In [1]:
import os, random, glob, pickle, collections, math, json, time
import numpy as np
import pandas as pd
from __future__ import division
from __future__ import print_function
from PIL import Image
from sklearn.model_selection import train_test_split
from sklearn.metrics import log_loss
from sklearn.preprocessing import LabelEncoder
import matplotlib.pyplot as plt
%matplotlib inline
from keras.models import Sequential, Model, load_model
from keras.layers import GlobalAveragePooling2D, Flatten, Dropout, Dense, LeakyReLU
from keras.optimizers import Adam
from keras.callbacks import EarlyStopping, ModelCheckpoint, ReduceLROnPlateau, TensorBoard
from keras.preprocessing.image import ImageDataGenerator
from keras.utils import np_utils
from keras.preprocessing import image
from keras import backend as K
K.set_image_dim_ordering('tf')
In [2]:
TRAIN_DIR = '../data/train/'
TEST_DIR = '../RFCN/JPEGImages/'
TRAIN_CROP_DIR = '../data/train_crop/'
TEST_CROP_DIR = '../data/test_stg1_crop/'
RFCN_MODEL = 'resnet101_rfcn_ohem_iter_30000'
CROP_MODEL = 'resnet50_FT38_Classifier_Rep6'
if not os.path.exists('./' + CROP_MODEL):
os.mkdir('./' + CROP_MODEL)
CHECKPOINT_DIR = './' + CROP_MODEL + '/checkpoint/'
if not os.path.exists(CHECKPOINT_DIR):
os.mkdir(CHECKPOINT_DIR)
LOG_DIR = './' + CROP_MODEL + '/log/'
if not os.path.exists(LOG_DIR):
os.mkdir(LOG_DIR)
OUTPUT_DIR = './' + CROP_MODEL + '/output/'
if not os.path.exists(OUTPUT_DIR):
os.mkdir(OUTPUT_DIR)
FISH_CLASSES = ['NoF', 'ALB', 'BET', 'DOL', 'LAG', 'OTHER', 'SHARK', 'YFT']
FISH_CLASSES_2 = ['ALB', 'BET', 'DOL', 'LAG', 'NoF', 'OTHER', 'SHARK', 'YFT']
# CROP_CLASSES=FISH_CLASSES[:]
# CROP_CLASSES.remove('NoF')
CONF_THRESH = 0.8
ROWS = 224
COLS = 224
BATCHSIZE = 128
LEARNINGRATE = 1e-4
le = LabelEncoder()
le.fit(FISH_CLASSES)
print(le.transform(FISH_CLASSES))
def imagewise_center(x):
mean = np.mean(x, axis=0, keepdims=True)
x_centered = x - mean
return x_centered
def channelwise_center(x):
mean = np.mean(x, axis=0, keepdims=True)
mean = np.mean(mean, axis=(1,2), keepdims=True)
x_centered = x - mean
return x_centered
def imagewise_mean(x):
mean = np.mean(x, axis=0)
return mean
def channelwise_mean(x):
mean = np.mean(x, axis=0)
mean = np.mean(mean, axis=(0,1))
return mean
def preprocess_imagewise(x, imagewise_mean):
#resnet50 image preprocessing
# 'RGB'->'BGR'
# x = x[:, :, ::-1]
# x /= 255.
x -= imagewise_mean
return x
def preprocess_channelwise(x, channelwise_mean):
#resnet50 image preprocessing
# 'RGB'->'BGR'
# x = x[:, :, ::-1]
# x /= 255.
x -= np.reshape(channelwise_mean, [1, 1, 3])
return x
def load_img(path, bbox, target_size=None):
img = Image.open(path)
# img = img.convert('RGB')
cropped = img.crop((bbox[0],bbox[1],bbox[2],bbox[3]))
width_cropped, height_cropped = cropped.size
if height_cropped > width_cropped: cropped = cropped.transpose(method=2)
image_name = 'temp_{:f}.jpg'.format(time.time())
cropped.save(image_name)
cropped = Image.open(image_name)
if target_size:
cropped = cropped.resize((target_size[1], target_size[0]), Image.BILINEAR)
os.remove(image_name)
return cropped
def get_best_model(checkpoint_dir = CHECKPOINT_DIR):
files = glob.glob(checkpoint_dir+'*')
val_losses = [float(f.split('-')[-1][:-5]) for f in files]
index = val_losses.index(min(val_losses))
print('Loading model from checkpoint file ' + files[index])
model = load_model(files[index])
model_name = files[index].split('/')[-1]
print('Loading model Done!')
