Nguyen Nguyen Anh
Nguyen Nguyen Anh
It took small image 0.6s/one object or few second on multiple objects. Not practically usable.
*** Môi trường Ubuntu 18.04 (or whatever), phải install Java JDK chứ không phải JRE vì cần javac cho cái C++ Tokenizer. Các file .yml tự làm cho chuẩn theo...
Hi, I read the paper and it very sounds. I have been trying NVIDIA StyleGanV2-ADA for weeks without success. It simply did not converge and generated images were full of...
I have 2 questions: 1) Can you please share how to train custom dataset (structure of data path) ? 2) Is this model capable to train conditional GAN ? Thanks,...
What exactly does this repo do in practice ? Sorry I am new to this. I tried GAN of all kinds, but very new to this. Are you trying to...
You need to convert alpha as below to make it work with Tensorflow 2. Assuming alpha input as a list: alpha = np.array(alpha).reshape(len(alpha), 1) alpha = tf.convert_to_tensor(alpha, dtype=tf.float32) Steve
I almost give up that it keep posing error after error running with tf.distribute.MirroredStrategy(). ValueError: in user code: :554 train_step * gradients_of_generator = gen_tape.gradient(gen_loss, self.GAN.GM.trainable_variables) C:\Users\ThuSi\AppData\Roaming\Python\Python38\site-packages\tensorflow\python\eager\backprop.py:1064 gradient ** flat_sources =...
I use standard codes from your git. Load BGR fast - preprocess input - resize - predict on batch - rescale... ! from keras_retinanet.utils.image import read_image_bgr, preprocess_image, resize_image from keras_retinanet...
We simply can not INFER because model was saved without network config on it ! Tensorflow 2 is so buggy as the ModelCheckpoint is not designed to save model config....
Hi, Great stuffs really. I walked through your code a lot, but still not sure how to reload weights to continue training should I terminate in the middle for some...