我们从Python开源项目中，提取了以下12个代码示例，用于说明如何使用train.Graph()。
def validation_check(): # Load graph g = Graph(is_training=False); print("Graph loaded") # Load data X, Y = load_data(mode="val") with g.graph.as_default(): sv = tf.train.Supervisor() with sv.managed_session(config=tf.ConfigProto(allow_soft_placement=True)) as sess: # Restore parameters sv.saver.restore(sess, tf.train.latest_checkpoint(hp.logdir)); print("Restored!") # Get model mname = open(hp.logdir + '/checkpoint', 'r').read().split('"')[1] # model name # Inference if not os.path.exists(hp.results): os.mkdir(hp.results) with open(os.path.join(hp.results, "validation_results.txt"), 'a') as fout: expected, predicted = [], [] for step in range(len(X) // hp.batch_size): x = X[step * hp.batch_size: (step + 1) * hp.batch_size] y = Y[step * hp.batch_size: (step + 1) * hp.batch_size] # predict intensities logits = sess.run(g.logits, {g.x: x}) expected.extend(list(y)) predicted.extend(list(logits)) # Get spearman coefficients score, _ = spearmanr(expected, predicted) fout.write("{}\t{}\n".format(mname, score))
def test(): x, y = load_data(type="test") g = Graph(is_training=False) with g.graph.as_default(): sv = tf.train.Supervisor() with sv.managed_session(config=tf.ConfigProto(allow_soft_placement=True)) as sess: # Restore parameters sv.saver.restore(sess, tf.train.latest_checkpoint(hp.logdir)) print("Restored!") # Get model name mname = open(hp.logdir + '/checkpoint', 'r').read().split('"')[1] # model name if not os.path.exists('results'): os.mkdir('results') fout = 'results/{}.txt'.format(mname) import copy _preds = copy.copy(x) while 1: istarget, probs, preds = sess.run([g.istarget, g.probs, g.preds], {g.x:_preds, g.y: y}) probs = probs.astype(np.float32) preds = preds.astype(np.float32) probs *= istarget #(N, 9, 9) preds *= istarget #(N, 9, 9) probs = np.reshape(probs, (-1, 9*9)) #(N, 9*9) preds = np.reshape(preds, (-1, 9*9))#(N, 9*9) _preds = np.reshape(_preds, (-1, 9*9)) maxprob_ids = np.argmax(probs, axis=1) # (N, ) <- blanks of the most probable prediction maxprobs = np.max(probs, axis=1, keepdims=False) for j, (maxprob_id, maxprob) in enumerate(zip(maxprob_ids, maxprobs)): if maxprob != 0: _preds[j, maxprob_id] = preds[j, maxprob_id] _preds = np.reshape(_preds, (-1, 9, 9)) _preds = np.where(x==0, _preds, y) # # Fill in the non-blanks with correct numbers if np.count_nonzero(_preds) == _preds.size: break write_to_file(x.astype(np.int32), y, _preds.astype(np.int32), fout)
def eval(): # Load graph g = Graph(is_training=False); print("Graph loaded") # Load data x, y = load_eval_data() char2idx, idx2char = load_vocab() with g.graph.as_default(): sv = tf.train.Supervisor() with sv.managed_session() as sess: # Restore parameters sv.saver.restore(sess, tf.train.latest_checkpoint(hp.logdir)) print("Restored!") # Get model name mname = open(hp.logdir + '/checkpoint', 'r').read().split('"')[1] # Speech to Text if not os.path.exists('samples'): os.mkdir('samples') with codecs.open('samples/{}.txt'.format(mname), 'w', 'utf-8') as fout: preds = np.zeros((hp.batch_size, hp.max_len), np.int32) for j in range(hp.max_len): _preds = sess.run(g.preds, {g.x: x, g.y: preds}) preds[:, j] = _preds[:, j] # Write to file for i, (expected, got) in enumerate(zip(y, preds)): # ground truth vs. prediction fout.write("Expected: {}\n".format(expected.split("S")[0])) fout.write("Got : {}\n\n".format(("".join(idx2char[idx] for idx in np.fromstring(got, np.int32))).split("S")[0])) fout.flush()