return (model, model_name)
def data_from_df(df):
X = np.ndarray((df.shape[0], ROWS, COLS, 3), dtype=np.uint8)
y = np.zeros((df.shape[0], len(FISH_CLASSES)), dtype=K.floatx())
i = 0
for index,row in df.iterrows():
image_file = row['image_file']
fish = row['crop_class']
bbox = [row['xmin'],row['ymin'],row['xmax'],row['ymax']]
cropped = load_img(TEST_DIR+image_file,bbox,target_size=(ROWS,COLS))
X[i] = np.asarray(cropped)
y[i,FISH_CLASSES.index(fish)] = 1
i += 1
return (X, y)
def data_load(name):
file_name = 'data_'+name+'_{}_{}.pickle'.format(ROWS, COLS)
if os.path.exists(OUTPUT_DIR+file_name):
print ('Loading from file '+file_name)
with open(OUTPUT_DIR+file_name, 'rb') as f:
data = pickle.load(f)
X = data['X']
y = data['y']
else:
print ('Generating file '+file_name)
if name=='train' or name=='valid':
df = GTbbox_df[GTbbox_df['split']==name]
elif name=='all':
df = GTbbox_df
else:
print('Invalid name '+name)
X, y = data_from_df(df)
data = {'X': X,'y': y}
with open(OUTPUT_DIR+file_name, 'wb') as f:
pickle.dump(data, f)
X = X.astype(np.float32)
X /= 255.
return (X, y)
In [5]:
#Loading data
import pickle
def read_image(src):
"""Read and resize individual images"""
im = Image.open(src)
im = im.resize((COLS, ROWS), Image.BILINEAR)
im = np.asarray(im)
return im
if os.path.exists(OUTPUT_DIR+'data_train_BBCrop_{}_{}.pickle'.format(ROWS, COLS)):
print ('Exist data_train_BBCrop_{}_{}.pickle. Loading data from file.'.format(ROWS, COLS))
with open(OUTPUT_DIR+'data_train_BBCrop_{}_{}.pickle'.format(ROWS, COLS), 'rb') as f:
data_train = pickle.load(f)
X_train_crop = data_train['X_train_crop']
y_train_crop = data_train['y_train_crop']
train_crop_files = data_train['train_crop_files']
class_weight = data_train['class_weight']
else:
print ('Loading data from original images. Generating data_train_BBCrop_{}_{}.pickle.'.format(ROWS, COLS))
y_train_crop = []
train_crop_files = []
for fish in FISH_CLASSES:
fish_dir = TRAIN_CROP_DIR+'{}'.format(fish)
fish_files = [fish+'/'+im for im in os.listdir(fish_dir)]
train_crop_files.extend(fish_files)
y_fish = np.tile(fish, len(fish_files))
y_train_crop.extend(y_fish)
y_train_crop = np.array(y_train_crop)
X_train_crop = np.ndarray((len(train_crop_files), ROWS, COLS, 3), dtype=np.uint8)
for i, im in enumerate(train_crop_files):
X_train_crop[i] = read_image(TRAIN_CROP_DIR+im)
if i%1000 == 0: print('Processed {} of {}'.format(i, len(train_crop_files)))
# class_weight
y_train_crop = le.transform(y_train_crop)
class_weight = dict(collections.Counter(y_train_crop))
ref = max(class_weight.values())
for key,value in class_weight.items():
class_weight[key] = ref/value
# One Hot Encoding Labels
y_train_crop = np_utils.to_categorical(y_train_crop)
train_crop_files = [file.split('/')[-1] for file in train_crop_files]
#save data to file
data_train = {'X_train_crop': X_train_crop,'y_train_crop': y_train_crop,'train_crop_files': train_crop_files,'class_weight':class_weight}
with open(OUTPUT_DIR+'data_train_BBCrop_{}_{}.pickle'.format(ROWS, COLS), 'wb') as f:
pickle.dump(data_train, f)
#rescale
print('Loading data done.')
X_train_crop = X_train_crop.astype(np.float32)
print('Convert to float32 done.')
X_train_crop /= 255.
print('Rescale by 255 done.')
#traing stg1 and stg2 and resume should have the same train test split!!! Remenber to set the random_state!
