tensorboard graphs tests (a1c3b782) · Commits · Elphel / python3-imagej-tiff

test_nn_feed.py

+120 −17

Original line number	Original line	Diff line number	Diff line
	@@ -23,6 +23,8 @@ import itertools

	import time		import time

			import matplotlib.pyplot as plt

	#http://stackoverflow.com/questions/287871/print-in-terminal-with-colors-using-python		#http://stackoverflow.com/questions/287871/print-in-terminal-with-colors-using-python
	class bcolors:		class bcolors:
	HEADER = '\033[95m'		HEADER = '\033[95m'
	@@ -45,6 +47,10 @@ VALUES_LAYER_NAME = 'other'
	LAYERS_OF_INTEREST = ['diagm-pair', 'diago-pair', 'hor-pairs', 'vert-pairs']		LAYERS_OF_INTEREST = ['diagm-pair', 'diago-pair', 'hor-pairs', 'vert-pairs']
	RADIUS = 1		RADIUS = 1

			DEBUG_PLT_LOSS = False
			# If false - will not pack or rescal
			DEBUG_PACK_TILES = True

	try:		try:
	src = sys.argv[1]		src = sys.argv[1]
	except IndexError:		except IndexError:
	@@ -214,40 +220,62 @@ def lrelu(x):

	def network(input):		def network(input):

	fc1 = slim.fully_connected(input,101,activation_fn=lrelu,scope='g_fc1')		fc1 = slim.fully_connected(input,2048,activation_fn=lrelu,scope='g_fc1')
	fc2 = slim.fully_connected(fc1, 101,activation_fn=lrelu,scope='g_fc2')		fc2 = slim.fully_connected(fc1, 1024,activation_fn=lrelu,scope='g_fc2')
	fc3 = slim.fully_connected(fc2, 101,activation_fn=lrelu,scope='g_fc3')		fc3 = slim.fully_connected(fc2, 512,activation_fn=lrelu,scope='g_fc3')
	fc4 = slim.fully_connected(fc3, 101,activation_fn=lrelu,scope='g_fc4')		fc4 = slim.fully_connected(fc3, 8,activation_fn=lrelu,scope='g_fc4')
	fc5 = slim.fully_connected(fc4, 2,activation_fn=lrelu,scope='g_fc5')		fc5 = slim.fully_connected(fc4, 4,activation_fn=lrelu,scope='g_fc5')
			fc6 = slim.fully_connected(fc5, 2,activation_fn=lrelu,scope='g_fc6')

	return fc5		return fc6


	sess = tf.Session()		sess = tf.Session()

	in_tile = tf.placeholder(tf.float32,[None,101])		in_tile = tf.placeholder(tf.float32,[None,101])
	gt = tf.placeholder(tf.float32,[None,2])		gt = tf.placeholder(tf.float32,[None,2])


			#losses = tf.get_variable("losses", [None])
			#update_operation = tf.assign(losses,tf.concat([losses,G_loss]))
			#mean_loss = tf.reduce_mean(losses)

			#tf.summary.scalar('gt_value', gt[0])
			#tf.summary.scalar('gt_confidence', gt[1])
			#tf.summary.scalar('gt_value',gt[0,0])

	#cf_cutoff = tf.constant(tf.float32,[None,1])		#cf_cutoff = tf.constant(tf.float32,[None,1])
	out = network(in_tile)		out = network(in_tile)

			#tf.summary.scalar('out_value', out[0,0])
			#tf.summary.scalar('out_confidence', out[1])

	# min cutoff		# min cutoff
	cf_cutoff = 0.173303		cf_cutoff = 0.173303


	cf_w = tf.pow(tf.maximum(gt[:,1]-cf_cutoff,0.0),1)		cf_w = tf.pow(tf.maximum(gt[:,1]-cf_cutoff,0.0),1)
	cf_wsum = tf.reduce_sum(cf_w)		#cf_wsum = tf.reduce_sum(cf_w[~tf.is_nan(cf_w)])
	cf_w_norm = cf_w/cf_wsum		#cf_w_norm = cf_w/cf_wsum
			cf_w_norm = tf.nn.softmax(cf_w)

	#out_cf = out[:,1]		#out_cf = out[:,1]

	G_loss = tf.reduce_mean(tf.abs(out[:,0]-cf_w_norm*gt[:,0]))		G_loss = tf.reduce_mean(tf.abs(tf.nn.softmax(out[:,1])out[:,0]-cf_w_normgt[:,0]))

			tf.summary.scalar('loss', G_loss)
			tf.summary.scalar('prediction', out[0,0])
			tf.summary.scalar('ground truth', gt[0,0])

	t_vars=tf.trainable_variables()		t_vars=tf.trainable_variables()
	lr=tf.placeholder(tf.float32)		lr=tf.placeholder(tf.float32)

