draw_filters(xparray(model.conv21.W), '%s/log_conv21_epoch_%d.jpg' % (result_dir, epoch))
draw_filters_sq(xparray(model.conv12.W), '%s/log_conv12_epoch_%d.jpg' % (result_dir, epoch), 16)
draw_filters_sq(xparray(model.conv22.W), '%s/log_conv22_epoch_%d.jpg' % (result_dir, epoch), 16)
# 適当なファイルの画像を入力する
video_num = int(np.random.random() * len(test_vis))
s_image_vis = xp.asarray(test_vis[video_num]).astype(np.float32)
s_image_dep = xp.asarray(test_dep[video_num]).astype(np.float32)
# プーリング1層まで通した結果を出力
frame_num = int(s_image_vis.shape[0]/ 2)
draw_image(xparray(model.extract_pool11(s_image_vis[frame_num,:,:]).data), '%s/sample_vis_pool1_%d.jpg' % (result_dir, epoch))
draw_image(xparray(model.extract_pool21(s_image_dep[frame_num,:,:]).data), '%s/sample_dep_pool1_%d.jpg' % (result_dir, epoch))
# 学習曲線を出力
draw_loss_curve(log_fn, '%s/log.jpg' % result_dir)
print("Confusion Matrix for train data:")
print_confmat(conf_array_train)
print("Confusion Matrix for test data:")
print_confmat(conf_array_test)
np.savetxt('%s/confmat_train_epoch_%d.csv' % (result_dir, epoch), conf_array_train, delimiter=',', fmt='%d')
np.savetxt('%s/confmat_test_epoch_%d.csv' % (result_dir, epoch), conf_array_test, delimiter=',', fmt='%d')
# テストセットの予測を出力
f = open('%s/pred_test_epoch_%d.csv' % (result_dir, epoch), 'w')
writer = csv.writer(f)
for i in range(len(pred)):
writer.writerow(test_labels_epoch[i].tolist())
model_fn = '%s/%s_epoch_%d.chainermodel' % (
result_dir, args.model, epoch)
pickle.dump(model, open(model_fn, 'wb'), -1)
"""
CNNで各層を可視化
1,2層の可視化
"""
if epoch % args.visualize == 0:
draw_filters(xparray(model.conv11.W), '%s/log_conv11_epoch_%d.jpg' % (result_dir, epoch))
draw_filters(xparray(model.conv21.W), '%s/log_conv21_epoch_%d.jpg' % (result_dir, epoch))
draw_filters_sq(xparray(model.conv12.W), '%s/log_conv12_epoch_%d.jpg' % (result_dir, epoch), 16)
draw_filters_sq(xparray(model.conv22.W), '%s/log_conv22_epoch_%d.jpg' % (result_dir, epoch), 16)
# 学習曲線を出力
draw_loss_curve(log_fn, '%s/loss_accuracy.jpg' % result_dir, result_dir, args.epoch_offset)
labels = "sf123456789012345678901234567890123456789012345678901234567890"[0:num_labels]
# 混同行列を表示
print("Confusion Matrix for train data:")
print_confmat(conf_array_train)
print("Confusion Matrix for test data:")
print_confmat(conf_array_test)
# 混同行列をcsvに出力
np.savetxt('%s/confmat_train_epoch_%d.csv' % (result_dir, epoch), conf_array_train, delimiter=',', fmt='%d')
np.savetxt('%s/confmat_test_epoch_%d.csv' % (result_dir, epoch), conf_array_test, delimiter=',', fmt='%d')
# テストセットの予測を出力
1,2層の可視化
"""
if epoch % args.visualize == 0:
draw_filters(xparray(model.conv11.W),
'%s/log_conv11_epoch_%d.jpg' % (result_dir, epoch))
draw_filters(xparray(model.conv21.W),
'%s/log_conv21_epoch_%d.jpg' % (result_dir, epoch))
draw_filters_sq(xparray(model.conv12.W),
'%s/log_conv12_epoch_%d.jpg' % (result_dir, epoch),
16)
draw_filters_sq(xparray(model.conv22.W),
'%s/log_conv22_epoch_%d.jpg' % (result_dir, epoch),
16)
# 学習曲線を出力
draw_loss_curve(log_fn, '%s/loss_accuracy.jpg' % result_dir,
result_dir, args.epoch_offset)
labels = "sf123456789012345678901234567890123456789012345678901234567890"[
0:num_labels]
# 混同行列を表示
print("Confusion Matrix for train data:")
print_confmat(conf_array_train)
print("Confusion Matrix for test data:")
print_confmat(conf_array_test)
# 混同行列をcsvに出力
np.savetxt('%s/confmat_train_epoch_%d.csv' % (result_dir, epoch),
conf_array_train,
delimiter=',',