X_train, X_valid, y_train, y_valid = train_test_split(X_train_crop, y_train_crop, test_size=0.2, random_state=1986, stratify=y_train_crop)
X_all = X_train_crop
y_all = y_train_crop
In [6]:
#data preprocessing
train_datagen = ImageDataGenerator(
featurewise_center=True,
rotation_range=180,
shear_range=0.2,
zoom_range=0.1,
width_shift_range=0.1,
height_shift_range=0.1,
horizontal_flip=True,
vertical_flip=True)
train_datagen.fit(X_train)
train_generator = train_datagen.flow(X_train, y_train, batch_size=BATCHSIZE, shuffle=True, seed=None)
valid_datagen = ImageDataGenerator(featurewise_center=True)
valid_datagen.fit(X_valid)
valid_generator = valid_datagen.flow(X_valid, y_valid, batch_size=BATCHSIZE, shuffle=True, seed=None)
In [10]:
#callbacks
early_stopping = EarlyStopping(monitor='val_loss', min_delta=0, patience=25, verbose=1, mode='auto')
model_checkpoint = ModelCheckpoint(filepath=CHECKPOINT_DIR+'weights.{epoch:03d}-{val_loss:.4f}.hdf5', monitor='val_loss', verbose=1, save_best_only=True, save_weights_only=False, mode='auto')
learningrate_schedule = ReduceLROnPlateau(monitor='val_loss', factor=0.1, patience=10, verbose=1, mode='auto', epsilon=0.001, cooldown=0, min_lr=0)
tensorboard = TensorBoard(log_dir=LOG_DIR, histogram_freq=0, write_graph=False, write_images=True)
In [ ]:
#Resnet50
#top layer training
from keras.applications.resnet50 import ResNet50
base_model = ResNet50(weights='imagenet', include_top=False)
x = base_model.output
x = GlobalAveragePooling2D()(x)
# x = Flatten()(x)
# x = Dense(256)(x)
# x = LeakyReLU(alpha=0.33)(x)
# x = Dropout(0.5)(x)
predictions = Dense(len(FISH_CLASSES), init='glorot_normal', activation='softmax')(x)
model = Model(input=base_model.input, output=predictions)
# first: train only the top layers (which were randomly initialized)
for layer in base_model.layers:
layer.trainable = False
# compile the model (should be done *after* setting layers to non-trainable)
optimizer = Adam(lr=LEARNINGRATE)
model.compile(optimizer=optimizer, loss='categorical_crossentropy', metrics=['accuracy'])
# train the model on the new data for a few epochs
model.fit_generator(train_generator, samples_per_epoch=len(X_train), nb_epoch=30, verbose=1,
callbacks=[early_stopping, model_checkpoint, learningrate_schedule, tensorboard],
validation_data=valid_generator, nb_val_samples=len(X_valid),
class_weight=class_weight, nb_worker=3, pickle_safe=True)
In [ ]:
### Resnet50
# fine tuning
# 164 conv5c+top
# 142 conv5+top
# 80 conv4+conv5+top
# 38 conv3+conv4+conv5+top
start_layer = 38
model, model_name = get_best_model()
# print('Loading model from weights.004-0.0565.hdf5')
# model = load_model(CHECHPOINT_DIR+'weights.004-0.0565.hdf5')
for layer in model.layers[:start_layer]:
layer.trainable = False
for layer in model.layers[start_layer:]:
layer.trainable = True
# we need to recompile the model for these modifications to take effect
# we use SGD with a low learning rate
optimizer = Adam(lr=1e-5)
model.compile(optimizer=optimizer, loss='categorical_crossentropy', metrics=['accuracy'])
model.fit_generator(train_generator, samples_per_epoch=len(X_train), nb_epoch=300, verbose=1,
callbacks=[early_stopping, model_checkpoint, learningrate_schedule, tensorboard],
validation_data=valid_generator, nb_val_samples=len(X_valid),
class_weight=class_weight, nb_worker=3, pickle_safe=True, initial_epoch=26)
In [9]:
#resume training
# model, model_name = get_best_model()
model = load_model(CHECKPOINT_DIR + 'weights.073-0.0472.hdf5')
model_name = 'weights.073-0.0472.hdf5'
print('model_name', model_name)
# #try increasing learningrate
# optimizer = Adam(lr=1e-4)
# model.compile(optimizer=optimizer, loss='categorical_crossentropy', metrics=['accuracy'])
model.fit_generator(train_generator, samples_per_epoch=len(X_train), nb_epoch=300, verbose=1,
callbacks=[early_stopping, model_checkpoint, learningrate_schedule, tensorboard],
validation_data=valid_generator, nb_val_samples=len(X_valid),
class_weight=class_weight, nb_worker=3, pickle_safe=True, initial_epoch=74)
In [11]:
#test prepare
# test_model, test_model_name = get_best_model()
test_model = load_model(CHECKPOINT_DIR + 'weights.073-0.0472.hdf5')
test_model_name = 'weights.073-0.0472.hdf5'
print('model_name', model_name)
def test_generator(df, mean, datagen = None, batch_size = BATCHSIZE):
n = df.shape[0]
batch_index = 0
while 1:
current_index = batch_index * batch_size
if n >= current_index + batch_size:
current_batch_size = batch_size
batch_index += 1
else:
current_batch_size = n - current_index
batch_index = 0
batch_df = df[current_index:current_index+current_batch_size]
batch_x = np.zeros((batch_df.shape[0], ROWS, COLS, 3), dtype=K.floatx())
i = 0
for index,row in batch_df.iterrows():
image_file = row['image_file']
bbox = [row['xmin'],row['ymin'],row['xmax'],row['ymax']]
cropped = load_img(TEST_DIR+image_file,bbox,target_size=(ROWS,COLS))
x = np.asarray(cropped, dtype=K.floatx())
x /= 255.