	G_opt=tf.train.AdamOptimizer(learning_rate=lr).minimize(G_loss,var_list=[var for var in t_vars if var.name.startswith('g_')])		G_opt=tf.train.AdamOptimizer(learning_rate=lr).minimize(G_loss,var_list=[var for var in t_vars if var.name.startswith('g_')])

	saver=tf.train.Saver()		saver=tf.train.Saver()

			# ?!!!!!
			merged = tf.summary.merge_all()
			train_writer = tf.summary.FileWriter(result_dir + '/train', sess.graph)
			test_writer = tf.summary.FileWriter(result_dir + '/test')

	sess.run(tf.global_variables_initializer())		sess.run(tf.global_variables_initializer())
	ckpt=tf.train.get_checkpoint_state(checkpoint_dir)		ckpt=tf.train.get_checkpoint_state(checkpoint_dir)

	@@ -263,17 +291,37 @@ for folder in allfolders:

	g_loss = np.zeros((packed_tiles.shape[0]*packed_tiles.shape[1],1))		g_loss = np.zeros((packed_tiles.shape[0]*packed_tiles.shape[1],1))

	learning_rate = 1e-4
			recorded_loss = []
			recorded_mean_loss = []

			recorded_gt_d = []
			recorded_gt_c = []

			recorded_pr_d = []
			recorded_pr_c = []

			LR = 1e-4

	print(bcolors.HEADER+"Last Epoch = "+str(lastepoch)+bcolors.ENDC)		print(bcolors.HEADER+"Last Epoch = "+str(lastepoch)+bcolors.ENDC)

			if DEBUG_PLT_LOSS:
			plt.ion() # something about plotting
			plt.figure(1, figsize=(4,12))
			pass




			# RUN

	for epoch in range(lastepoch,1):		for epoch in range(lastepoch,1):
	#for epoch in range(lastepoch,4001):		#for epoch in range(lastepoch,4001):
	if os.path.isdir("result/%04d"%epoch):		if os.path.isdir("result/%04d"%epoch):
	continue		continue
	cnt=0		cnt=0
	if epoch > 2000:		if epoch > 2000:
	learning_rate = 1e-5		LR = 1e-5

	for ind in np.random.permutation(packed_tiles.shape[0]*packed_tiles.shape[1]):		for ind in np.random.permutation(packed_tiles.shape[0]*packed_tiles.shape[1]):

	@@ -313,18 +361,73 @@ for epoch in range(lastepoch,1):
	#print(bcolors.WARNING+"Found NaN, skipping iteration for tile "+str(i)+","+str(j)+bcolors.ENDC)		#print(bcolors.WARNING+"Found NaN, skipping iteration for tile "+str(i)+","+str(j)+bcolors.ENDC)
	pass		pass
	else:		else:
	_,G_current,output = sess.run([G_opt,G_loss,out],feed_dict={in_tile:input_patch,gt:gt_patch,lr:learning_rate})
			run_options = tf.RunOptions(trace_level=tf.RunOptions.FULL_TRACE)
			run_metadata = tf.RunMetadata()

			_,G_current,output,summary = sess.run([G_opt,G_loss,out,merged],feed_dict={in_tile:input_patch,gt:gt_patch,lr:LR},options=run_options,run_metadata=run_metadata)
			#_,G_current,output = sess.run([G_opt,G_loss,out],feed_dict={in_tile:input_patch,gt:gt_patch,lr:LR})

	g_loss[ind]=G_current		g_loss[ind]=G_current
			mean_loss = np.mean(g_loss[np.where(g_loss)])

			if DEBUG_PLT_LOSS:

			recorded_loss.append(G_current)
			recorded_mean_loss.append(mean_loss)

			recorded_pr_d.append(output[0,0])
			recorded_pr_c.append(output[0,1])

			recorded_gt_d.append(gt_patch[0,0])
			recorded_gt_c.append(gt_patch[0,1])

			plt.clf()

	print("%d %d Loss=%.3f CurrentLoss=%.3f Time=%.3f"%(epoch,cnt,np.mean(g_loss[np.where(g_loss)]),G_current,time.time()-st))		plt.subplot(311)

			plt.plot(recorded_loss, label='loss')
			plt.plot(recorded_mean_loss, label='mean loss', color='red')
			plt.xlabel('Iteration')
			plt.ylabel('Loss')
			plt.title("Loss=%.5f, Mean Loss=%.5f"%(G_current,mean_loss), fontdict={'size': 20, 'color': 'red'})
			#plt.text(0.5, 0.5, 'Loss=%.5f' % G_current, fontdict={'size': 20, 'color': 'red'})

			plt.subplot(312)

