Pownie/advancedskrald
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Hmm

Browse Source
This commit is contained in:
= 2019-04-10 22:45:49 +02:00
parent bfe38a8a2d
commit deb083224f
2 changed files with 16 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
tensor_classifier.py
View File

@ -1,7 +1,6 @@
from __future__ import absolute_import, division, print_function, unicode_literals from __future__ import absolute_import, division, print_function, unicode_literals
import tensorflow as tf import tensorflow as tf
import tensorflow_datasets as tfds
from tensorflow.python.keras import datasets, layers, models from tensorflow.python.keras import datasets, layers, models
import glob import glob
import numpy as np import numpy as np

21
tmp/tensor.py
View File

@ -1,7 +1,6 @@
from __future__ import absolute_import, division, print_function, unicode_literals from __future__ import absolute_import, division, print_function, unicode_literals
import tensorflow as tf import tensorflow as tf
import tensorflow_datasets as tfds
from tensorflow.python.keras import datasets, layers, models from tensorflow.python.keras import datasets, layers, models
import glob import glob
import numpy as np import numpy as np
@ -30,11 +29,21 @@ for _ in range(10):
training_img.append(cv2.cvtColor(cv2.imread(filename), cv2.COLOR_BGR2GRAY)) training_img.append(cv2.cvtColor(cv2.imread(filename), cv2.COLOR_BGR2GRAY))
training_labels.append(0) training_labels.append(0)
for _ in range(10):
for filename in glob.glob(f"../training_images/bishop/*_square/*.png")[:-50]:
training_img.append(cv2.cvtColor(cv2.imread(filename), cv2.COLOR_BGR2GRAY))
training_labels.append(2)
for _ in range(5): for _ in range(5):
for filename in glob.glob(f"../training_images/rook/*_square/*.png")[-50:]: for filename in glob.glob(f"../training_images/rook/*_square/*.png")[-50:]:
test_img.append(cv2.cvtColor(cv2.imread(filename), cv2.COLOR_BGR2GRAY)) test_img.append(cv2.cvtColor(cv2.imread(filename), cv2.COLOR_BGR2GRAY))
test_labels_.append(1) test_labels_.append(1)
for _ in range(5):
for filename in glob.glob(f"../training_images/bishop/*_square/*.png")[-50:]:
test_img.append(cv2.cvtColor(cv2.imread(filename), cv2.COLOR_BGR2GRAY))
test_labels_.append(2)
for _ in range(5): for _ in range(5):
for filename in glob.glob(f"../training_images/knight/*_square/*.png")[-50:]: for filename in glob.glob(f"../training_images/knight/*_square/*.png")[-50:]:
test_img.append(cv2.cvtColor(cv2.imread(filename), cv2.COLOR_BGR2GRAY)) test_img.append(cv2.cvtColor(cv2.imread(filename), cv2.COLOR_BGR2GRAY))
@ -50,7 +59,9 @@ test_img = np.array(test_img).reshape((len(test_img),width, height, 1))
train_images, test_images = training_img / 255.0, test_img / 255.0 train_images, test_images = training_img / 255.0, test_img / 255.0
model = models.Sequential() model = models.Sequential()
model.add(layers.Conv2D(32, (3, 3), activation='relu', input_shape=(width, height, 1))) model.add(layers.Conv2D(256, (3, 3), activation='relu', input_shape=(width, height, 1)))
model.add(layers.MaxPooling2D((2, 2)))
model.add(layers.Conv2D(128, (3, 3), activation='relu'))
model.add(layers.MaxPooling2D((2, 2))) model.add(layers.MaxPooling2D((2, 2)))
model.add(layers.Conv2D(64, (3, 3), activation='relu')) model.add(layers.Conv2D(64, (3, 3), activation='relu'))
model.add(layers.MaxPooling2D((2, 2))) model.add(layers.MaxPooling2D((2, 2)))
@ -58,7 +69,7 @@ model.add(layers.Conv2D(64, (3, 3), activation='relu'))
model.add(layers.Flatten()) model.add(layers.Flatten())
model.add(layers.Dense(64, activation='relu')) model.add(layers.Dense(64, activation='relu'))
model.add(layers.Dense(2, activation='softmax')) model.add(layers.Dense(3, activation='softmax'))
model.summary() model.summary()
@ -66,12 +77,12 @@ model.compile(optimizer='adam',
loss='sparse_categorical_crossentropy', loss='sparse_categorical_crossentropy',
metrics=['accuracy']) metrics=['accuracy'])
model.fit(train_images, training_labels, epochs=5) model.fit(train_images, training_labels, epochs=10)
test_loss, test_acc = model.evaluate(test_images, test_labels_) test_loss, test_acc = model.evaluate(test_images, test_labels_)
print(test_acc) print(test_acc)
# Save entire model to a HDF5 file # Save entire model to a HDF5 file
model.save('test_chess_model.h5') model.save('chess_model_3_pieces.h5')