if datagen is not None: x = datagen.random_transform(x)
x = preprocess_imagewise(x, mean)
batch_x[i] = x
i += 1
if batch_index%50 == 0: print('batch_index', batch_index)
yield(batch_x)
test_aug_datagen = ImageDataGenerator(
rotation_range=180,
shear_range=0.2,
zoom_range=0.1,
width_shift_range=0.1,
height_shift_range=0.1,
horizontal_flip=True,
vertical_flip=True)
In [12]:
#valid
# print(test_model.evaluate(X_valid-imagewise_mean(X_train), y_valid, batch_size=BATCHSIZE, verbose=1))
valid_pred = test_model.predict(X_valid-imagewise_mean(X_train), batch_size=BATCHSIZE, verbose=1)
valid_pred_df = pd.DataFrame(valid_pred, columns=FISH_CLASSES_2)
y_valid_fish = []
for i in range(y_valid.shape[0]):
index = np.argmax(y_valid[i,:])
y_valid_fish.append(FISH_CLASSES_2[index])
valid_pred_df['crop_class'] = pd.Series(y_valid_fish)
valid_pred_df['logloss'] = valid_pred_df.apply(lambda row: -math.log(row[row['crop_class']]), axis=1)
for fish in FISH_CLASSES:
valid_pred_df[fish+'_woNoF'] = valid_pred_df.apply(lambda row: row[fish]/(1-row['NoF']+K.epsilon()) if fish!='NoF' else np.inf , axis=1)
valid_pred_df['logloss_woNoF'] = valid_pred_df.apply(lambda row: -math.log(row[row['crop_class']+'_woNoF']), axis=1)
print('valid loss:', valid_pred_df['logloss'].mean())
print('valid_woNoF loss:', valid_pred_df[valid_pred_df['crop_class']!='NoF']['logloss_woNoF'].mean())
print(valid_pred_df[valid_pred_df['crop_class']!='NoF'].groupby(['crop_class'])['logloss_woNoF'].mean())
crop_valid_woNoF_logloss = valid_pred_df[valid_pred_df['crop_class']!='NoF']['logloss_woNoF'].mean()
print('crop_valid_woNoF_logloss:', crop_valid_woNoF_logloss)
In [13]:
#train
# print(test_model.evaluate(X_train-imagewise_mean(X_train), y_train, batch_size=BATCHSIZE, verbose=1))
train_pred = test_model.predict(X_train-imagewise_mean(X_train), batch_size=BATCHSIZE, verbose=1)
train_pred_df = pd.DataFrame(train_pred, columns=FISH_CLASSES_2)
y_train_fish = []
for i in range(y_train.shape[0]):
index = np.argmax(y_train[i,:])
y_train_fish.append(FISH_CLASSES_2[index])
train_pred_df['crop_class'] = pd.Series(y_train_fish)
train_pred_df['logloss'] = train_pred_df.apply(lambda row: -math.log(row[row['crop_class']]), axis=1)
for fish in FISH_CLASSES:
train_pred_df[fish+'_woNoF'] = train_pred_df.apply(lambda row: row[fish]/(1-row['NoF']+K.epsilon()) if fish!='NoF' else np.inf , axis=1)
train_pred_df['logloss_woNoF'] = train_pred_df.apply(lambda row: -math.log(row[row['crop_class']+'_woNoF']), axis=1)
print('train loss:', train_pred_df['logloss'].mean())
print('train_woNoF loss:', train_pred_df[train_pred_df['crop_class']!='NoF']['logloss_woNoF'].mean())
print(train_pred_df[train_pred_df['crop_class']!='NoF'].groupby(['crop_class'])['logloss_woNoF'].mean())
In [15]:
#all