def eval(mode): ''' Get a Spearman rank-order correlation coefficient. Args: mode: A string. Either `val` or `test`. ''' # Set save directory savedir = hp.valdir if mode=="val" else hp.testdir # Load graph g = Graph(is_training=False) print("Graph loaded") # Load data X, Y = load_data(mode=mode) nucl2idx, idx2nucl = load_vocab() with g.graph.as_default(): sv = tf.train.Supervisor() with sv.managed_session(config=tf.ConfigProto(allow_soft_placement=True)) as sess: # Restore parameters sv.saver.restore(sess, tf.train.latest_checkpoint(hp.logdir)) print("Restored!") # Get model mname = open(hp.logdir + '/checkpoint', 'r').read().split('"')[1] # model name # Inference if not os.path.exists(savedir): os.mkdir(savedir) with open("{}/{}".format(savedir, mname), 'w') as fout: fout.write("{}\t{}\t{}]\n".format("probe", "expected intensity", "predicted intensity")) expected, got = [], [] for step in range(len(X) // hp.batch_size): x = X[step * hp.batch_size: (step + 1) * hp.batch_size] y = Y[step * hp.batch_size: (step + 1) * hp.batch_size] # predict nucl logits = sess.run(g.logits, {g.x: x}) for xx, yy, ll in zip(x, y, logits): # sequence-wise fout.write("{}\t{}\t{}\n".format("".join(idx2nucl[idx] for idx in xx), yy, ll)) expected.append(yy) got.append(ll) # Spearman rank coefficient score, _ =spearmanr(expected, got) fout.write("Spearman rank correlation coefficients: " + str(score))
def eval(): # Load graph g = Graph(is_training=False); print("Graph loaded") # Load data X, Y = load_data(mode="test") nucl2idx, idx2nucl = load_vocab() with g.graph.as_default(): sv = tf.train.Supervisor() with sv.managed_session(config=tf.ConfigProto(allow_soft_placement=True)) as sess: # Restore parameters sv.saver.restore(sess, tf.train.latest_checkpoint(hp.logdir)); print("Restored!") # Get model name mname = open(hp.logdir + '/checkpoint', 'r').read().split('"')[1] # model name # Inference if not os.path.exists(hp.results): os.mkdir(hp.results) with open(os.path.join(hp.results, mname), 'w') as fout: fout.write("{}\t{}\t{}\n".format("probe", "expected intensity", "predicted intensity")) expected, predicted = [], [] for step in range(len(X) // hp.batch_size): x = X[step * hp.batch_size: (step + 1) * hp.batch_size] y = Y[step * hp.batch_size: (step + 1) * hp.batch_size] # predict intensities logits = sess.run(g.logits, {g.x: x}) expected.extend(list(y)) predicted.extend(list(logits)) for xx, yy, ll in zip(x, y, logits): # sequence-wise fout.write("{}\t{}\t{}\n".format("".join(idx2nucl[idx] for idx in xx), yy, ll)) # Get spearman coefficients score, _ = spearmanr(expected, predicted) fout.write("{}{}\n".format("Spearman Coefficient: ", score)) # Plot the ranks of the top 100 positive probes expected_predicted = sorted(zip(expected, predicted), key=lambda x: float(x[0]), reverse=True) expected_predicted = [list(each) + [int(i < 100)] for i, each in enumerate(expected_predicted)] expected_predicted = sorted(expected_predicted, key=lambda x: float(x[1]), reverse=True) predicted_ranks = np.array([each[-1] for each in expected_predicted]) # Plot axprops = dict(xticks=[], yticks=[]) barprops = dict(aspect='auto', cmap=plt.cm.binary, interpolation='nearest') fig = plt.figure() predicted_ranks.shape = len(predicted_ranks), 1 ax = fig.add_axes([0, 0, .5, 1], **axprops) ax.imshow(predicted_ranks, **barprops) fig.savefig('fig/rank.png')
