Merge branch 'master' of git.elphel.com:Elphel/python3-imagej-tiff (39b8eb55) · Commits · Elphel / python3-imagej-tiff

nn_ds_inmem4_tmp.py

+162 −79

Original line number	Original line	Diff line number	Diff line
	#!/usr/bin/env python3		#!/usr/bin/env python3
	from numpy import float64		from numpy import float64
			from _stat import S_IEXEC

	__copyright__ = "Copyright 2018, Elphel, Inc."		__copyright__ = "Copyright 2018, Elphel, Inc."
	__license__ = "GPL-3.0+"		__license__ = "GPL-3.0+"
	@@ -33,17 +34,17 @@ MAX_EPOCH = 500
	#LR = 1e-4 # learning rate		#LR = 1e-4 # learning rate
	LR = 1e-3 # learning rate		LR = 1e-3 # learning rate
	USE_CONFIDENCE = False		USE_CONFIDENCE = False
	ABSOLUTE_DISPARITY = False # True # False		ABSOLUTE_DISPARITY = True # True # False
	DEBUG_PLT_LOSS = True		DEBUG_PLT_LOSS = True
	FEATURES_PER_TILE = 324		FEATURES_PER_TILE = 324
	EPOCHS_TO_RUN = 10000 #0		EPOCHS_TO_RUN = 10000 #0
	RUN_TOT_AVG = 100 # last batches to average. Epoch is 307 training batches		RUN_TOT_AVG = 100 # last batches to average. Epoch is 307 training batches
	BATCH_SIZE = 1000 # Each batch of tiles has balanced D/S tiles, shuffled batches but not inside batches		BATCH_SIZE = 1000 # Each batch of tiles has balanced D/S tiles, shuffled batches but not inside batches
	SHUFFLE_EPOCH = True		SHUFFLE_EPOCH = True
	NET_ARCH = 3 # overwrite with argv?		NET_ARCH = 0 # overwrite with argv?
	#DEBUG_PACK_TILES = True		#DEBUG_PACK_TILES = True
	SUFFIX=str(NET_ARCH)+ (["R","A"][ABSOLUTE_DISPARITY])		SUFFIX=str(NET_ARCH)+ (["R","A"][ABSOLUTE_DISPARITY])
	MAX_TRAIN_FILES_TFR = 4		MAX_TRAIN_FILES_TFR = 6
	#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'
	@@ -211,6 +212,9 @@ def lrelu(x):
	# return tf.nn.relu(x)		# return tf.nn.relu(x)

	def network_fc_simple(input, arch = 0):		def network_fc_simple(input, arch = 0):

			global image_summary_op1

	layouts = {0:[0, 0, 0, 32, 20, 16],		layouts = {0:[0, 0, 0, 32, 20, 16],
	1:[0, 0, 0, 256, 128, 64],		1:[0, 0, 0, 256, 128, 64],
	2:[0, 128, 32, 32, 32, 16],		2:[0, 128, 32, 32, 32, 16],
	@@ -226,9 +230,88 @@ def network_fc_simple(input, arch = 0):
	inp = input		inp = input

	fc.append(slim.fully_connected(inp, num_outs, activation_fn=lrelu,scope='g_fc'+str(i)))		fc.append(slim.fully_connected(inp, num_outs, activation_fn=lrelu,scope='g_fc'+str(i)))
	with tf.variable_scope('g_fc'+str(i)+'/fully_connected',reuse=tf.AUTO_REUSE):
			#with tf.variable_scope('g_fc'+str(i)+'/fully_connected',reuse=tf.AUTO_REUSE):
			with tf.variable_scope('g_fc'+str(i),reuse=tf.AUTO_REUSE):

	w = tf.get_variable('weights',shape=[inp.shape[1],num_outs])		w = tf.get_variable('weights',shape=[inp.shape[1],num_outs])
	b = tf.get_variable('weights',shape=[inp.shape[1],num_outs])		#image = tf.get_variable('w_images',shape=[1, inp.shape[1],num_outs,1])
			if (i==3):

			# red border
			grid = tf.constant([0.1,-0.1,-0.1],dtype=tf.float32,name="GRID")
			#grid = tf.constant([255,100,100],dtype=tf.float32,name="GRID")