# print(test_model.evaluate(X_all-imagewise_mean(X_train), y_all, batch_size=BATCHSIZE, verbose=1))
all_pred = test_model.predict(X_all-imagewise_mean(X_train), batch_size=BATCHSIZE, verbose=1)
all_pred_df = pd.DataFrame(all_pred, columns=FISH_CLASSES_2)
y_all_fish = []
for i in range(y_all.shape[0]):
index = np.argmax(y_all[i,:])
y_all_fish.append(FISH_CLASSES_2[index])
all_pred_df['crop_class'] = pd.Series(y_all_fish)
all_pred_df['logloss'] = all_pred_df.apply(lambda row: -math.log(row[row['crop_class']]), axis=1)
for fish in FISH_CLASSES:
all_pred_df[fish+'_woNoF'] = all_pred_df.apply(lambda row: row[fish]/(1-row['NoF']+K.epsilon()) if fish!='NoF' else np.inf , axis=1)
all_pred_df['logloss_woNoF'] = all_pred_df.apply(lambda row: -math.log(row[row['crop_class']+'_woNoF']), axis=1)
print('all loss:', all_pred_df['logloss'].mean())
print(all_pred_df.groupby(['crop_class'])['logloss'].mean())
print('all_woNoF loss:', all_pred_df[all_pred_df['crop_class']!='NoF']['logloss_woNoF'].mean())
print(all_pred_df[all_pred_df['crop_class']!='NoF'].groupby(['crop_class'])['logloss_woNoF'].mean())
In [16]:
# RFCNbbox_RFCNpred_df = ['image_class','image_file','crop_index','xmin','ymin','xmax','ymax',
# 'NoF_RFCN', 'ALB_RFCN', 'BET_RFCN', 'DOL_RFCN',
# 'LAG_RFCN', 'OTHER_RFCN', 'SHARK_RFCN', 'YFT_RFCN']
# select fish_conf >= CONF_THRESH
file_name = 'RFCNbbox_RFCNpred_df_conf{:.2f}.pickle'.format(CONF_THRESH)
if os.path.exists(OUTPUT_DIR+file_name):
print ('Loading from file '+file_name)
RFCNbbox_RFCNpred_df = pd.read_pickle(OUTPUT_DIR+file_name)
else:
print ('Generating file '+file_name)
RFCNbbox_RFCNpred_df = pd.DataFrame(columns=['image_class','image_file','crop_index','xmin','ymin','xmax','ymax',
'NoF_RFCN', 'ALB_RFCN', 'BET_RFCN', 'DOL_RFCN',
'LAG_RFCN', 'OTHER_RFCN', 'SHARK_RFCN', 'YFT_RFCN'])
with open('../data/RFCN_detections/detections_full_AGNOSTICnms_'+RFCN_MODEL+'.pkl','rb') as f:
detections_full_AGNOSTICnms = pickle.load(f, encoding='latin1')
with open("../RFCN/ImageSets/Main/test.txt","r") as f:
test_files = f.readlines()
with open("../RFCN/ImageSets/Main/train_test.txt","r") as f:
train_file_labels = f.readlines()
assert len(detections_full_AGNOSTICnms) == len(test_files)
count = np.zeros(len(detections_full_AGNOSTICnms))
for im in range(len(detections_full_AGNOSTICnms)):
if im%1000 == 0: print(im)
basename = test_files[im][:9]
if im<1000:
image_class = '--'
else:
for i in range(len(train_file_labels)):
if train_file_labels[i][:9] == basename:
image_class = train_file_labels[i][10:-1]
break
image = Image.open(TEST_DIR+'/'+basename+'.jpg')
width_image, height_image = image.size
bboxes = []
detects_im = detections_full_AGNOSTICnms[im]
for i in range(len(detects_im)):
if np.sum(detects_im[i,5:]) >= CONF_THRESH:
# if np.max(detects_im[i,5:]) >= CONF_THRESH:
bboxes.append(detects_im[i,:])
