from tools import data_loader, model_io, render, data_analysis import matplotlib.pyplot as plt import numpy as np import settings import math import mpl_toolkits.axes_grid1 as axes_grid1 # load trained neural network (nn) nnName = 'nn_Linear_4096_4_Rect_Linear_4_2_SoftMax_(batchsize_10_number_iterations_20000).txt' # nnName = 'nn_Linear_1024_2_Rect_Linear_2_2_SoftMax_(batchsize_10_number_iterations_10000).txt' nn = model_io.read(settings.modelPath + nnName) # I do not want to load the data every time, therefore the if statement if 'X' not in locals(): # load data X, Y = data_loader.load_data() # choose some test data idx = 0 x = X['train'][[idx]] y = Y['train'][[idx]] nnPred = nn.forward(x) # print nnPred # lrpScores = nn.lrp(nnPred, 'alphabeta', 2) # print np.sum(lrpScores) #plt.matshow(render.vec2im(x[0] + innerCircleSq)) # inspect first linear layer # -------------------------- W1 = nn.modules[0].W
class original_db(): train_data, test_data = load_data(DATA_PATH)
# load data from tools.data_loader import load_data PROJECT_NAME = '003_digit' DATA_PATH = 'datasets\\{}\\'.format(PROJECT_NAME) data_train, data_test = load_data(DATA_PATH) #----------------------------------------------------------- Y_train = data_train["label"] X_train = data_train.drop(labels=["label"], axis=1) del data_train # ---------------------------------------------------------- from time import time import pandas as pd from pandas import Series, DataFrame import numpy as np import matplotlib.pyplot as plt import matplotlib.image as mpimg import seaborn as sns np.random.seed(2) from sklearn.model_selection import train_test_split from sklearn.metrics import confusion_matrix import itertools from keras.utils.np_utils import to_categorical # convert to one-hot-encoding
f['pred_k'] = pred_k f['cFrm'] = cFrm f['idx'] = te_idx f.close() if __name__ == '__main__': dataset_testing = 'SumMe' # testing dataset: SumMe or TVSum model_type = 2 # 1 for vsLSTM and 2 for dppLSTM, please refer to the readme file for more detail model_idx = 'dppLSTM_' + dataset_testing + '_' + model_type.__str__() # load data print('... loading data') train_set, val_set, val_idx, test_set, te_idx = data_loader.load_data( data_dir='../data/', dataset_testing=dataset_testing, model_type=model_type) model_file = '../models/model_trained_' + dataset_testing train(model_idx=model_idx, train_set=train_set, val_set=val_set, model_saved=model_file) inference(model_file=model_file, model_idx=model_idx, test_set=test_set, test_dir='./res_LSTM/', te_idx=te_idx)
# -*- coding: utf-8 -*- import requests as req from time import time PROJECT_NAME = '005_landmarks_retrieval' DATA_PATH = 'datasets\\{}\\'.format(PROJECT_NAME) from tools.data_loader import load_data train_data, test_data = load_data(DATA_PATH) print(train_data.columns) print(train_data.shape) # ----------------------------------------------- # primary analysis # missing value from tools.pandas_extend import NA_refiner nar = NA_refiner(train_data) nar.show() # comments: there is no missing value # how much images for one landmark print(train_data.landmark_id.value_counts().describe()) # comments: very less # ------------------------------------------------------ # read the image from skimage import io t0 = time()
# load data from tools.data_loader import load_data PROJECT_NAME = '002_house_price' DATA_PATH = 'datasets\\{}\\'.format(PROJECT_NAME) train, test = load_data(DATA_PATH) #--------------------------------------------------- import pandas as pd # pd.set_option('display.float_format', lambda x: '{:.3f}'.format(x)) #Limiting floats output to 3 decimal points import numpy as np from pandas import Series,DataFrame all_data = pd.concat((train, test)).reset_index(drop=True) ntrain = train.shape[0] # ntest = test.shape[0] y_train = train.SalePrice.values # ---------------------------------------------------------------------------- train.info() train.shape test.info() test.shape import seaborn as sns color = sns.color_palette()
from networks.dpp_lstm import DPPLSTM from networks.loss import LOSS from torch.autograd import Variable import numpy as np import torch import pdb if __name__ == '__main__': # load data data_dir = '../data/' test_data_name = 'SumMe' model_type = 2 # 1 for vsLSTM, 2 for dppLSTM print('...loading data') train_set, valid_set, test_set, test_idx = load_data( data_dir, test_data_name, model_type) one_sample = train_set[0][0] one_bin_label = train_set[1][ 0] # binary value: 0 - non keyframe, 1 - keyfram one_idx_label = train_set[2][0] # keyframe index seq_len = one_sample.shape[0] input_size = 1024 hidden_size = 256 output_size = 256 c_mlp_output_size = 1 k_mlp_output_size = 256 num_layers = 1 batch_size = 1