			# (325,32)
			wimg_1 = w
			# (32,325)
			wimg_2 = tf.transpose(wimg_1,[1,0])
			# (32,324)
			wimg_3 = wimg_2[:,:-1]

			# res?
			#wimg_res = tf.get_variable('wimg_res',shape=[32(9+1),(9+1)4, 3])

			# long list
			tmp1 = []
			for mi in range(32):
			tmp2 = []
			for mj in range(4):

			s_i = mj*81
			e_i = (mj+1)*81

			tile = tf.reshape(wimg_3[mi,s_i:e_i],shape=(9,9))
			tiles = tf.stack([tile]*3,axis=2)

			#gtiles1 = tf.concat([tiles, tf.reshape(9*[grid],shape=(1,9,3))],axis=0)
			gtiles1 = tf.concat([tiles, tf.expand_dims(9*[grid],0)],axis=0)
			gtiles2 = tf.concat([gtiles1,tf.expand_dims(10*[grid],1)],axis=1)
			tmp2.append(gtiles2)

			ts = tf.concat(tmp2,axis=1)
			tmp1.append(ts)

			image_summary_op2 = tf.concat(tmp1,axis=0)

			#image_summary_op1 = tf.assign(wimg_res,tf.zeros(shape=[32(9+1),(9+1)4, 3],dtype=tf.float32))

			#wimgo1 = tf.zeros(shape=[32(9+1),(9+1)4, 3],dtype=tf.float32)

			#tf.summary.image("wimg_res1",tf.reshape(wimg_res,[1,32(9+1),(9+1)4, 3]))

			#tf.summary.image("wimgo1",tf.reshape(wimgo1,[1,32(9+1),(9+1)4, 3]))
			#tf.summary.image("wimgo2",tf.reshape(wimgo2,[1,32(9+1),(9+1)4, 3]))
			#tf.summary.image("TILE",tf.reshape(gtiles2,[1,10,10,3]))
			#tf.summary.image("STRIPE",tf.reshape(ts,[1,10,40,3]))
			tf.summary.image("W8S",tf.reshape(image_summary_op2,[1,320,40,3]))

			# borders
			#for mi in range(0,wimg_res.shape[0],10):
			# for mj in range(wimg_res.shape[1]):
			# wimg_res[mi,mj].assign([255,255,255])

			#wimg_res[9::(9+1),:].assign([255,0,0])
			#wimg_res[:,9::(9+1)].assign([255,0,0])

			#for mi in range(0,wimg_res.shape[0],10):
			# print(mi)
			#wimg_res = tf.stack([wing_res,])

			#wimg_1 = tf.reshape(w,[1,inp.shape[1],num_outs,1])
			#wimg_1t = tf.transpose(wimg_1,[0,2,1,3])

			# w = w[a,b]
			# wt = w[b,a]
			# for i in range(b):
			# tmp =


			#tf.summary.image("wimg_1",wimg_1)
			#tf.summary.image("wimg_1t",wimg_1t)
			#tf.summary.image("wimg_res1",tf.reshape(wimg_res,[1,32(9+1),(9+1)4, 3]))

			b = tf.get_variable('biases',shape=[num_outs])
	tf.summary.histogram("weights",w)		tf.summary.histogram("weights",w)
	tf.summary.histogram("biases",b)		tf.summary.histogram("biases",b)
	"""		"""
	@@ -247,7 +330,8 @@ def network_fc_simple(input, arch = 0):

	with tf.variable_scope('g_fc_out',reuse=tf.AUTO_REUSE):		with tf.variable_scope('g_fc_out',reuse=tf.AUTO_REUSE):
	w = tf.get_variable('weights',shape=[fc[-1].shape[1],2])		w = tf.get_variable('weights',shape=[fc[-1].shape[1],2])
	b = tf.get_variable('biases',shape=[fc[-1].shape[1],2])		tf.summary.image("wimage",tf.reshape(w,[1,fc[-1].shape[1],2,1]))
			b = tf.get_variable('biases',shape=[2])
	tf.summary.histogram("weights",w)		tf.summary.histogram("weights",w)
	tf.summary.histogram("biases",b)		tf.summary.histogram("biases",b)