count[im] = len(bboxes)
if len(bboxes) == 0:
ind = np.argmax(np.sum(detects_im[:,5:], axis=1))
bboxes.append(detects_im[ind,:])
bboxes = np.asarray(bboxes)
for j in range(len(bboxes)):
bbox = bboxes[j]
xmin = bbox[0]
ymin = bbox[1]
xmax = bbox[2]
ymax = bbox[3]
assert max(xmin,0)<min(xmax,width_image)
assert max(ymin,0)<min(ymax,height_image)
RFCNbbox_RFCNpred_df.loc[len(RFCNbbox_RFCNpred_df)]=[image_class,basename+'.jpg',j,max(xmin,0),max(ymin,0),
min(xmax,width_image),min(ymax,height_image),
bbox[4],bbox[5],bbox[6],bbox[7],bbox[8],bbox[9],bbox[10],bbox[11]]
RFCNbbox_RFCNpred_df.to_pickle(OUTPUT_DIR+file_name)
In [17]:
# RFCNbbox_RFCNpred_CROPpred_HYBRIDpred_df = ['image_class', 'image_file','crop_index','xmin','ymin','xmax','ymax',
# 'NoF_RFCN', 'ALB_RFCN', 'BET_RFCN', 'DOL_RFCN',
# 'LAG_RFCN', 'OTHER_RFCN', 'SHARK_RFCN', 'YFT_RFCN',
# 'NoF_CROP', 'ALB_CROP', 'BET_CROP', 'DOL_CROP',
# 'LAG_CROP', 'OTHER_CROP', 'SHARK_CROP', 'YFT_CROP',
# 'NoF', 'ALB', 'BET', 'DOL', 'LAG', 'OTHER', 'SHARK', 'YFT']
file_name = 'RFCNbbox_RFCNpred_CROPpred_HYBRIDpred_df_'+test_model_name+'_.pickle'
if os.path.exists(OUTPUT_DIR+file_name):
print ('Loading from file '+file_name)
RFCNbbox_RFCNpred_CROPpred_HYBRIDpred_df = pd.read_pickle(OUTPUT_DIR+file_name)
else:
print ('Generating file '+file_name)
nb_augmentation = 1
if nb_augmentation ==1:
test_preds = test_model.predict_generator(test_generator(df=RFCNbbox_RFCNpred_df, mean=imagewise_mean(X_train)),
val_samples=RFCNbbox_RFCNpred_df.shape[0], nb_worker=1, pickle_safe=False)
else:
test_preds = np.zeros((RFCNbbox_RFCNpred_df.shape[0], len(FISH_CLASSES)), dtype=K.floatx())
for idx in range(nb_augmentation):
print('{}th augmentation for testing ...'.format(idx+1))
test_preds += test_model.predict_generator(test_generator(df=RFCNbbox_RFCNpred_df, mean=imagewise_mean(X_train), datagen=test_aug_datagen),
val_samples=RFCNbbox_RFCNpred_df.shape[0], nb_worker=1, pickle_safe=False)
test_preds /= nb_augmentation
CROPpred_df = pd.DataFrame(test_preds, columns=['ALB_CROP', 'BET_CROP', 'DOL_CROP', 'LAG_CROP', 'NoF_CROP', 'OTHER_CROP', 'SHARK_CROP', 'YFT_CROP'])
RFCNbbox_RFCNpred_CROPpred_HYBRIDpred_df = pd.concat([RFCNbbox_RFCNpred_df,CROPpred_df], axis=1)
RFCNbbox_RFCNpred_CROPpred_HYBRIDpred_df['NoF'] = RFCNbbox_RFCNpred_CROPpred_HYBRIDpred_df['NoF_RFCN']
for fish in ['ALB', 'BET', 'DOL', 'LAG', 'OTHER', 'SHARK', 'YFT']:
RFCNbbox_RFCNpred_CROPpred_HYBRIDpred_df[fish] = RFCNbbox_RFCNpred_CROPpred_HYBRIDpred_df.apply(lambda row: (1-row['NoF_RFCN'])*row[fish+'_CROP']/(1-row['NoF_CROP']+K.epsilon()), axis=1)
# for fish in FISH_CLASSES:
# RFCNbbox_RFCNpred_CROPpred_HYBRIDpred_df[fish] = RFCNbbox_RFCNpred_CROPpred_HYBRIDpred_df[fish+'_CROP']
RFCNbbox_RFCNpred_CROPpred_HYBRIDpred_df.to_pickle(OUTPUT_DIR+file_name)
print('Done!')
