From 07b38ce0b47704253c78208a5f6981e1754a4e5c Mon Sep 17 00:00:00 2001 From: AntreasAntoniou Date: Mon, 6 Nov 2017 17:34:25 +0000 Subject: [PATCH] Delete generate_inputs.py --- scripts/generate_inputs.py | 63 -------------------------------------- 1 file changed, 63 deletions(-) delete mode 100644 scripts/generate_inputs.py diff --git a/scripts/generate_inputs.py b/scripts/generate_inputs.py deleted file mode 100644 index ee7c46b..0000000 --- a/scripts/generate_inputs.py +++ /dev/null @@ -1,63 +0,0 @@ -import numpy as np -from mlp.layers import ConvolutionalLayer, BatchNormalizationLayer -import argparse - -parser = argparse.ArgumentParser(description='Welcome to GAN-Shot-Learning script') - -parser.add_argument('--student_id', nargs="?", type=str, help='Your student id in the format "sxxxxxxx"') - -args = parser.parse_args() - -student_id = args.student_id - -def generate_inputs(student_id): - student_number = student_id - tests = np.arange(96).reshape((2, 3, 4, 4)) - tests[:, 0, :, :] = float(student_number[1:3]) / 10 - 5 - tests[:, :, 1, :] = float(student_number[3:5]) / 10 - 5 - tests[:, 2, :, :] = float(student_number[5:7]) / 10 - 5 - tests[0, 1, :, :] = float(student_number[7]) / 10 - 5 - return tests - - - -test_inputs = generate_inputs(student_id) -test_grads_wrt_outputs = np.arange(-20, 16).reshape((2, 2, 3, 3)) -inputs = np.arange(96).reshape((2, 3, 4, 4)) -kernels = np.arange(-12, 12).reshape((2, 3, 2, 2)) -biases = np.arange(2) - -#produce ConvolutionalLayer fprop, bprop and grads_wrt_params -activation_layer = ConvolutionalLayer(num_input_channels=3, num_output_channels=2, input_dim_1=4, input_dim_2=4, - kernel_dim_1=2, kernel_dim_2=2) -activation_layer.params = [kernels, biases] -conv_fprop = activation_layer.fprop(test_inputs) -conv_bprop = activation_layer.bprop( - test_inputs, conv_fprop, test_grads_wrt_outputs) -conv_grads_wrt_params = activation_layer.grads_wrt_params(test_inputs, test_grads_wrt_outputs) - -test_inputs = np.reshape(test_inputs, newshape=(2, -1)) -test_grads_wrt_outputs = np.arange(-48, 48).reshape((2, -1)) - -#produce ELU fprop and bprop -activation_layer = BatchNormalizationLayer(input_dim=48) - -beta = np.array(48*[0.3]) -gamma = np.array(48*[0.8]) - -activation_layer.params = [gamma, beta] -BN_fprop = activation_layer.fprop(test_inputs) -BN_bprop = activation_layer.bprop( - test_inputs, BN_fprop, test_grads_wrt_outputs) -BN_grads_wrt_params = activation_layer.grads_wrt_params( - test_inputs, test_grads_wrt_outputs) - -test_output = "ConvolutionalLayer:\nFprop: {}\nBprop: {}\nGrads_wrt_params: {}\n" \ - "BatchNormalization:\nFprop: {}\nBprop: {}\nGrads_wrt_params: {}\n"\ - .format(conv_fprop, - conv_bprop, - conv_grads_wrt_params, - BN_fprop, BN_bprop, BN_grads_wrt_params) - -with open("{}_test_file.txt".format(student_id), "w+") as out_file: - out_file.write(test_output) \ No newline at end of file