def eval(): # Load graph g = Graph(is_training=False) print("Graph loaded") # Load data X, Y = load_data(mode="test") # texts char2idx, idx2char = load_vocab() with g.graph.as_default(): sv = tf.train.Supervisor() with sv.managed_session(config=tf.ConfigProto(allow_soft_placement=True)) as sess: # Restore parameters sv.saver.restore(sess, tf.train.latest_checkpoint(hp.logdir)) print("Restored!") # Get model mname = open(hp.logdir + '/checkpoint', 'r').read().split('"')[1] # model name # Inference if not os.path.exists(hp.savedir): os.mkdir(hp.savedir) with open("{}/{}".format(hp.savedir, mname), 'w') as fout: results = [] baseline_results = [] for step in range(len(X) // hp.batch_size): x = X[step * hp.batch_size: (step + 1) * hp.batch_size] y = Y[step * hp.batch_size: (step + 1) * hp.batch_size] # predict characters preds = sess.run(g.preds, {g.x: x}) for xx, yy, pp in zip(x, y, preds): # sentence-wise expected = '' got = '' for xxx, yyy, ppp in zip(xx, yy, pp): # character-wise if xxx == 0: break else: got += idx2char.get(xxx, "*") expected += idx2char.get(xxx, "*") if ppp == 1: got += " " if yyy == 1: expected += " " # prediction results if ppp == yyy: results.append(1) else: results.append(0) # baseline results if yyy == 0: # no space baseline_results.append(1) else: baseline_results.append(0) fout.write("?Expected: " + expected + "\n") fout.write("?Got: " + got + "\n\n") fout.write( "Final Accuracy = %d/%d=%.4f\n" % (sum(results), len(results), float(sum(results)) / len(results))) fout.write( "Baseline Accuracy = %d/%d=%.4f" % (sum(baseline_results), len(baseline_results), float(sum(baseline_results)) / len(baseline_results)))
def eval_it(): # Load graph g = Graph(is_training=False) print("Graph loaded") # Load data X = load_eval_data() # texts char2idx, idx2char = load_vocab() with g.graph.as_default(): sv = tf.train.Supervisor() with sv.managed_session(config=tf.ConfigProto(allow_soft_placement=True)) as sess: # Restore parameters sv.saver.restore(sess, tf.train.latest_checkpoint(hp.logdir)) print("Restored!") # Get model mname = open(hp.logdir + '/checkpoint', 'r').read().split('"')[1] # model name timesteps = 100 # Adjust this number as you want outputs1 = np.zeros((hp.num_samples, timesteps, hp.n_mels * hp.r), np.float32) # hp.n_mels*hp.r for j in range(timesteps): _outputs1 = sess.run(g.outputs1, {g.x: X, g.y: outputs1}) outputs1[:, j, :] = _outputs1[:, j, :] outputs2 = sess.run(g.outputs2, {g.outputs1: outputs1}) # Generate wav files if not os.path.exists(hp.outputdir): os.mkdir(hp.outputdir) with codecs.open(hp.outputdir + '/text.txt', 'w', 'utf-8') as fout: for i, (x, s) in enumerate(zip(X, outputs2)): # write text fout.write(str(i) + "\t" + "".join(idx2char[idx] for idx in np.fromstring(x, np.int32) if idx != 0) + "\n") s = restore_shape(s, hp.win_length // hp.hop_length, hp.r) # generate wav files if hp.use_log_magnitude: audio = spectrogram2wav(np.power(np.e, s) ** hp.power) else: s = np.where(s < 0, 0, s) audio = spectrogram2wav(s ** hp.power) write(hp.outputdir + "/{}_{}.wav".format(mname, i), hp.sr, audio)
def eval(): # Load graph g = Graph(mode="inference"); print("Graph Loaded") with tf.Session() as sess: # Initialize variables tf.sg_init(sess) # Restore parameters saver = tf.train.Saver() saver.restore(sess, tf.train.latest_checkpoint('asset/train')) print("Restored!") mname = open('asset/train/checkpoint', 'r').read().split('"')[1] # model name # Load data X, Sources, Targets = load_test_data() char2idx, idx2char = load_vocab() with codecs.open(mname, "w", "utf-8") as fout: list_of_refs, hypotheses = [], [] for i in range(len(X) // Hp.batch_size): # Get mini-batches x = X[i*Hp.batch_size: (i+1)*Hp.batch_size] # mini-batch sources = Sources[i*Hp.batch_size: (i+1)*Hp.batch_size] targets = Targets[i*Hp.batch_size: (i+1)*Hp.batch_size] preds_prev = np.zeros((Hp.batch_size, Hp.maxlen), np.int32) preds = np.zeros((Hp.batch_size, Hp.maxlen), np.int32) for j in range(Hp.maxlen): # predict next character outs = sess.run(g.preds, {g.x: x, g.y_src: preds_prev}) # update character sequence if j < Hp.maxlen - 1: preds_prev[:, j + 1] = outs[:, j] preds[:, j] = outs[:, j] # Write to file for source, target, pred in zip(sources, targets, preds): # sentence-wise got = "".join(idx2char[idx] for idx in pred).split(u"?")