In [18]:
# clsMaxAve and hybrid RFCNpred&CROPpred such that RFCNpred for NoF and CROPpred for fish
# test_pred_df = ['logloss','image_class','image_file','NoF', 'ALB', 'BET', 'DOL', 'LAG', 'OTHER', 'SHARK', 'YFT']
# RFCNbbox_RFCNpred_CROPpred_HYBRIDpred_df = ['image_class', 'image_file','crop_index','xmin','ymin','xmax','ymax',
# 'NoF_RFCN', 'ALB_RFCN', 'BET_RFCN', 'DOL_RFCN',
# 'LAG_RFCN', 'OTHER_RFCN', 'SHARK_RFCN', 'YFT_RFCN',
# 'ALB_CROP', 'BET_CROP', 'DOL_CROP',
# 'LAG_CROP', 'OTHER_CROP', 'SHARK_CROP', 'YFT_CROP',
# 'NoF', 'ALB', 'BET', 'DOL', 'LAG', 'OTHER', 'SHARK', 'YFT']
file_name = 'test_pred_df_Hybrid_'+test_model_name+'_.pickle'
if os.path.exists(OUTPUT_DIR+file_name):
print ('Loading from file '+file_name)
test_pred_df = pd.read_pickle(OUTPUT_DIR+file_name)
else:
print ('Generating file '+file_name)
with open("../RFCN/ImageSets/Main/test.txt","r") as f:
test_files = f.readlines()
test_pred_df = pd.DataFrame(columns=['logloss','image_class','image_file','NoF', 'ALB', 'BET', 'DOL', 'LAG', 'OTHER', 'SHARK', 'YFT'])
for j in range(len(test_files)):
image_file = test_files[j][:-1]+'.jpg'
test_pred_im_df = RFCNbbox_RFCNpred_CROPpred_HYBRIDpred_df.loc[RFCNbbox_RFCNpred_CROPpred_HYBRIDpred_df['image_file'] == image_file,
['image_class', 'NoF', 'ALB', 'BET', 'DOL', 'LAG', 'OTHER', 'SHARK', 'YFT']]
image_class = test_pred_im_df.iloc[0]['image_class']
test_pred_im_df.drop('image_class', axis=1, inplace=True)
max_score = test_pred_im_df.max(axis=1)
max_cls = test_pred_im_df.idxmax(axis=1)
test_pred_im_df['max_score'] = max_score
test_pred_im_df['max_cls'] = max_cls
test_pred_im_df['Count'] = test_pred_im_df.groupby(['max_cls'])['max_cls'].transform('count')
idx = test_pred_im_df.groupby(['max_cls'])['max_score'].transform(max) == test_pred_im_df['max_score']
test_pred_im_clsMax_df = test_pred_im_df.loc[idx,['NoF', 'ALB', 'BET', 'DOL', 'LAG', 'OTHER', 'SHARK', 'YFT', 'Count']]
test_pred_im_clsMax_array = test_pred_im_clsMax_df.values
pred = np.average(test_pred_im_clsMax_array[:,:-1], axis=0, weights=test_pred_im_clsMax_array[:,-1], returned=False).tolist()
if image_class!='--':
ind = FISH_CLASSES.index(image_class)
logloss = -math.log(pred[ind])
else:
logloss = np.nan
test_pred_im_clsMaxAve = [logloss,image_class,image_file]
test_pred_im_clsMaxAve.extend(pred)
test_pred_df.loc[len(test_pred_df)]=test_pred_im_clsMaxAve
test_pred_df.to_pickle(OUTPUT_DIR+file_name)
print('Done!')
