json").read_text())
17
+ CLASSES = meta["class_names"]
18
+ IMG_SIZE = meta["img_size"]
19
+
20
+ model = SceneCNN(base=meta["base"], num_classes=len(CLASSES))
21
+ model.load_state_dict(torch.load(ROOT / "cnn_intel.pth", map_location="cpu"))
22
+ model.eval()
23
+
24
+ preprocess = T.Compose([
25
+ T.Resize((IMG_SIZE, IMG_SIZE)),
26
+ T.ToTensor(),
27
+ T.Normalize(meta["mean"], meta["std"]),
28
+ ])
29
+
30
+ # ---------- prediction ----------
31
+ def predict(img):
32
+ if img is None:
33
+ return None, None
34
+ img = img.convert("RGB")
35
+ cam, probs = grad_cam(model, preprocess(img))
36
+
37
+ show = 384
38
+ base = np.asarray(img.resize((show, show))) / 255.0
39
+ cam_big = np.asarray(Image.fromarray((cam * 255).astype(np.uint8)).resize((show, show), Image.BILINEAR)) / 255.0
40
+ heat = colormaps["jet"](cam_big)[..., :3]
41
+ overlay = (0.55 * base + 0.45 * heat).clip(0, 1)
42
+
43
+ label = {c: float(p) for c, p in zip(CLASSES, probs)}
44
+ return label, (overlay * 255).astype(np.uint8)
45
+
46
+ # ---------- metrics ----------
47
+ def metrics_markdown():
48
+ p = ROOT / "metrics.json"
49
+ if not p.exists():
50
+ return "_metrics.json not found._"
51
+ m = json.loads(p.read_text())
52
+ out = [
53
+ f"**Test accuracy:** {m['test_accuracy']:.2%}  Β·  "
54
+ f"**Macro F1:** {m['macro_f1']:.3f}  Β·  "
55
+ f"**Best val accuracy:** {m['best_val_accuracy']:.2%}  Β·  "
56
+ f"**Parameters:** {m['params']:,}",
57
+ "",
58
+ "| Class | Precision | Recall | F1 | Test images |",
59
+ "|---|---|---|---|---|",
60
+ ]
61
+ for c, r in m["per_class"].items():
62
+ out.append(f"| {c} | {r['precision']:.3f} | {r['recall']:.3f} | {r['f1-score']:.3f} | {int(r['support'])} |")
63
+ return "\n".join(out)
64
+
65
+ PLOTS = [
66
+ ("10_curves.png", "Training curves"),
67
+ ("11_confusion_matrix.png", "Confusion matrix"),
68
+ ("12_per_class_accuracy.png", "Per-class accuracy"),
69
+ ("13_confidence.png", "Confidence: correct vs wrong"),
70
+ ("14_mistakes.png", "Most confident mistakes"),
71
+ ("15_gradcam.png", "Grad-CAM per class"),
72
+ ("16_gradcam_mistakes.png", "Grad-CAM on mistakes"),
73
+ ("08_feature_maps_after.png", "Feature maps after training"),
74
+ ("09_filters_after.png", "First-layer filters after training"),
75
+ ("04_augmentation.png", "Augmentation"),
76
+ ("01_samples.png", "Dataset samples"),
77
+ ("02_class_distribution.png", "Class distribution"),
78
+ ]
79
+ gallery_items = [(str(ROOT / "images" / f), cap) for f, cap in PLOTS if (ROOT / "images" / f).exists()]
80
+ examples = [[str(p)] for p in sorted((ROOT / "examples").glob("*.jpg"))] if (ROOT / "examples").exists() else []
81
+
82
+ # ---------- UI ----------
83
+ with gr.Blocks(title="Intel Scene CNN", theme=gr.themes.Soft()) as demo:
84
+ gr.Markdown(
85
+ "# Intel Scene Classifier: a CNN built from scratch\n"
86
+ "Upload a photo of a **building, forest, glacier, mountain, sea or street**. "
87
+ "The CNN predicts the scene, and Grad-CAM shows which pixels drove the decision. "
88
+ "No pretrained backbone: 4 conv blocks trained from scratch on ~14k images."
89
+ )
90
+ with gr.Row():
91
+ inp = gr.Image(type="pil", label="Upload a scene", height=384)
92
+ with gr.Column():
93
+ out_label = gr.Label(num_top_classes=6, label="Prediction")
94
+ out_cam = gr.Image(label="Grad-CAM (red = most important)", height=384)
95
+ inp.change(predict, inputs=inp, outputs=[out_label, out_cam])
96
+ if examples:
97
+ gr.Examples(examples=examples, inputs=inp, cache_examples=False)
98
+
99
+ gr.Markdown("> Note: the model always picks one of the 6 classes, even for a photo of a cat.")
100
+
101
+ gr.Markdown("## Test-set metrics (seg_test, 3,000 held-out images)")
102
+ gr.Markdown(metrics_markdown())
103
+
104
+ if gallery_items:
105
+ gr.Markdown("## Training and evaluation plots")
106
+ gr.Gallery(value=gallery_items, columns=2, height="auto", object_fit="contain")
107
+
108
+ gr.Markdown(
109
+ "## Architecture\n"
110
+ "`[Conv3x3-BN-ReLU] x2 β†’ MaxPool β†’ Dropout2d` Γ— 4 blocks "
111
+ f"(channels {meta['base']}β†’{meta['base']*2}β†’{meta['base']*4}β†’{meta['base']*8}) "
112
+ "β†’ Global Avg Pool β†’ Dropout β†’ FC 128 β†’ ReLU β†’ FC 6"
113
+ )
114
+
115
+ demo.launch()