			plt.xlabel('Iteration')
			plt.ylabel('Disparities')
			plt.plot(recorded_gt_d, label='gt_d',color='green')
			plt.plot(recorded_pr_d, label='pr_d',color='red')
			plt.legend(loc='best',ncol=1)

			plt.subplot(313)

			plt.xlabel('Iteration')
			plt.ylabel('Confidences')
			plt.plot(recorded_gt_c, label='gt_c',color='green')
			plt.plot(recorded_pr_c, label='pr_c',color='red')
			plt.legend(loc='best',ncol=1)

			plt.pause(0.001)

			else:
			print("%d %d Loss=%.3f CurrentLoss=%.3f Time=%.3f"%(epoch,cnt,mean_loss,G_current,time.time()-st))
			train_writer.add_run_metadata(run_metadata, 'step%d' % cnt)

			#test_writer.add_summary(summary,cnt)
			train_writer.add_summary(summary, cnt)

	if epoch%save_freq==0:		if epoch%save_freq==0:
	if not os.path.isdir(result_dir + '%04d'%epoch):		if not os.path.isdir(result_dir + '%04d'%epoch):
	os.makedirs(result_dir + '%04d'%epoch)		os.makedirs(result_dir + '%04d'%epoch)

	saver.save(sess, checkpoint_dir + 'model.ckpt')		saver.save(sess, checkpoint_dir + 'model.ckpt')
			train_writer.close()
			test_writer.close()

	print_time()		print_time()
	print(bcolors.OKGREEN+"time: "+str(time.time())+bcolors.ENDC)		print(bcolors.OKGREEN+"time: "+str(time.time())+bcolors.ENDC)

			plt.ioff()
			plt.show()

test_nn_infer.py

+29 −6

Original line number	Original line	Diff line number	Diff line
	@@ -68,13 +68,14 @@ def lrelu(x):

	def network(input):		def network(input):

	fc1 = slim.fully_connected(input,101,activation_fn=lrelu,scope='g_fc1')		fc1 = slim.fully_connected(input,2048,activation_fn=lrelu,scope='g_fc1')
	fc2 = slim.fully_connected(fc1, 101,activation_fn=lrelu,scope='g_fc2')		fc2 = slim.fully_connected(fc1, 1024,activation_fn=lrelu,scope='g_fc2')
	fc3 = slim.fully_connected(fc2, 101,activation_fn=lrelu,scope='g_fc3')		fc3 = slim.fully_connected(fc2, 512,activation_fn=lrelu,scope='g_fc3')
	fc4 = slim.fully_connected(fc3, 101,activation_fn=lrelu,scope='g_fc4')		fc4 = slim.fully_connected(fc3, 8,activation_fn=lrelu,scope='g_fc4')
	fc5 = slim.fully_connected(fc4, 2,activation_fn=lrelu,scope='g_fc5')		fc5 = slim.fully_connected(fc4, 4,activation_fn=lrelu,scope='g_fc5')
			fc6 = slim.fully_connected(fc5, 2,activation_fn=lrelu,scope='g_fc6')

	return fc5		return fc6


	sess = tf.Session()		sess = tf.Session()
	@@ -147,6 +148,9 @@ for item in tlist:
	packed_tiles = np.array([[pile.pack_tile(tiles[i,j],ptab) for j in range(tiles.shape[1])] for i in range(tiles.shape[0])])		packed_tiles = np.array([[pile.pack_tile(tiles[i,j],ptab) for j in range(tiles.shape[1])] for i in range(tiles.shape[0])])
	packed_tiles = np.dstack((packed_tiles,values[:,:,0]))		packed_tiles = np.dstack((packed_tiles,values[:,:,0]))

			print(packed_tiles.shape)
			print("ENDDD!")

	# flatten		# flatten
	packed_tiles_flat = packed_tiles.reshape(-1, packed_tiles.shape[-1])		packed_tiles_flat = packed_tiles.reshape(-1, packed_tiles.shape[-1])
	values_flat = values.reshape(-1, values.shape[-1])		values_flat = values.reshape(-1, values.shape[-1])
	@@ -160,6 +164,25 @@ for item in tlist:

	print("Output shape: "+str(output.shape))		print("Output shape: "+str(output.shape))

			output_image = np.reshape(output,(tiles.shape[0],tiles.shape[1],-1))
			print(output_image.shape)

			import imagej_tiffwriter

			# 1 prediction
			# 2 ground truth
			# difference 1 - 2

			im1 = output_image[:,:,0]
			im2 = values[:,:,1]
			im3 = im1-im2

			tif = np.dstack((im1,im2,im3))

			imagej_tiffwriter.save('prediction_results.tiff',tif)

			sys.exit(0)

	# so, let's print		# so, let's print
	for i in range(output.shape[0]):		for i in range(output.shape[0]):
	p = output[i,0]		p = output[i,0]

Admin message