def testtt(): folder = "/opt/visal/tmp/for_sijin/tmp/tmp_saved_tt" meta = dutils.collect_feature_meta(folder) meta_folder = "/opt/visal/tmp/for_sijin/Data/H36M/H36MFeatures/2015_02_02_acm_act_14_exp_2_19_graph_0012" iu.ensure_dir(meta_folder) meta_path = iu.fullfile(meta_folder, "prediction.meta") mio.pickle(meta_path, meta)
def pack_01(): """ input: fc_j0 feature, rel_pose outputs: rel_pose, fc_j0_feature """ source_feature_network_path = '/opt/visal/tmp/for_sijin/Data/saved/theano_models/2015_02_02_acm_act_14_exp_2_19_graph_0012/' source_meta_path = '/opt/visal/tmp/for_sijin/tmp/tmp_saved' exp_meta_path = '/opt/visal/tmp/for_sijin/Data/H36M/H36MExp/folder_ASM_act_14_exp_2/batches.meta' save_path = '/opt/visal/tmp/for_sijin/Data/H36M/H36MExp/folder_FCJ0_act_14' feature_name = 'Relative_Y3d_mono_body' res = dict() exp_meta = mio.unpickle(exp_meta_path) source_meta = dutils.collect_feature_meta(source_meta_path) rel_pose = exp_meta[feature_name] fc_j0_feature = source_meta['feature_list'][1] rel_gt = source_meta['feature_list'][0] diff = rel_gt.reshape((-1, rel_gt.shape[-1]),order='F') * 1200 - rel_pose print 'diff is {}'.format(diff.flatten().sum()) feature_list = [rel_pose, fc_j0_feature] feature_dim = [rel_pose.shape[0], fc_j0_feature.shape[0]] print feature_dim, '<<<feature dim' res = {'feature_list': feature_list, 'feature_dim':feature_dim, 'info':{'indexes':source_meta['info']['indexes'], 'max_depth': 1200.0}} indexes = res['info']['indexes'] res['info']['soure_feature_network_path'] = source_feature_network_path print indexes[:10], min(indexes), max(indexes) print 'The number of data is {} == {}'.format(indexes.size, feature_list[0].shape[-1]) iu.ensure_dir(save_path) mio.pickle(iu.fullfile(save_path, 'batches.meta'), res)
def testtt(): folder = '/opt/visal/tmp/for_sijin/tmp/tmp_saved_tt' meta = dutils.collect_feature_meta(folder) meta_folder = '/opt/visal/tmp/for_sijin/Data/H36M/H36MFeatures/2015_02_02_acm_act_14_exp_2_19_graph_0012' iu.ensure_dir(meta_folder) meta_path = iu.fullfile(meta_folder, 'prediction.meta') mio.pickle(meta_path, meta)
def collect_feature(op): save_path = op.get_value('res_save_path') import dhmlpe_utils as dutils meta = dutils.collect_feature_meta(save_path) meta_save_path =iu.fullfile(save_path, 'imgfeatures.meta') force_collect_type = op.get_value('force_collect_type') if force_collect_type == 'float32': print 'Force the feature dtype=float32' meta['feature_list'] = [np.array(x,dtype=np.float32) for x in meta['feature_list']] mio.pickle(meta_save_path, meta)
def collect_feature(op): save_path = op.get_value('res_save_path') import dhmlpe_utils as dutils meta = dutils.collect_feature_meta(save_path) meta_save_path = iu.fullfile(save_path, 'imgfeatures.meta') force_collect_type = op.get_value('force_collect_type') if force_collect_type == 'float32': print 'Force the feature dtype=float32' meta['feature_list'] = [ np.array(x, dtype=np.float32) for x in meta['feature_list'] ] mio.pickle(meta_save_path, meta)
def test_collect(): folder = "/opt/visal/tmp/for_sijin/tmp/tmp_saved" allfile = sorted(iu.getfilelist(folder, "feature_batch"), key=lambda x: dutils.extract_batch_num(x)) ntot = 0 for fn in allfile: d = mio.unpickle(iu.fullfile(folder, fn)) ndata = d["feature_list"][0].shape[-1] ntot += ndata print "The total number of data is {}".format(ntot) meta = dutils.collect_feature_meta(folder) print meta.keys() print meta["info"]["indexes"][:10] print meta["feature_dim"]
def test_collect(): folder = '/opt/visal/tmp/for_sijin/tmp/tmp_saved' allfile = sorted(iu.getfilelist(folder, 'feature_batch'), key=lambda x: dutils.extract_batch_num(x)) ntot = 0 for fn in allfile: d = mio.unpickle(iu.fullfile(folder, fn)) ndata = d['feature_list'][0].shape[-1] ntot += ndata print 'The total number of data is {}'.format(ntot) meta = dutils.collect_feature_meta(folder) print meta.keys() print meta['info']['indexes'][:10] print meta['feature_dim']
def pack_01(): """ input: fc_j0 feature, rel_pose outputs: rel_pose, fc_j0_feature """ source_feature_network_path = '/opt/visal/tmp/for_sijin/Data/saved/theano_models/2015_02_02_acm_act_14_exp_2_19_graph_0012/' source_meta_path = '/opt/visal/tmp/for_sijin/tmp/tmp_saved' exp_meta_path = '/opt/visal/tmp/for_sijin/Data/H36M/H36MExp/folder_ASM_act_14_exp_2/batches.meta' save_path = '/opt/visal/tmp/for_sijin/Data/H36M/H36MExp/folder_FCJ0_act_14' feature_name = 'Relative_Y3d_mono_body' res = dict() exp_meta = mio.unpickle(exp_meta_path) source_meta = dutils.collect_feature_meta(source_meta_path) rel_pose = exp_meta[feature_name] fc_j0_feature = source_meta['feature_list'][1] rel_gt = source_meta['feature_list'][0] diff = rel_gt.reshape((-1, rel_gt.shape[-1]), order='F') * 1200 - rel_pose print 'diff is {}'.format(diff.flatten().sum()) feature_list = [rel_pose, fc_j0_feature] feature_dim = [rel_pose.shape[0], fc_j0_feature.shape[0]] print feature_dim, '<<<feature dim' res = { 'feature_list': feature_list, 'feature_dim': feature_dim, 'info': { 'indexes': source_meta['info']['indexes'], 'max_depth': 1200.0 } } indexes = res['info']['indexes'] res['info']['soure_feature_network_path'] = source_feature_network_path print indexes[:10], min(indexes), max(indexes) print 'The number of data is {} == {}'.format(indexes.size, feature_list[0].shape[-1]) iu.ensure_dir(save_path) mio.pickle(iu.fullfile(save_path, 'batches.meta'), res)