Update app.py

app.py

@@ -1,19 +1,119 @@
+import sys
 import os
 import gradio as gr
 from PIL import Image
 
-os.system("git clone https://github.com/AK391/projected_gan.git")
+os.system("git clone https://github.com/autonomousvision/projected_gan.git")
 
-os.chdir("projected_gan")
+sys.path.append("projected_gan")
 
-os.mkdir("outputs")
 
+"""Generate images using pretrained network pickle."""
 
-def inference(seeds):
-  os.system("python gen_images.py --outdir=./outputs/ --seeds="+str(int(seeds))+" --network=https://s3.eu-central-1.amazonaws.com/avg-projects/projected_gan/models/pokemon.pkl")
-  seeds = int(seeds)
-  image = Image.open(f"./outputs/seed{seeds:04d}.png")
-  return image
+import os
+import re
+from typing import List, Optional, Tuple, Union
+
+import click
+import dnnlib
+import numpy as np
+import PIL.Image
+import torch
+
+import legacy
+
+#----------------------------------------------------------------------------
+
+def parse_range(s: Union[str, List]) -> List[int]:
+    '''Parse a comma separated list of numbers or ranges and return a list of ints.
+    Example: '1,2,5-10' returns [1, 2, 5, 6, 7]
+    '''
+    if isinstance(s, list): return s
+    ranges = []
+    range_re = re.compile(r'^(\d+)-(\d+)$')
+    for p in s.split(','):
+        m = range_re.match(p)
+        if m:
+            ranges.extend(range(int(m.group(1)), int(m.group(2))+1))
+        else:
+            ranges.append(int(p))
+    return ranges
+
+#----------------------------------------------------------------------------
+
+def parse_vec2(s: Union[str, Tuple[float, float]]) -> Tuple[float, float]:
+    '''Parse a floating point 2-vector of syntax 'a,b'.
+    Example:
+        '0,1' returns (0,1)
+    '''
+    if isinstance(s, tuple): return s
+    parts = s.split(',')
+    if len(parts) == 2:
+        return (float(parts[0]), float(parts[1]))
+    raise ValueError(f'cannot parse 2-vector {s}')
+
+#----------------------------------------------------------------------------
+
+def make_transform(translate: Tuple[float,float], angle: float):
+    m = np.eye(3)
+    s = np.sin(angle/360.0*np.pi*2)
+    c = np.cos(angle/360.0*np.pi*2)
+    m[0][0] = c
+    m[0][1] = s
+    m[0][2] = translate[0]
+    m[1][0] = -s
+    m[1][1] = c
+    m[1][2] = translate[1]
+    return m
+
+#----------------------------------------------------------------------------
+
+
+def generate_images(seeds):
+    """Generate images using pretrained network pickle.
+    Examples:
+    \b
+    # Generate an image using pre-trained AFHQv2 model ("Ours" in Figure 1, left).
+    python gen_images.py --outdir=out --trunc=1 --seeds=2 \\
+        --network=https://api.ngc.nvidia.com/v2/models/nvidia/research/stylegan3/versions/1/files/stylegan3-r-afhqv2-512x512.pkl
+    \b
+    # Generate uncurated images with truncation using the MetFaces-U dataset
+    python gen_images.py --outdir=out --trunc=0.7 --seeds=600-605 \\
+        --network=https://api.ngc.nvidia.com/v2/models/nvidia/research/stylegan3/versions/1/files/stylegan3-t-metfacesu-1024x1024.pkl
+    """
+
+    device = torch.device('cuda') if torch.cuda.is_available() else torch.device('cpu')
+    with dnnlib.util.open_url('https://s3.eu-central-1.amazonaws.com/avg-projects/projected_gan/models/pokemon.pkl') as f:
+        G = legacy.load_network_pkl(f)['G_ema'].to(device) # type: ignore
+
+
+    # Labels.
+    label = torch.zeros([1, G.c_dim], device=device)
+
+
+    # Generate images.
+    for seed_idx, seed in enumerate(seeds):
+        print('Generating image for seed %d (%d/%d) ...' % (seed, seed_idx, len(seeds)))
+        z = torch.from_numpy(np.random.RandomState(seed).randn(1, G.z_dim)).to(device).float()
+
+        # Construct an inverse rotation/translation matrix and pass to the generator.  The
+        # generator expects this matrix as an inverse to avoid potentially failing numerical
+        # operations in the network.
+        if hasattr(G.synthesis, 'input'):
+            m = make_transform('0,0', 0)
+            m = np.linalg.inv(m)
+            G.synthesis.input.transform.copy_(torch.from_numpy(m))
+
+        img = G(z, label, truncation_psi=1, noise_mode='const')
+        img = (img.permute(0, 2, 3, 1) * 127.5 + 128).clamp(0, 255).to(torch.uint8)
+        pilimg = PIL.Image.fromarray(img[0].cpu().numpy(), 'RGB')
+    return pilimg
+
+
+def inference(seedin):
+  listseed = [int(seedin)]
+  output = generate_images(listseed)
+  return output
 
 title = "Projected GAN"
 description = "Gradio demo for Projected GANs Converge Faster, Pokemon. To use it, add seed, or click one of the examples to load them. Read more at the links below. We’re getting a lot of traffic from Hacker News so we added 10 cached examples"