deep-learning

问题 I have a tiff image of size 21 X 513 X 513 where (513, 513) is the height and width of the image containing 21 channels. How can I resize this image to 21 X 500 X 375? I am trying to use PILLOW to do so. But can't figure out if I am doing something wrong. >>> from PIL import Image >>> from tifffile import imread >>> img = Image.open('new.tif') >>> img <PIL.TiffImagePlugin.TiffImageFile image mode=F size=513x513 at 0x7FB0C8E5B940> >>> resized_img = img.resize((500, 375), Image.ANTIALIAS) >>>

问题 I am working in python and tensor flow but I miss 'units' argument and I do not know how to solve it, It looks like your post is mostly code; please add some more details.It looks like your post is mostly code; please add some more details. here the code def createModel(): model = Sequential() # first set of CONV => RELU => MAX POOL layers model.add(Conv2D(32, (3, 3), padding='same', activation='relu', input_shape=inputShape)) model.add(Conv2D(32, (3, 3), activation='relu')) model.add

问题 I am working in python and tensor flow but I miss 'units' argument and I do not know how to solve it, It looks like your post is mostly code; please add some more details.It looks like your post is mostly code; please add some more details. here the code def createModel(): model = Sequential() # first set of CONV => RELU => MAX POOL layers model.add(Conv2D(32, (3, 3), padding='same', activation='relu', input_shape=inputShape)) model.add(Conv2D(32, (3, 3), activation='relu')) model.add

问题 Is the above visualization a rendering of the weights of the first convolutional layer or the activations on a given input image on the first convolutional layer? Below is a visualization of the weights of the first convolutional layer of the Inception v2 model that I've been training for 48 hours: I'm sure I have not converged my model after only 48 hours (on a CPU). Shouldn't those weights begin to smooth out by now, where training accuracy is over 90%? 回答1: According to ImageNet

问题 Is the above visualization a rendering of the weights of the first convolutional layer or the activations on a given input image on the first convolutional layer? Below is a visualization of the weights of the first convolutional layer of the Inception v2 model that I've been training for 48 hours: I'm sure I have not converged my model after only 48 hours (on a CPU). Shouldn't those weights begin to smooth out by now, where training accuracy is over 90%? 回答1: According to ImageNet

问题 I'm currently using the Cross Entropy Loss function but with the imbalance data-set the performance is not great. Is there better lost function? 回答1: It's a very broad subject, but IMHO, you should try focal loss: It was introduced by Tsung-Yi Lin, Priya Goyal, Ross Girshick, Kaiming He and Piotr Dollar to handle imbalance prediction in object detection. Since introduced it was also used in the context of segmentation. The idea of the focal loss is to reduce both loss and gradient for correct

问题 I'm currently using the Cross Entropy Loss function but with the imbalance data-set the performance is not great. Is there better lost function? 回答1: It's a very broad subject, but IMHO, you should try focal loss: It was introduced by Tsung-Yi Lin, Priya Goyal, Ross Girshick, Kaiming He and Piotr Dollar to handle imbalance prediction in object detection. Since introduced it was also used in the context of segmentation. The idea of the focal loss is to reduce both loss and gradient for correct

问题 I have several GPUs but I only want to use one GPU for my training. I am using following options: config = tf.ConfigProto(allow_soft_placement=True, log_device_placement=True) config.gpu_options.allow_growth = True with tf.Session(config=config) as sess: Despite setting / using all these options, all of my GPUs allocate memory and #processes = #GPUs How can I prevent this from happening? Note I do not want use set the devices manually and I do not want to set CUDA_VISIBLE_DEVICES since I want

问题 I have several GPUs but I only want to use one GPU for my training. I am using following options: config = tf.ConfigProto(allow_soft_placement=True, log_device_placement=True) config.gpu_options.allow_growth = True with tf.Session(config=config) as sess: Despite setting / using all these options, all of my GPUs allocate memory and #processes = #GPUs How can I prevent this from happening? Note I do not want use set the devices manually and I do not want to set CUDA_VISIBLE_DEVICES since I want

问题 I have trained a model to predict topic categories using word2vec and an lstm model using keras and got about 98% accuracy during training, I saved the model then loaded it into another file for trying on the test set, I used model.evaluate and model.predict and the results were very different. I'm using keras with tensorflow as a backend, the model summary is: _________________________________________________________________ Layer (type) Output Shape Param # =================================