def test_save_and_load_convtasnet(fb): model1 = ConvTasNet(n_src=2, n_repeats=2, n_blocks=2, bn_chan=16, hid_chan=4, skip_chan=8, n_filters=32, fb_name=fb) test_input = torch.randn(1, 800) model_conf = model1.serialize() reconstructed_model = ConvTasNet.from_pretrained(model_conf) assert_allclose(model1.separate(test_input), reconstructed_model(test_input))
def main(conf): model_path = os.path.join(conf["exp_dir"], "best_model.pth") model = ConvTasNet.from_pretrained(model_path) # Handle device placement if conf["use_gpu"]: model.cuda() model_device = next(model.parameters()).device torch.no_grad().__enter__() alto, fs = sf.read( '/home/pc2752/share//Darius/data/satb_dst/test_dcs/raw_audio/DCS_TPQuartetA/DCS_TPQuartetA_alto_1.wav' ) bass, fs = sf.read( '/home/pc2752/share//Darius/data/satb_dst/test_dcs/raw_audio/DCS_TPQuartetA/DCS_TPQuartetA_bass_1.wav' ) soprano, fs = sf.read( '/home/pc2752/share//Darius/data/satb_dst/test_dcs/raw_audio/DCS_TPQuartetA/DCS_TPQuartetA_soprano_1.wav' ) tenor, fs = sf.read( '/home/pc2752/share//Darius/data/satb_dst/test_dcs/raw_audio/DCS_TPQuartetA/DCS_TPQuartetA_tenor_1.wav' ) mix, fs = sf.read( '/home/pc2752/share//Darius/Wave-U-Net/test_set_mixes/dcs/DCS_TPQuartetA_mix.wav' ) mix = torch.from_numpy(mix).type(torch.FloatTensor) outputs = model.float()(mix) sdr, sir, sar, perm = separation.bss_eval_sources( np.array([soprano, alto, tenor, bass]), outputs[:, :soprano.shape[0]].detach().numpy()) print("SDR: {}\nSIR: {}\nSAR: {}".format(sdr, sir, sar)) sf.write('./DCS_TPQuartetA_Soprano.wav', outputs[0], fs) sf.write('./DCS_TPQuartetA_Alto.wav', outputs[1], fs) sf.write('./DCS_TPQuartetA_Tenor.wav', outputs[2], fs) sf.write('./DCS_TPQuartetA_Bass.wav', outputs[3], fs)
def convtasnet(conf): sys.path.append('./asteroid') from asteroid.models import ConvTasNet from asteroid.utils import tensors_to_device from asteroid.models import save_publishable model_path = './models/convtasnet_usecase2.pth' model = ConvTasNet.from_pretrained(model_path) # Handle device placement if conf["use_gpu"]: model.cuda() model_device = next(model.parameters()).device torch.no_grad().__enter__() mix, fs = sf.read(conf["input_path"]) mix = torch.from_numpy(mix).type(torch.FloatTensor) outputs = model.float()(mix) return outputs
def main(conf): model_path = os.path.join(conf["exp_dir"], "best_model.pth") model = ConvTasNet.from_pretrained(model_path) # Handle device placement if conf["use_gpu"]: model.cuda() model_device = next(model.parameters()).device test_set = SourceFolderDataset( os.path.join(conf["exp_dir"], "json/"), conf["wav_dir"], conf["n_src"], conf["sample_rate"], conf["batch_size"], ) # Uses all segment length # Used to reorder sources only loss_func = PITLossWrapper(pairwise_neg_sisdr, pit_from="pw_mtx") # Randomly choose the indexes of sentences to save. ex_save_dir = os.path.join(conf["exp_dir"], "examples/") if conf["n_save_ex"] == -1: conf["n_save_ex"] = len(test_set) save_idx = random.sample(range(len(test_set)), conf["n_save_ex"]) series_list = [] torch.no_grad().__enter__() for idx in tqdm(range(len(test_set))): # Forward the network on the mixture. mix, sources = tensors_to_device(test_set[idx], device=model_device) mix = mix.unsqueeze(0) sources = sources.unsqueeze(0) est_sources = model(mix) #print(test_set[idx]) #print(est_sources.shape, sources.shape, mix.shape, len(test_set)) loss, reordered_sources = loss_func(est_sources, sources, return_est=True) #mix_np = mix.squeeze(0).cpu().data.numpy() mix_np = mix.cpu().data.numpy() sources_np = sources.squeeze(0).cpu().data.numpy() est_sources_np = reordered_sources.squeeze(0).cpu().data.numpy() utt_metrics = get_metrics( mix_np, sources_np, est_sources_np, sample_rate=conf["sample_rate"], metrics_list=compute_metrics, ) utt_metrics["mix_path"] = test_set.mix[idx][0] series_list.append(pd.Series(utt_metrics)) # Save some examples in a folder. Wav files and metrics as text. if idx in save_idx: local_save_dir = os.path.join(ex_save_dir, "ex_{}/".format(idx)) os.makedirs(local_save_dir, exist_ok=True) #print(mix_np.shape) sf.write(local_save_dir + "mixture.wav", np.swapaxes(mix_np,0,1), conf["sample_rate"]) # Loop over the sources and estimates for src_idx, src in enumerate(sources_np): sf.write(local_save_dir + "s{}.wav".format(src_idx + 1), src, conf["sample_rate"]) for src_idx, est_src in enumerate(est_sources_np): est_src *= np.max(np.abs(mix_np)) / np.max(np.abs(est_src)) sf.write( local_save_dir + "s{}_estimate.wav".format(src_idx + 1), est_src, conf["sample_rate"], ) # Write local metrics to the example folder. with open(local_save_dir + "metrics.json", "w") as f: json.dump(utt_metrics, f, indent=0) # Save all metrics to the experiment folder. all_metrics_df = pd.DataFrame(series_list) all_metrics_df.to_csv(os.path.join(conf["exp_dir"], "all_metrics.csv")) # Print and save summary metrics final_results = {} for metric_name in compute_metrics: input_metric_name = "input_" + metric_name ldf = all_metrics_df[metric_name] - all_metrics_df[input_metric_name] final_results[metric_name] = all_metrics_df[metric_name].mean() final_results[metric_name + "_imp"] = ldf.mean() print("Overall metrics :") pprint(final_results) with open(os.path.join(conf["exp_dir"], "final_metrics.json"), "w") as f: json.dump(final_results, f, indent=0) model_dict = torch.load(model_path, map_location="cpu") os.makedirs(os.path.join(conf["exp_dir"], "publish_dir"), exist_ok=True) publishable = save_publishable( os.path.join(conf["exp_dir"], "publish_dir"), model_dict, metrics=final_results, train_conf=train_conf, )
def main(conf): model_path = os.path.join(conf['exp_dir'], 'best_model.pth') model = ConvTasNet.from_pretrained(model_path) # Handle device placement if conf['use_gpu']: model.cuda() model_device = next(model.parameters()).device test_set = WhamDataset(conf['test_dir'], conf['task'], sample_rate=conf['sample_rate'], nondefault_nsrc=model.masker.n_src, segment=None) # Uses all segment length # Used to reorder sources only loss_func = PITLossWrapper(pairwise_neg_sisdr, pit_from='pw_mtx') # Randomly choose the indexes of sentences to save. ex_save_dir = os.path.join(conf['exp_dir'], 'examples/') if conf['n_save_ex'] == -1: conf['n_save_ex'] = len(test_set) save_idx = random.sample(range(len(test_set)), conf['n_save_ex']) series_list = [] torch.no_grad().__enter__() for idx in tqdm(range(len(test_set))): # Forward the network on the mixture. mix, sources = tensors_to_device(test_set[idx], device=model_device) est_sources = model(mix[None, None]) loss, reordered_sources = loss_func(est_sources, sources[None], return_est=True) mix_np = mix[None].cpu().data.numpy() sources_np = sources.cpu().data.numpy() est_sources_np = reordered_sources.squeeze(0).cpu().data.numpy() utt_metrics = get_metrics(mix_np, sources_np, est_sources_np, sample_rate=conf['sample_rate'], metrics_list=compute_metrics) utt_metrics['mix_path'] = test_set.mix[idx][0] series_list.append(pd.Series(utt_metrics)) # Save some examples in a folder. Wav files and metrics as text. if idx in save_idx: local_save_dir = os.path.join(ex_save_dir, 'ex_{}/'.format(idx)) os.makedirs(local_save_dir, exist_ok=True) sf.write(local_save_dir + "mixture.wav", mix_np[0], conf['sample_rate']) # Loop over the sources and estimates for src_idx, src in enumerate(sources_np): sf.write(local_save_dir + "s{}.wav".format(src_idx + 1), src, conf['sample_rate']) for src_idx, est_src in enumerate(est_sources_np): est_src *= np.max(np.abs(mix_np)) / np.max(np.abs(est_src)) sf.write( local_save_dir + "s{}_estimate.wav".format(src_idx + 1), est_src, conf['sample_rate']) # Write local metrics to the example folder. with open(local_save_dir + 'metrics.json', 'w') as f: json.dump(utt_metrics, f, indent=0) # Save all metrics to the experiment folder. all_metrics_df = pd.DataFrame(series_list) all_metrics_df.to_csv(os.path.join(conf['exp_dir'], 'all_metrics.csv')) # Print and save summary metrics final_results = {} for metric_name in compute_metrics: input_metric_name = 'input_' + metric_name ldf = all_metrics_df[metric_name] - all_metrics_df[input_metric_name] final_results[metric_name] = all_metrics_df[metric_name].mean() final_results[metric_name + '_imp'] = ldf.mean() print('Overall metrics :') pprint(final_results) with open(os.path.join(conf['exp_dir'], 'final_metrics.json'), 'w') as f: json.dump(final_results, f, indent=0) model_dict = torch.load(model_path, map_location='cpu') os.makedirs(os.path.join(conf['exp_dir'], 'publish_dir'), exist_ok=True) publishable = save_publishable(os.path.join(conf['exp_dir'], 'publish_dir'), model_dict, metrics=final_results, train_conf=train_conf)
def main(conf): model_path = os.path.join(conf['exp_dir'], 'best_model.pth') model = ConvTasNet.from_pretrained(model_path) # Handle device placement if conf['use_gpu']: model.cuda() model_device = next(model.parameters()).device # get data for evaluation - this should change in the future to work on real test data the was not used for training dataset = SeparationDataset(combination_list_path=os.path.join( conf['exp_dir'], 'combination_list.pkl')) n_val = int( len(dataset) * conf['train_conf']['data'] ['fraction_of_examples_to_use_for_validation']) train_set, val_set = random_split(dataset, [len(dataset) - n_val, n_val]) # noqa # test_set = val_set test_set = train_set # Used to reorder sources only loss_func = PITLossWrapper(pairwise_neg_sisdr, pit_from='pw_mtx') # Randomly choose the indexes of sentences to save. ex_save_dir = os.path.join(conf['exp_dir'], 'examples/') if conf['n_save_ex'] == -1: conf['n_save_ex'] = len(test_set) save_idx = random.sample(range(len(test_set)), conf['n_save_ex']) # series_list = [] torch.no_grad().__enter__() for idx in tqdm(range(len(test_set))): # Forward the network on the mixture. mix, sources = tensors_to_device(test_set[idx], device=model_device) est_sources = model(mix[None, None]) loss, reordered_sources = loss_func(est_sources, sources[None], return_est=True) # noqa mix_np = to_complex(mix[None].cpu().data.numpy()) sources_np = to_complex(sources.cpu().data.numpy()) est_sources_np = to_complex( reordered_sources.squeeze(0).cpu().data.numpy()) # utt_metrics = get_metrics(mix_np, sources_np, est_sources_np, # sample_rate=conf['sample_rate'], # metrics_list=compute_metrics) # utt_metrics['mix_path'] = test_set.mix[idx][0] # series_list.append(pd.Series(utt_metrics)) # Save some examples in a folder. Wav files and metrics as text. if idx in save_idx: local_save_dir = os.path.join(ex_save_dir, 'ex_{}/'.format(idx)) os.makedirs(local_save_dir, exist_ok=True) iq_data = mix_np[0] ax = plot_spectogram(iq_data, scale=False, show_plot=False) ax.figure.savefig(local_save_dir + 'mixture.png') # Loop over the sources and estimates for src_idx, src in enumerate(sources_np): iq_data = src ax = plot_spectogram(iq_data, scale=False, show_plot=False) ax.figure.savefig(local_save_dir + "s{}.png".format(src_idx + 1)) for src_idx, est_src in enumerate(est_sources_np): # est_src *= np.max(np.abs(mix_np))/np.max(np.abs(est_src)) iq_data = np.reshape(est_src, (32, 128)).T ax = plot_spectogram(iq_data, scale=False, show_plot=False) ax.figure.savefig(local_save_dir + "s{}_estimate.png".format(src_idx + 1))