Create textToImage.py

textToImage.py

@@ -0,0 +1,77 @@
+import os, requests, huggingface.dataset
+import tensorflow as tf
+
+PAGES = ['xing', 'pacific', 'gsc', 'rrc']
+
+PAGE_SIZE = 100
+WEIGHTS_PATH = os.path.expanduser('~/.huggingface')
+WEIGHTS_PATH += '/model.h5'
+FLATTENED_PATH = WEIGHTS_PATH + '/flattened'
+BELIEF_PATH = WEIGHTS_PATH + '/belief'
+TRAIN_DIR = os.path.expanduser('~/.huggingface')
++ '/models/nlp-train'
+DEMO_DIR = os.path.expanduser('~/.huggingface')
++ '/models/nlp-demo'
+
+PAGE_DIRS = []
+for page in PAGES:
+    filename = page.replace('-', '_')
+    PAGE_DIRS.append(os.path.expanduser('~/.huggingface') + '/text/{0}/pages'.format(filename))
+
+Y_TO_X = {}
+def add_page(page, dirs):
+    page_dir = dirs[page]
+    assert page_dir is not None
+    train_page, test_page, train_test_ratio, _, _ = huggingface.dataset.read_page(page, page_dir, page_size=PAGE_SIZE)
+    assert train_page is not None
+    assert test_page is not None
+    if train_test_ratio == 0.5:
+        assert train_page.shape == (PAGE_SIZE,)
+        assert test_page.shape == (PAGE_SIZE,)
+    else:
+        assert train_page.shape == (int(train_page.shape[0] * train_test_ratio),)
+        assert test_page.shape == (PAGE_SIZE - int(train_page.shape[0] * train_test_ratio),)
+    X = np.hstack([train_page, test_page])
+    if page in Y_TO_X:
+        Y = Y_TO_X[page]
+    else:
+        Y = list(huggingface.dataset.read_text(page).encode('utf8'))
+        Y_TO_X[page] = Y
+    return X, Y
+
+add_page(xing, PAGE_DIRS)
+add_page(pacific, PAGE_DIRS)
+add_page(gsc, PAGE_DIRS)
+add_page(rrc, PAGE_DIRS)
+
+# load model
+with tf.Session() as sess:
+    model = huggingface.model.load(sess, FLATTENED_PATH, PAGE_DIRS)
+    model.to(sess)
+
+X, Y = np.array(list(map(add_page, PAGES))), []
+
+for page in PAGES:
+    X, Y = np.array(list(map(add_page, PAGES))), list(Y_TO_X[page])
+
+X = np.array(X)
+/ 255.0
+Y = np.array(Y) / 255.0
+X = np.reshape(X, (-1, 100, 200, 1))
+Y = np.reshape(Y, (-1, 10))
+
+model = tf.keras.models.Model(inputs=model.input, outputs=model.output)
+model.compile(optimizer=tf.keras.optimizers.Adam(),
+              loss='categorical_crossentropy',
+              metrics=['accuracy'])
+model.fit(X, Y, batch_size=100, nb_epoch=1000, verbose=2, validation_data=(X, Y))
+model.save_weights(WEIGHTS_PATH)
+
+BELIEF_PATH = WEIGHTS_PATH + '/belief'
+model.compile(optimizer=tf.keras.optimizers.Adam(),
+loss=tf.keras.losses.HuberLoss(delta=0.01))
+model.load_weights(WEIGHTS_PATH)
+model.fit(X, Y, batch_size=10, epochs=1)
+
+NOTE : To know more about why to use Huber loss instead of Mean Square Error follow this link
+Good Luck!