[0] fout.write("- source: " + source +"\n") fout.write("- expected: " + target + "\n") fout.write("- got: " + got + "\n\n") fout.flush() # For bleu score ref = target.split() hypothesis = got.split() if len(ref) > 2: list_of_refs.append([ref]) hypotheses.append(hypothesis) # Get bleu score score = corpus_bleu(list_of_refs, hypotheses) fout.write("Bleu Score = " + str(100*score))
def eval(): # Load graph g = Graph(is_training=False) print("Graph loaded") # Load data X = load_eval_data() # texts char2idx, idx2char = load_vocab() with g.graph.as_default(): sv = tf.train.Supervisor() with sv.managed_session(config=tf.ConfigProto(allow_soft_placement=True)) as sess: # Restore parameters sv.saver.restore(sess, tf.train.latest_checkpoint(hp.logdir)) print("Restored!") # Get model mname = open(hp.logdir + '/checkpoint', 'r').read().split('"')[1] # model name timesteps = 100 # Adjust this number as you want outputs1 = np.zeros((hp.num_samples, timesteps, hp.n_mels * hp.r), np.float32) # hp.n_mels*hp.r for j in range(timesteps): _outputs1 = sess.run(g.outputs1, {g.x: X, g.y: outputs1}) outputs1[:, j, :] = _outputs1[:, j, :] outputs2 = sess.run(g.outputs2, {g.outputs1: outputs1}) # Generate wav files if not os.path.exists(hp.outputdir): os.mkdir(hp.outputdir) with codecs.open(hp.outputdir + '/text.txt', 'w', 'utf-8') as fout: for i, (x, s) in enumerate(zip(X, outputs2)): # write text fout.write(str(i) + "\t" + "".join(idx2char[idx] for idx in np.fromstring(x, np.int32) if idx != 0) + "\n") s = restore_shape(s, hp.win_length//hp.hop_length, hp.r) # generate wav files if hp.use_log_magnitude: audio = spectrogram2wav(np.power(np.e, s)**hp.power) else: s = np.where(s < 0, 0, s) audio = spectrogram2wav(s**hp.power) write(hp.outputdir + "/{}_{}.wav".format(mname, i), hp.sr, audio)
def eval(): # Load graph g = Graph(is_training=False) with tf.Session(graph=g.graph) as sess: saver = tf.train.Saver() saver.restore(sess, tf.train.latest_checkpoint(hp.logdir)) print("Restored!") mname = open(hp.logdir + '/checkpoint', 'r').read().split('"')[1] # model name print(mname) # Load data X, Sources, Targets = load_test_data() char2idx, idx2char = load_vocab() with codecs.open(hp.savedir + "/" + mname, "w", "utf-8") as fout: list_of_refs, hypotheses = [], [] for i in range(len(X) // hp.batch_size): # Get mini-batches x = X[i*hp.batch_size: (i+1)*hp.batch_size] # mini-batch sources = Sources[i*hp.batch_size: (i+1)*hp.batch_size] targets = Targets[i*hp.batch_size: (i+1)*hp.batch_size] preds_prev = np.zeros((hp.batch_size, hp.maxlen), np.int32) preds_prev[:, 0] = 2 preds = np.zeros((hp.batch_size, hp.maxlen), np.int32) for j in range(hp.maxlen): # predict next character outs = sess.run(g.preds, {g.x: x, g.decoder_inputs: preds_prev}) # update character sequence if j < hp.maxlen - 1: preds_prev[:, j + 1] = outs[:, j] preds[:, j] = outs[:, j] # Write to file for source, target, pred in zip(sources, targets, preds): # sentence-wise got = "".join(idx2char[idx] for idx in pred).split(u"?")[0] fout.write("- source: " + source +"\n") fout.write("- expected: " + target + "\n") fout.write("- got: " + got + "\n\n") fout.flush() # For bleu score ref = target.split() hypothesis = got.split() if len(ref) > 3 and len(hypothesis) > 3: list_of_refs.append([ref]) hypotheses.append(hypothesis) # Get bleu score score = corpus_bleu(list_of_refs, hypotheses) fout.write("Bleu Score = " + str(100*score))
