File size: 4,456 Bytes
fe8e241 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 | import argparse
import os
from pathlib import Path
import numpy as np
import tensorflow as tf
os.environ.setdefault("TF_FORCE_GPU_ALLOW_GROWTH", "true")
AA_ORDER = ["A", "R", "N", "D", "C", "Q", "E", "G", "H", "I",
"L", "K", "M", "F", "P", "S", "T", "W", "Y", "V", "X", "-"]
def decode_one(img):
arr = np.asarray(img)
arr = arr.reshape(32, 22)
# remove X column, same as README
arr_no_x = np.delete(arr, 20, axis=1)
aa_no_x = AA_ORDER[:20] + ["-"]
aa_idx = np.argmax(arr_no_x, axis=1)
aa = np.array([aa_no_x[i] for i in aa_idx], dtype=object)
gaps = np.where(aa == "-")[0] + 1 # use 1-based position to mimic R logic
if len(gaps) > 0:
gap_first_candidates = gaps[gaps > 1]
gap_last_candidates = gaps[gaps < 32]
if len(gap_first_candidates) > 0 and len(gap_last_candidates) > 0:
gap_first = int(gap_first_candidates[0])
gap_last = int(gap_last_candidates[-1])
if gap_first <= gap_last:
aa[(gap_first - 1):gap_last] = "-"
seq = "".join(aa.tolist()).replace("-", "")
return seq
def generate_one(model_id, n_seq=100, batch_size=20, latent_dim=100, seed=2026):
#model_dir = Path(f"weight/GAN/GAN_model_{model_id}_dcu.keras")
model_dir = Path(f"weight/GAN/GAN_model_{model_id}_dcu")
if not model_dir.exists():
raise FileNotFoundError(f"Missing trained model: {model_dir}")
np.random.seed(seed + model_id)
tf.random.set_seed(seed + model_id)
model = tf.keras.models.load_model(str(model_dir), compile=False)
seqs = []
with tf.device("/GPU:0"):
while len(seqs) < n_seq:
noise = np.random.normal(size=(batch_size, latent_dim)).astype("float32")
fake = model(noise, training=False).numpy()
for i in range(fake.shape[0]):
seqs.append(decode_one(fake[i]))
if len(seqs) >= n_seq:
break
return seqs
def load_group_names():
names = []
for i in range(1, 16):
f = Path(f"model/GAN/seq_encoded_{i:02d}.npz")
if f.exists():
d = np.load(f, allow_pickle=True)
names.append(str(d["name"]))
else:
names.append(f"GAN_model_{i}")
return names
def main():
parser = argparse.ArgumentParser()
parser.add_argument("--model-id", type=int, default=0, help="0 means all models; otherwise 1-15")
parser.add_argument("--n-seq", type=int, default=100)
parser.add_argument("--batch-size", type=int, default=20)
parser.add_argument("--latent-dim", type=int, default=100)
parser.add_argument("--seed", type=int, default=2026)
parser.add_argument("--out-tsv", default="model/GAN/gen_seq_trained_dcu.tsv")
args = parser.parse_args()
group_names = load_group_names()
if args.model_id == 0:
model_ids = range(1, 16)
else:
if args.model_id < 1 or args.model_id > 15:
raise ValueError("--model-id must be 0 or 1-15")
model_ids = [args.model_id]
rows = []
all_seqs = {}
for model_id in model_ids:
group = group_names[model_id - 1]
print(f"\nGenerating from trained model {model_id}: {group}")
seqs = generate_one(
model_id=model_id,
n_seq=args.n_seq,
batch_size=args.batch_size,
latent_dim=args.latent_dim,
seed=args.seed,
)
all_seqs[model_id] = seqs
unique = []
seen = set()
for s in seqs:
if s not in seen:
unique.append(s)
seen.add(s)
print("unique first 10:")
print(unique[:10])
print("n_seq:", len(seqs), "n_unique:", len(unique))
for rank, seq in enumerate(seqs, start=1):
rows.append((model_id, group, rank, seq, len(seq)))
out_path = Path(args.out_tsv)
out_path.parent.mkdir(parents=True, exist_ok=True)
with out_path.open("w") as f:
f.write("model_id\tgroup\trank\taa\tlength\n")
for row in rows:
f.write("\t".join(map(str, row)) + "\n")
np.savez_compressed(
str(out_path).replace(".tsv", ".npz"),
**{f"model_{k:02d}": np.array(v, dtype=object) for k, v in all_seqs.items()}
)
print("\nsaved:", out_path)
print("saved:", str(out_path).replace(".tsv", ".npz"))
print("GAN trained-model generation OK")
if __name__ == "__main__":
main()
|