def train_top_model():
# load top model architecture
top_model, _, _ = create_top_model(num_classes=500)
top_model.compile(optimizer=optimizers.Adam(),
loss='categorical_crossentropy',
metrics=['accuracy',metrics.top_k_categorical_accuracy])
best_val_loss = 100
f = open('console_dumps/{}.txt'.format(exp_name),'w')
unpickled_train = pickle.load(open('cache/parts_train.p','rb'))
unpickled_valid = pickle.load(open('cache/parts_validation.p','rb'))
#unpickled_test = pickle.load(open('cache/parts_test.p','rb'))
for i in range(epochs):
time_start = time.time()
train_generator = utils.img_parts_generator(part_file_name, train_data_dir, batch_size=5000, bottleneck_file='bottleneck/bottleneck_60_train.npy', unpickled=unpickled_train)
val_generator = utils.img_parts_generator(part_file_name, validation_data_dir, batch_size=5000, bottleneck_file='bottleneck/bottleneck_60_validation.npy', unpickled=unpickled_valid)
j = 0
train_eval = []
print('Training')
for inp, label in train_generator:
hist = top_model.fit(inp, label, verbose=0, batch_size=400)
res = [hist.history['loss'][0], hist.history['acc'][0]]
train_eval.append(res)
#print("Epoch: {}/{} Batch (train): {}/{} train_l: {:.4f} train_acc: {:.4f}".format(i+1,epochs,j+1,42320/batch_size, res[0], res[1]))
j += 1
# find mean of loss and acc
train_eval = np.mean(train_eval, axis=0)
val_eval = []
j = 0
print('Evaluating validation set')
for inp, label in val_generator:
res = top_model.evaluate(inp, label, verbose=0, batch_size=400)
#print("Epoch: {}/{} Batch (valid): {}/{} val_l: {:.4f} val_acc: {:.4f}".format(i+1,epochs,j+1,3000/batch_size, res[0], res[1]))
val_eval.append(res)
j += 1
if j==5:
break
val_eval = np.mean(val_eval, axis=0)
if val_eval[0] < best_val_loss:
#print('Saving weights')
best_val_loss = val_eval[0]
top_model.save_weights('models/{}_{}_{:.4f}.hdf5'.format(exp_name,i+1,round(best_val_loss)))
time_taken = time.time() - time_start
log = 'Epoch: {}, train_l: {:.4f}, train_a: {:.4f}, val_l: {:.4f}, val_a: {:.4f}, time: {:.4f}\n'.format(i+1,train_eval[0], train_eval[1], val_eval[0],val_eval[1], time_taken)
f.write(log)
print(log)
f.close()
def train_top_model():
# get mapping of label id (0...499) to label string
label_mapping = utils.get_label_mapping_from_file('train_labels.txt')
# load bottlenecks
print('Train')
train_data = np.load(open('bottleneck/bottleneck_features_train.npy', 'rb'))
print(train_data.shape)
train_labels = utils.get_labels_from_file('train_labels.txt')
print(len(train_labels))
print('Validation')
validation_data = np.load(open('bottleneck/bottleneck_features_validation.npy', 'rb'))
print(validation_data.shape)
val_size_per_class = 6
validation_labels = get_fixed_labels(val_size_per_class)
print('Test')
test_data = np.load(open('bottleneck/bottleneck_features_test.npy', 'rb'))
print(test_data.shape)
test_size_per_class = 9
test_labels = get_fixed_labels(test_size_per_class)
epochs = 20
tensorboard_callback = TensorBoard(log_dir='./logs/top_model/', histogram_freq=0, write_graph=True, write_images=False)
checkpoint_callback = ModelCheckpoint('./models/top_model_weights.{epoch:02d}-{val_acc:.2f}.hdf5', monitor='val_acc', verbose=0, save_best_only=True, save_weights_only=False, mode='auto')
# load top model architecture
top_model, x, top_model_inputs = create_top_model()
top_model.compile(optimizer=optimizers.Adam(),
loss='categorical_crossentropy', metrics=['accuracy'])
history_model = top_model.fit(train_data, train_labels,
epochs=epochs,
batch_size=batch_size,
verbose=1,
validation_data=(validation_data, validation_labels),
callbacks = [tensorboard_callback, checkpoint_callback])
