From cb919de96a970ca7454c2dac35282926ce5323a3 Mon Sep 17 00:00:00 2001
From: maali <mahmoud-ahmed.ali@liris.cnrs.fr>
Date: Mon, 13 Mar 2023 14:02:34 +0100
Subject: [PATCH] Update the paths in the training part
---
models.py | 120 ++++++++++++++++++------------------------------------
1 file changed, 40 insertions(+), 80 deletions(-)
diff --git a/models.py b/models.py
index 4934cbd..5552a29 100644
--- a/models.py
+++ b/models.py
@@ -5,6 +5,7 @@ from tensorflow.keras import backend as K
from classes import modelSet, modelDictVal
import random
from data import *
+import argparse
huberDelta = .5
@@ -237,7 +238,8 @@ def stvNetNew(inputShape=(480, 640, 3), outVectors=True, outClasses=True, modelN
return tf.keras.Model(inputs=xIn, outputs=outputs, name=modelName)
-def uNet(inputShape=(480, 640, 3), outVectors=True, outClasses=True, modelName="uNet"): # neural net structure used for image segmentation
+def uNet(inputShape=(480, 640, 3), outVectors=True, outClasses=True,
+ modelName="uNet"): # neural net structure used for image segmentation
xIn = tf.keras.Input(inputShape, dtype=np.dtype('uint8'))
x = tf.keras.layers.Lambda(lambda x: x / 255)(xIn)
@@ -305,7 +307,7 @@ def uNet(inputShape=(480, 640, 3), outVectors=True, outClasses=True, modelName="
return tf.keras.Model(inputs=[xIn], outputs=outputs, name=modelName)
-def trainModel(modelStruct, modelGen, modelClass='cat', batchSize=2, optimizer=tf.keras.optimizers.Adam,
+def trainModel_Fruits(modelStruct, modelGen, modelClass='cat', batchSize=2, optimizer=tf.keras.optimizers.Adam,
learning_rate=0.01, losses=None, metrics=None, saveModel=True, modelName='stvNet_weights',
epochs=1, loss_weights=None, outVectors=False, outClasses=False, dataSplit=True, altLabels=True,
augmentation=True): # train and save model weights
@@ -321,11 +323,12 @@ def trainModel(modelStruct, modelGen, modelClass='cat', batchSize=2, optimizer=t
trainData, validData = None, None
if dataSplit: # if using datasplit, otherwise all available data is used
- trainData, validData = data.getDataSplit(modelClass=modelClass)
+ trainData, validData = data.getDataSplit_Fruits(modelClass=modelClass)
logger = tf.keras.callbacks.CSVLogger("models/history/" + modelName + "_" + modelClass + "_history.csv",
append=True)
- # evalLogger = tf.keras.callbacks.CSVLogger("models/history/" + modelName + "_" + modelClass + "_eval_history.csv", append = True)
+ evalLogger = tf.keras.callbacks.CSVLogger("models/history/" + modelName + "_" + modelClass + "_eval_history.csv",
+ append=True)
history, valHistory = [], []
@@ -336,14 +339,15 @@ def trainModel(modelStruct, modelGen, modelClass='cat', batchSize=2, optimizer=t
print("Epoch {0} of {1}".format(i + 1, epochs))
hist = model.fit(modelGen(modelClass, batchSize, masterList=trainData, out0=outKeys[0], out1=outKeys[1],
altLabels=altLabels, augmentation=augmentation),
- steps_per_epoch=math.ceil(len(trainData) / batchSize), max_queue_size=2,
+ steps_per_epoch=math.ceil(len(trainData)), max_queue_size=2,
callbacks=[logger])
history.append(hist.history)
if dataSplit:
- print("Validation:")
+ print("################ Validation: ############")
valHist = model.evaluate(
- modelGen(modelClass, batchSize, masterList=validData, out0=outKeys[0], out1=outKeys[1],
- altLabels=altLabels, augmentation=False), steps=math.ceil(len(validData) / batchSize),
+ modelGen(modelClass, batchSize, val=True, masterList=validData, out0=outKeys[0],
+ out1=outKeys[1],
+ altLabels=altLabels, augmentation=False), steps=math.ceil(len(validData)),
max_queue_size=2)
valHistory.append(valHist)
else:
@@ -353,13 +357,14 @@ def trainModel(modelStruct, modelGen, modelClass='cat', batchSize=2, optimizer=t
print("Epoch {0} of {1}".format(i + 1, epochs))
hist = model.fit(
modelGen(modelClass, batchSize, masterList=trainData, altLabels=altLabels, augmentation=augmentation),
- steps_per_epoch=math.ceil(len(trainData) / batchSize), max_queue_size=2, callbacks=[logger])
