layer.trainable = False
# compile our model (this needs to be done after our setting our
# layers to being non-trainable
print("[INFO] compiling model...")
opt = SGD(lr=config.MIN_LR, momentum=0.9)
model.compile(loss="categorical_crossentropy", optimizer=opt,
metrics=["accuracy"])
# check to see if we are attempting to find an optimal learning rate
# before training for the full number of epochs
if args["lr_find"] > 0:
# initialize the learning rate finder and then train with learning
# rates ranging from 1e-10 to 1e+1
print("[INFO] finding learning rate...")
lrf = LearningRateFinder(model)
lrf.find(
aug.flow(trainX, trainY, batch_size=config.BATCH_SIZE),
1e-10, 1e+1,
stepsPerEpoch=np.ceil((trainX.shape[0] / float(config.BATCH_SIZE))),
epochs=20,
batchSize=config.BATCH_SIZE)
# plot the loss for the various learning rates and save the
# resulting plot to disk
lrf.plot_loss()
plt.savefig(config.LRFIND_PLOT_PATH)
# gracefully exit the script so we can adjust our learning rates
# in the config and then train the network for our full set of
# epochs
precision = true_positives / (predicted_positives + K.epsilon())
return precision
def f1(y_true, y_pred):
precision = precision_m(y_true, y_pred)
recall = recall_m(y_true, y_pred)
return 2 * ((precision * recall) / (precision + recall + K.epsilon()))
# ## Compiled model using Adam optimizer and computed accuracy and f1 score
rate = 0
if rate != 1:
print("[INFO] finding learning rate...")
lrf = LearningRateFinder(model)
lrf.find(train_datagen.flow(trainX, trainY, batch_size=config.BATCH_SIZE),
1e-15,
1e+1,
epochs=8,
stepsPerEpoch=np.ceil((len(trainX) / float(config.BATCH_SIZE))),
batchSize=config.BATCH_SIZE)
# plot the loss for the various learning rates and save the
# resulting plot to disk
lrf.plot_loss()
plt.savefig(config.LRFIND_PLOT_PATH)
print("[INFO] learning rate finder complete")
print("[INFO] examine plot and adjust learning rates before training")
sys.exit(0)