	@@ -256,6 +340,7 @@ def network_fc_simple(input, arch = 0):

	with tf.variable_scope('g_fc_out',reuse=tf.AUTO_REUSE):		with tf.variable_scope('g_fc_out',reuse=tf.AUTO_REUSE):
	w = tf.get_variable('weights',shape=[fc[-1].shape[1],1])		w = tf.get_variable('weights',shape=[fc[-1].shape[1],1])
			tf.summary.image("wimage",tf.reshape(w,[1,fc[-1].shape[1],1,1]))
	b = tf.get_variable('biases',shape=[1])		b = tf.get_variable('biases',shape=[1])
	tf.summary.histogram("weights",w)		tf.summary.histogram("weights",w)
	tf.summary.histogram("biases",b)		tf.summary.histogram("biases",b)
	@@ -504,6 +589,8 @@ with tf.Session() as sess:
	# if SHUFFLE_EPOCH:		# if SHUFFLE_EPOCH:
	# dataset_train = dataset_train.shuffle(buffer_size=10000)		# dataset_train = dataset_train.shuffle(buffer_size=10000)

			# RUN TRAIN SESSION

	sess.run(iterator_train.initializer, feed_dict={corr2d_train_placeholder: corr2d_trains[train_file_index],		sess.run(iterator_train.initializer, feed_dict={corr2d_train_placeholder: corr2d_trains[train_file_index],
	target_disparity_train_placeholder: target_disparity_trains[train_file_index],		target_disparity_train_placeholder: target_disparity_trains[train_file_index],
	gt_ds_train_placeholder: gt_ds_trains[train_file_index]})		gt_ds_train_placeholder: gt_ds_trains[train_file_index]})
	@@ -530,6 +617,7 @@ with tf.Session() as sess:
	#train_writer.add_summary(train_summary, i)		#train_writer.add_summary(train_summary, i)
	loss_train_hist[i] = G_loss_trained		loss_train_hist[i] = G_loss_trained
	loss2_train_hist[i] = out_cost1		loss2_train_hist[i] = out_cost1

	except tf.errors.OutOfRangeError:		except tf.errors.OutOfRangeError:
	print("train done at step %d"%(i))		print("train done at step %d"%(i))
	break		break
	@@ -537,10 +625,7 @@ with tf.Session() as sess:
	train_avg = np.average(loss_train_hist).astype(np.float32)		train_avg = np.average(loss_train_hist).astype(np.float32)
	train2_avg = np.average(loss2_train_hist).astype(np.float32)		train2_avg = np.average(loss2_train_hist).astype(np.float32)

	#_,_=sess.run([tf_ph_G_loss,tf_ph_sq_diff],feed_dict={tf_ph_G_loss:train_avg, tf_ph_sq_diff:train2_avg})		# RUN TEST SESSION

	#tf_ph_G_loss = tf.placeholder(tf.float32,shape=None,name='G_loss_avg')
	#tf_ph_sq_diff = tf.placeholder(tf.float32,shape=None,name='sq_diff_avg')

	sess.run(iterator_train.initializer, feed_dict={corr2d_train_placeholder: corr2d_test,		sess.run(iterator_train.initializer, feed_dict={corr2d_train_placeholder: corr2d_test,
	target_disparity_train_placeholder: target_disparity_test,		target_disparity_train_placeholder: target_disparity_test,
	@@ -567,12 +652,10 @@ with tf.Session() as sess:
	print("test done at step %d"%(i))		print("test done at step %d"%(i))
	break		break

	# print_time("%d:%d -> %f"%(epoch,i,G_current))
	test_avg = np.average(loss_test_hist).astype(np.float32)		test_avg = np.average(loss_test_hist).astype(np.float32)
	test2_avg = np.average(loss2_test_hist).astype(np.float32)		test2_avg = np.average(loss2_test_hist).astype(np.float32)

	# _,_=sess.run([tf_ph_G_loss,tf_ph_sq_diff],feed_dict={tf_ph_G_loss:test_avg, tf_ph_sq_diff:test2_avg})		# they include image summaries as well

	train_writer.add_summary(train_summary, epoch)		train_writer.add_summary(train_summary, epoch)
	test_writer.add_summary(test_summary, epoch)		test_writer.add_summary(test_summary, epoch)

Admin message