+ steps_per_epoch=math.ceil(len(trainData)), max_queue_size=2, callbacks=[logger])
history.append(hist.history)
if dataSplit:
- print("Validation:")
+ print("########## Validation: ############2")
valHist = model.evaluate(
- modelGen(modelClass, batchSize, masterList=validData, altLabels=altLabels, augmentation=False),
- steps=math.ceil(len(validData) / batchSize), max_queue_size=2)
+ modelGen(modelClass, batchSize, val=True, masterList=validData, altLabels=altLabels,
+ augmentation=False),
+ steps=math.ceil(len(validData)), max_queue_size=2)
valHistory.append(valHist)
historyLog = {"struct": modelStruct.__name__,
@@ -391,11 +396,10 @@ def trainModel(modelStruct, modelGen, modelClass='cat', batchSize=2, optimizer=t
return model
-
-def trainModel_Fruits(modelStruct, modelGen, modelClass='cat', batchSize=2, optimizer=tf.keras.optimizers.Adam,
- learning_rate=0.01, losses=None, metrics=None, saveModel=True, modelName='stvNet_weights',
- epochs=1, loss_weights=None, outVectors=False, outClasses=False, dataSplit=True, altLabels=True,
- augmentation=True): # train and save model weights
+def trainModel(modelStruct, modelGen, modelClass='cat', batchSize=2, optimizer=tf.keras.optimizers.Adam,
+ learning_rate=0.01, losses=None, metrics=None, saveModel=True, modelName='stvNet_weights',
+ epochs=1, loss_weights=None, outVectors=False, outClasses=False, dataSplit=True, altLabels=True,
+ augmentation=True): # train and save model weights
if metrics is None:
metrics = ['accuracy']
if not (outVectors or outClasses):
@@ -427,7 +431,7 @@ def trainModel_Fruits(modelStruct, modelGen, modelClass='cat', batchSize=2, opti
callbacks=[logger])
history.append(hist.history)
if dataSplit:
- print("Validation:")
+ print("############# Validation: ##############")
valHist = model.evaluate(
modelGen(modelClass, batchSize, masterList=validData, out0=outKeys[0], out1=outKeys[1],
altLabels=altLabels, augmentation=False), steps=math.ceil(len(validData) / batchSize),
@@ -443,7 +447,7 @@ def trainModel_Fruits(modelStruct, modelGen, modelClass='cat', batchSize=2, opti
steps_per_epoch=math.ceil(len(trainData) / batchSize), max_queue_size=2, callbacks=[logger])
history.append(hist.history)
if dataSplit:
- print("Validation:")
+ print("############ Validation: ##########2")
valHist = model.evaluate(
modelGen(modelClass, batchSize, masterList=validData, altLabels=altLabels, augmentation=False),
steps=math.ceil(len(validData) / batchSize), max_queue_size=2)
@@ -482,7 +486,7 @@ def trainModels(modelSets, shutDown=False):
for modelSet in modelSets:
print("Training {0}".format(modelSet.name))
model = modelsDict[modelSet.name]
- trainModel(model.structure, model.generator, modelClass=modelSet.modelClass, epochs=model.epochs,
+ trainModel_Fruits(model.structure, model.generator, modelClass=modelSet.modelClass, epochs=model.epochs,
losses=model.losses, modelName=modelSet.name, outClasses=model.outClasses,
outVectors=model.outVectors, learning_rate=model.lr, metrics=model.metrics,
altLabels=model.altLabels, augmentation=model.augmentation)
@@ -501,7 +505,7 @@ def evaluateModel(modelStruct, modelName, evalGen, modelClass='cat', outVectors=
metrics = ['accuracy']
model = tf.keras.models.load_model(
os.path.dirname(os.path.realpath(__file__)) + '/models/' + modelName + '_' + modelClass)
- model.evaluate(evalGen(modelClass, batchSize), steps=samples // batchSize)
+ model.evaluate(evalGen(modelClass, batchSize), steps=samples, val=True)
def evaluateModels(modelSets, batchSize=2, dataSplit=True):
@@ -516,13 +520,13 @@ def evaluateModels(modelSets, batchSize=2, dataSplit=True):
model.evaluate(
modelEnt.generator(modelSet.modelClass, batchSize=batchSize, masterList=validData, out0=outKeys[0],
out1=outKeys[1], altLabels=modelEnt.altLabels, augmentation=False),
- steps=math.ceil(len(validData) / batchSize), max_queue_size=2)
+ steps=math.ceil(len(validData)), max_queue_size=2)
else:
raise Exception("Probably shouldn't be here ever..")
else:
- model.evaluate(modelEnt.generator(modelSet.modelClass, batchSize=batchSize, masterList=validData,
+ model.evaluate(modelEnt.generator(modelSet.modelClass, val=True, batchSize=batchSize, masterList=validData,
altLabels=modelEnt.altLabels, augmentation=False),
- steps=math.ceil(len(validData) / batchSize), max_queue_size=2)
+ steps=math.ceil(len(validData)), max_queue_size=2)
def trainModelClassGen(modelStruct, modelName, losses, modelClass='cat', batchSize=2,
@@ -666,70 +670,26 @@ class generatorClass: # simulates generator behaviour, unused
output[self.outVecName] = np.array(yCoordBatch)
if self.outClasses:
output[self.outClassName] = np.array(yClassBatch)
- return (False, np.array(xBatch), output)
+ return False, np.array(xBatch), output
modelsDict = {
'uNet_classes': modelDictVal(uNet, data.classTrainingGenerator, tf.keras.losses.BinaryCrossentropy(), False, True,
- epochs=20, lr=0.001, augmentation=False),
- 'uNet_coords': modelDictVal(uNet, data.coordsTrainingGenerator, tf.keras.losses.Huber(), True, False, epochs=5,
- lr=0.001, metrics=['mae', 'mse']),
- 'uNet_coords_smooth': modelDictVal(uNet, data.coordsTrainingGenerator, smoothL1, True, False, epochs=3, lr=0.0001,
- metrics=['mae', 'mse']),
- 'stvNet': modelDictVal(stvNet, data.combinedTrainingGenerator,
- {'coordsOut': tf.keras.losses.Huber(), 'classOut': tf.keras.losses.BinaryCrossentropy()},
- True, True, epochs=5, lr=0.00005,
- metrics={'coordsOut': ['mae', 'mse'], "classOut": ['accuracy']}),
- 'stvNet_coords_slow_learner': modelDictVal(stvNet, data.coordsTrainingGenerator, tf.keras.losses.Huber(), True,
- False, epochs=40, lr=0.00001, metrics=['mae', 'mse'],
- outVecName='coordsOut'),
- 'stvNetAltLabels': modelDictVal(stvNet, data.combinedTrainingGenerator, {'coordsOut': tf.keras.losses.Huber(),
- 'classOut': tf.keras.losses.BinaryCrossentropy()},
- True, True, epochs=10, lr=0.001,
- metrics={'coordsOut': ['mae', 'mse'], "classOut": ['accuracy']}, altLabels=True,
- augmentation=True),
- 'stvNetNormLabels': modelDictVal(stvNet, data.combinedTrainingGenerator, {'coordsOut': tf.keras.losses.Huber(),
- 'classOut': tf.keras.losses.BinaryCrossentropy()},
- True, True, epochs=10, lr=0.001,
- metrics={'coordsOut': ['mae', 'mse'], "classOut": ['accuracy']}, altLabels=False,
- augmentation=True),
- 'stvNet_coords': modelDictVal(stvNet, data.coordsTrainingGenerator, tf.keras.losses.Huber(), True, False, epochs=20,
- lr=0.001, metrics=['mae', 'mse'], altLabels=False, augmentation=True),
- 'stvNet_coords_altLabels': modelDictVal(stvNet, data.coordsTrainingGenerator, tf.keras.losses.Huber(), True, False,
- epochs=20, lr=0.001, metrics=['mae', 'mse'], altLabels=True,
