File size: 3,006 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 | import os
import numpy as np
import tensorflow as tf
os.environ.setdefault("TF_FORCE_GPU_ALLOW_GROWTH", "true")
def build_model():
model = tf.keras.Sequential([
tf.keras.layers.Conv2D(64, (3, 3), activation="relu", input_shape=(36, 22, 1), padding="same"),
tf.keras.layers.Dropout(0.5),
tf.keras.layers.MaxPooling2D((2, 2), padding="same"),
tf.keras.layers.Conv2D(32, (3, 4), activation="relu", padding="same"),
tf.keras.layers.Dropout(0.4),
tf.keras.layers.MaxPooling2D((2, 2), padding="same"),
tf.keras.layers.Conv2D(32, (4, 4), activation="relu", padding="same"),
tf.keras.layers.Dropout(0.3),
tf.keras.layers.Flatten(),
tf.keras.layers.Dense(64, activation="relu"),
tf.keras.layers.Dropout(0.4),
tf.keras.layers.Dense(2, activation="softmax"),
])
model.compile(
loss="categorical_crossentropy",
optimizer="adam",
metrics=["accuracy"],
)
return model
def mcc_score(y_pred, y_real):
y_pred = y_pred.astype(int)
y_real = y_real.astype(int)
tp = float(np.sum((y_pred == 1) & (y_real == 1)))
tn = float(np.sum((y_pred == 0) & (y_real == 0)))
fp = float(np.sum((y_pred == 1) & (y_real == 0)))
fn = float(np.sum((y_pred == 0) & (y_real == 1)))
denom = np.sqrt((tp + fp) * (tp + fn) * (tn + fp) * (tn + fn))
return np.nan if denom == 0 else (tp * tn - fp * fn) / denom
def train_one(name, data_file, out_dir):
print(f"\n==== training {name} ====")
data = np.load(data_file)
x_train = data["x_train"].astype("float32")
y_train = data["y_train"].astype("float32")
x_test = data["x_test"].astype("float32")
y_test = data["y_test"].astype("float32")
print("x_train", x_train.shape, "y_train", y_train.shape)
print("x_test ", x_test.shape, "y_test ", y_test.shape)
print("GPUs:", tf.config.list_physical_devices("GPU"))
with tf.device("/GPU:0"):
model = build_model()
model.fit(
x_train,
y_train,
epochs=30,
batch_size=50,
validation_split=0.2,
verbose=2,
)
prob = model.predict(x_test, batch_size=128, verbose=0)
y_real = np.argmax(y_test, axis=1)
y_pred = np.argmax(prob, axis=1)
acc = float(np.mean(y_real == y_pred))
mcc = float(mcc_score(y_pred, y_real))
print(f"\n{name} accuracy: {acc:.4f}")
print(f"{name} mcc: {mcc:.4f}")
print("confusion matrix rows=real cols=pred")
cm = np.zeros((2, 2), dtype=int)
for r, p in zip(y_real, y_pred):
cm[r, p] += 1
print(cm)
model.save(out_dir)
#model.save(out_dir + ".keras")
np.savez_compressed(out_dir + "_eval.npz", prob=prob, y_real=y_real, y_pred=y_pred, cm=cm, acc=acc, mcc=mcc)
print("saved", out_dir)
train_one("CTLA-4", "model/CNN/c1_data.npz", "weight/CNN/model_c1_dcu")
train_one("PD-1", "model/CNN/p1_data.npz", "weight/CNN/model_p1_dcu")
print("\nCNN DCU training OK")
|