image_all_logloss = test_pred_df[test_pred_df['image_class']!='--']['logloss'].mean()
print('imag_all_logloss:', image_all_logloss)
In [ ]:
#### visualization
# RFCNbbox_RFCNpred_CROPpred_df = ['image_class', 'image_file','crop_index','x_min','y_min','x_max','ymax',
# 'NoF_RFCN', 'ALB_RFCN', 'BET_RFCN', 'DOL_RFCN',
# 'LAG_RFCN', 'OTHER_RFCN', 'SHARK_RFCN', 'YFT_RFCN'
# 'NoF_CROP', 'ALB_CROP', 'BET_CROP', 'DOL_CROP',
# 'LAG_CROP', 'OTHER_CROP', 'SHARK_CROP', 'YFT_CROP']
#GTbbox_CROPpred_df = ['image_file','crop_index','crop_class','xmin','ymin','xmax','ymax',
# 'NoF', 'ALB', 'BET', 'DOL', 'LAG', 'OTHER', 'SHARK', 'YFT', 'logloss']
# test_pred_df = ['logloss','image_class','image_file','NoF', 'ALB', 'BET', 'DOL', 'LAG', 'OTHER', 'SHARK', 'YFT']
for j in range(test_pred_df.shape[0]):
image_logloss = test_pred_df.iat[j,0]
image_class = test_pred_df.iat[j,1]
image_file = test_pred_df.iat[j,2]
if j<1000 and j%30== 0:
pass
else:
continue
im = Image.open('../RFCN/JPEGImages/'+image_file)
im = np.asarray(im)
fig, ax = plt.subplots(figsize=(10, 8))
ax.imshow(im, aspect='equal')
RFCN_dets = RFCNbbox_RFCNpred_CROPpred_HYBRIDpred_df.loc[RFCNbbox_RFCNpred_CROPpred_HYBRIDpred_df['image_file']==image_file]
for index,row in RFCN_dets.iterrows():
bbox = [row['xmin'],row['ymin'],row['xmax'],row['ymax']]
RFCN = [row['NoF_RFCN'],row['ALB_RFCN'],row['BET_RFCN'],row['DOL_RFCN'],row['LAG_RFCN'],row['OTHER_RFCN'],row['SHARK_RFCN'],row['YFT_RFCN']]
CROP = [row['NoF'],row['ALB'],row['BET'],row['DOL'],row['LAG'],row['OTHER'],row['SHARK'],row['YFT']]
score_RFCN = max(RFCN)
score_CROP = max(CROP)
index_RFCN = RFCN.index(score_RFCN)
index_CROP = CROP.index(score_CROP)
class_RFCN = FISH_CLASSES[index_RFCN]
class_CROP = FISH_CLASSES[index_CROP]
ax.add_patch(plt.Rectangle((bbox[0], bbox[1]), bbox[2] - bbox[0], bbox[3] - bbox[1], fill=False, edgecolor='red', linewidth=2))
ax.text(bbox[0], bbox[1] - 2, 'RFCN_{:s} {:.3f} \nHYBRID_{:s} {:.3f}'.format(class_RFCN, score_RFCN, class_CROP, score_CROP), bbox=dict(facecolor='red', alpha=0.5), fontsize=8, color='white')
GT_dets = GTbbox_CROPpred_df.loc[GTbbox_CROPpred_df['image_file']==image_file]
for index,row in GT_dets.iterrows():
bbox = [row['xmin'],row['ymin'],row['xmax'],row['ymax']]
CROP = [row['NoF'],row['ALB'],row['BET'],row['DOL'],row['LAG'],row['OTHER'],row['SHARK'],row['YFT']]
score_CROP = max(CROP)
index_CROP = CROP.index(score_CROP)
class_CROP = FISH_CLASSES[index_CROP]
ax.add_patch(plt.Rectangle((bbox[0], bbox[1]), bbox[2] - bbox[0], bbox[3] - bbox[1], fill=False, edgecolor='green', linewidth=2))
ax.text(bbox[0], bbox[3] + 40, 'GT_{:s} \nCROP_{:s} {:.3f}'.format(row['crop_class'], class_CROP, score_CROP), bbox=dict(facecolor='green', alpha=0.5), fontsize=8, color='white')
ax.set_title(('Image {:s} FISH {:s} logloss {}').format(image_file, image_class, image_logloss), fontsize=10)
plt.axis('off')
plt.tight_layout()
plt.draw()
In [19]:
#temperature
T = 2.5
test_pred_array = test_pred_df[FISH_CLASSES].values
test_pred_T_array = np.exp(np.log(test_pred_array)/T)
test_pred_T_array = test_pred_T_array/np.sum(test_pred_T_array, axis=1, keepdims=True)
test_pred_T_df = pd.DataFrame(test_pred_T_array, columns=FISH_CLASSES)
test_pred_T_df = pd.concat([test_pred_df[['image_class','image_file']],test_pred_T_df], axis=1)
#test submission
submission = test_pred_T_df.loc[:999,['image_file','NoF', 'ALB', 'BET', 'DOL', 'LAG', 'OTHER', 'SHARK', 'YFT']]
submission.rename(columns={'image_file':'image'}, inplace=True)
sub_file = 'RFCN_AGONOSTICnms_'+RFCN_MODEL+'_'+CROP_MODEL+'_'+test_model_name+'_clsMaxAve_conf{:.2f}_cropvalidloss{:.4f}_imageallloss{:.4f}_T{}.csv'.format(CONF_THRESH, crop_valid_woNoF_logloss, image_all_logloss, T)
submission.to_csv(sub_file, index=False)
submission.to_csv(OUTPUT_DIR + sub_file, index=False)
print('Done!'+sub_file)
In [ ]: