Linear = Linear(in_size=144, out_size=10) #calling model for creating features model_test = RBM(n_visible=28 * 28, n_hidden=144) #Loading Weight rbm_weight_file = open("model/rbm_weight.npy", 'rb') model_test.weight = pickle.load(rbm_weight_file) #Loading visible layer bias rbm_v_bias_file = open("model/rbm_v_bias.npy", 'rb') model_test.v_bias = pickle.load(rbm_v_bias_file) #Loading hidden layer bias rbm_h_bias_file = open("model/rbm_h_bias.npy", 'rb') model_test.h_bias = pickle.load(rbm_h_bias_file) img_num = 60000 def train(x_train, y_train, alpha=0.001, weight_decay=0.0, epochs=40): for i in range(epochs): train_loss = 0 count = 0 for j in range(img_num): input = x_train[j].copy().reshape(1, 784) / 255.0 target = y_train[j].copy() #Extracting hidden features using RBM input, _ = model_test.sample_h_given_v(input)