def eval(): g = Graph(is_training = False) print("MSG : Graph loaded!") X, Sources, Targets = load_data('test') en2idx, idx2en = load_vocab('en.vocab.tsv') de2idx, idx2de = load_vocab('de.vocab.tsv') with g.graph.as_default(): sv = tf.train.Supervisor() with sv.managed_session(config = tf.ConfigProto(allow_soft_placement = True)) as sess: # load pre-train model sv.saver.restore(sess, tf.train.latest_checkpoint(pm.checkpoint)) print("MSG : Restore Model!") mname = open(pm.checkpoint + '/checkpoint', 'r').read().split('"')[1] if not os.path.exists('Results'): os.mkdir('Results') with codecs.open("Results/" + mname, 'w', 'utf-8') as f: list_of_refs, predict = [], [] # Get a batch for i in range(len(X) // pm.batch_size): x = X[i * pm.batch_size: (i + 1) * pm.batch_size] sources = Sources[i * pm.batch_size: (i + 1) * pm.batch_size] targets = Targets[i * pm.batch_size: (i + 1) * pm.batch_size] # Autoregressive inference preds = np.zeros((pm.batch_size, pm.maxlen), dtype = np.int32) for j in range(pm.maxlen): _preds = sess.run(g.preds, feed_dict = {g.inpt: x, g.outpt: preds}) preds[:, j] = _preds[:, j] for source, target, pred in zip(sources, targets, preds): got = " ".join(idx2de[idx] for idx in pred).split("<EOS>")[0].strip() f.write("- Source: {}\n".format(source)) f.write("- Ground Truth: {}\n".format(target)) f.write("- Predict: {}\n\n".format(got)) f.flush() # Bleu Score ref = target.split() prediction = got.split() if len(ref) > pm.word_limit_lower and len(prediction) > pm.word_limit_lower: list_of_refs.append([ref]) predict.append(prediction) score = corpus_bleu(list_of_refs, predict) f.write("Bleu Score = " + str(100 * score))
def eval(): # Load graph g = Graph(is_training=False) print("Graph loaded") # Load data X, Sources, Targets = load_test_data() de2idx, idx2de = load_de_vocab() en2idx, idx2en = load_en_vocab() # X, Sources, Targets = X[:33], Sources[:33], Targets[:33] # Start session with g.graph.as_default(): sv = tf.train.Supervisor() with sv.managed_session(config=tf.ConfigProto(allow_soft_placement=True)) as sess: ## Restore parameters sv.saver.restore(sess, tf.train.latest_checkpoint(hp.logdir)) print("Restored!") ## Get model name mname = open(hp.logdir + '/checkpoint', 'r').read().split('"')[1] # model name ## Inference if not os.path.exists('results'): os.mkdir('results') with codecs.open("results/" + mname, "w", "utf-8") as fout: list_of_refs, hypotheses = [], [] for i in range(len(X) // hp.batch_size): ### Get mini-batches x = X[i*hp.batch_size: (i+1)*hp.batch_size] sources = Sources[i*hp.batch_size: (i+1)*hp.batch_size] targets = Targets[i*hp.batch_size: (i+1)*hp.batch_size] ### Autoregressive inference preds = np.zeros((hp.batch_size, hp.maxlen), np.int32) for j in range(hp.maxlen): _preds = sess.run(g.preds, {g.x: x, g.y: preds}) preds[:, j] = _preds[:, j] ### Write to file for source, target, pred in zip(sources, targets, preds): # sentence-wise got = " ".join(idx2en[idx] for idx in pred).split("</S>")[0].strip() fout.write("- source: " + source +"\n") fout.write("- expected: " + target + "\n") fout.write("- got: " + got + "\n\n") fout.flush() # bleu score ref = target.split() hypothesis = got.split() if len(ref) > 3 and len(hypothesis) > 3: list_of_refs.append([ref]) hypotheses.append(hypothesis) ## Calculate bleu score score = corpus_bleu(list_of_refs, hypotheses) fout.write("Bleu Score = " + str(100*score))