- augmentation=True),
- 'stvNet_coords_altLabels_noAug': modelDictVal(stvNet, data.coordsTrainingGenerator, tf.keras.losses.Huber(), True,
- False, epochs=20, lr=0.001, metrics=['mae', 'mse'], altLabels=True,
- augmentation=False),
- 'stvNet_coords_noAug': modelDictVal(stvNet, data.coordsTrainingGenerator, tf.keras.losses.Huber(), True, False,
- epochs=20, lr=0.001, metrics=['mae', 'mse'], altLabels=False,
- augmentation=False),
- 'stvNet_classes': modelDictVal(stvNet, data.classTrainingGenerator, tf.keras.losses.BinaryCrossentropy(), False,
- True, epochs=10, lr=0.001, altLabels=False, augmentation=True),
- 'stvNet_classes_noAug': modelDictVal(stvNet, data.classTrainingGenerator, tf.keras.losses.BinaryCrossentropy(),
- False, True, epochs=10, lr=0.001, altLabels=False, augmentation=False),
- 'stvNet_new_coords_alt': modelDictVal(stvNetNew, data.coordsTrainingGenerator, tf.keras.losses.Huber(), True, False,
- epochs=20, lr=0.001, metrics=['mae', 'mse'], altLabels=True,
- augmentation=False),
+ epochs=50, lr=0.0001, augmentation=True),
+
'stvNet_new_coords': modelDictVal(stvNetNew, data.coordsTrainingGenerator, tf.keras.losses.Huber(), True, False,
- epochs=20, lr=0.001, metrics=['mae', 'mse'], altLabels=False, augmentation=False),
- 'stvNet_new_coords_alt_aug': modelDictVal(stvNetNew, data.coordsTrainingGenerator, tf.keras.losses.Huber(), True,
- False, epochs=20, lr=0.001, metrics=['mae', 'mse'], altLabels=True,
- augmentation=True),
- 'stvNet_new_coords_aug': modelDictVal(stvNetNew, data.coordsTrainingGenerator, tf.keras.losses.Huber(), True, False,
- epochs=20, lr=0.001, metrics=['mae', 'mse'], altLabels=False,
- augmentation=True),
- 'stvNet_new_classes': modelDictVal(stvNetNew, data.classTrainingGenerator, tf.keras.losses.BinaryCrossentropy(),
- False, True, epochs=20, lr=0.001, augmentation=False),
- 'stvNet_new_combined': modelDictVal(stvNetNew, data.combinedTrainingGenerator,
- {'coordsOut': tf.keras.losses.Huber(),
- 'classOut': tf.keras.losses.BinaryCrossentropy()}, True, True, epochs=20,
- lr=0.001, metrics={'coordsOut': ['mae', 'mse'], "classOut": ['accuracy']},
- augmentation=False),
+ epochs=50, lr=0.0001, metrics=['mae', 'mse'], altLabels=False, augmentation=False)
}
if __name__ == "__main__":
- class_name = 'pear'
+ ap = argparse.ArgumentParser()
+ ap.add_argument("-cls_name", "--class_name", type=str,
+ default='kiwi1',
+ help="[kiwi1, pear2, banana1, orange, peach1]")
+
+ args = vars(ap.parse_args())
+
+ class_name = args["class_name"]
modelSets = [modelSet('uNet_classes', class_name), modelSet('stvNet_new_coords', class_name)]
trainModels(modelSets)
evaluateModels(modelSets)
--
GitLab