pandas.DataFrame(history_model.history).to_csv('./history/top_model.csv')
ev = top_model.evaluate(test_data,test_labels, batch_size=batch_size, verbose=1)
print(ev)
def train_top_model():
exp_name = 'top_cropped'
# load bottlenecks
print('Train')
train_data = np.load(open('bottleneck/cropped_60_train.npy', 'rb'))
print(train_data.shape)
train_labels = utils.get_labels_from_file('train_labels.txt')
print(len(train_labels))
print('Validation')
validation_data = np.load(
open('bottleneck/cropped_60_validation.npy', 'rb'))
print(validation_data.shape)
val_size_per_class = 6
validation_labels = get_fixed_labels(val_size_per_class)
epochs = 20
tensorboard_callback = TensorBoard(log_dir='./logs/' + exp_name + '/',
histogram_freq=0,
write_graph=True,
write_images=False)
checkpoint_callback = ModelCheckpoint('./models/' + exp_name +
'.{epoch:02d}-{val_acc:.2f}.hdf5',
monitor='val_acc',
verbose=0,
save_best_only=True,
save_weights_only=False,
mode='auto')
# load top model architecture
top_model, x, top_model_inputs = create_top_model()
top_model.compile(optimizer=optimizers.Adam(),
loss='categorical_crossentropy',
metrics=['accuracy', metrics.top_k_categorical_accuracy])
history_model = top_model.fit(
train_data,
train_labels,
epochs=epochs,
batch_size=batch_size,
verbose=1,
validation_data=(validation_data, validation_labels),
callbacks=[tensorboard_callback, checkpoint_callback])
def train_top_model():
# load top model architecture
top_model, _, _ = create_top_model(
num_classes=4,
activation=None,
weights='models/v2_top_bb_30_28.0000.hdf5')
top_model.compile(optimizer=optimizers.Adam(),
loss='mean_absolute_error',
metrics=['accuracy'])
print(top_model.summary())
bottlenecks_train = utils.load_bottlenecks(bottleneck_dir +
'bottleneck_60_train.npy')
bottlenecks_valid = utils.load_bottlenecks(bottleneck_dir +
'bottleneck_60_validation.npy')
best_val_loss = 100
f = open('console_dumps/{}.txt'.format(exp_name), 'w')
unpickled_train = pickle.load(open('cache/bb_train.p', 'rb'))
unpickled_valid = pickle.load(open('cache/bb_validation.p', 'rb'))
for i in range(epochs):
time_start = time.time()
train_generator = utils.img_parts_generator(
part_file_name,
'train/',
batch_size=5000,
bottlenecks=bottlenecks_train,
unpickled=unpickled_train,
bb_only=True)
val_generator = utils.img_parts_generator(
part_file_name,
'validation/',
batch_size=5000,
bottlenecks=bottlenecks_valid,
unpickled=unpickled_valid,
bb_only=True)
train_eval = [] # stores metrics of training iterations
# print('Training')
for inp, label in train_generator:
hist = top_model.fit(inp, label, verbose=0, batch_size=400)
res = [hist.history['loss'][0], hist.history['acc'][0]]
train_eval.append(res)
# find mean of loss and acc
train_eval = np.mean(train_eval, axis=0)
val_eval = [] # stores metrics of validation iterations
j = 0
# print('Evaluating validation set')
for inp, label in val_generator:
res = top_model.evaluate(inp, label, verbose=0, batch_size=400)
#print("Epoch: {}/{} Batch (valid): {}/{} val_l: {:.4f} val_acc: {:.4f}".format(i+1,epochs,j+1,3000/batch_size, res[0], res[1]))
val_eval.append(res)
j += 1
#if j==5:
# break
val_eval = np.mean(val_eval, axis=0)
# save weights if current loss beats best loss
if val_eval[0] < best_val_loss:
#print('Saving weights')
best_val_loss = val_eval[0]
top_model.save_weights('models/{}_{}_{:.4f}.hdf5'.format(
exp_name, i + 1, round(best_val_loss)))
time_taken = time.time() - time_start
log = 'Epoch: {}, train_l: {:.4f}, train_a: {:.4f}, val_l: {:.4f}, val_a: {:.4f}, time: {:.4f}\n'.format(
i + 1, train_eval[0], train_eval[1], val_eval[0], val_eval[1],
time_taken)
f.write(log)
print(log)
f.close()