global_step refers to the number of batches seen by the graph. Every time a batch is provided, the weights are updated in the direction that minimizes the loss. global_step just keeps track of the number of batches seen so far. When it is passed in the minimize() argument list, the variable is increased by one. … Read more
EDIT: You probably want to give the official %tensorboard magic a go, available from TensorFlow 1.13 onward. Prior to the existence of the %tensorboard magic, the standard way to achieve this was to proxy network traffic to the Colab VM using ngrok. A Colab example can be found here. These are the steps (the code … Read more
When to use? If you’re using compile, surely it must be after load_model(). After all, you need a model to compile. (PS: load_model automatically compiles the model with the optimizer that was saved along with the model) What does compile do? Compile defines the loss function, the optimizer and the metrics. That’s all. It has … Read more
Keras has now added Train / validation split from a single directory using ImageDataGenerator: train_datagen = ImageDataGenerator(rescale=1./255, shear_range=0.2, zoom_range=0.2, horizontal_flip=True, validation_split=0.2) # set validation split train_generator = train_datagen.flow_from_directory( train_data_dir, target_size=(img_height, img_width), batch_size=batch_size, class_mode=”binary”, subset=”training”) # set as training data validation_generator = train_datagen.flow_from_directory( train_data_dir, # same directory as training data target_size=(img_height, img_width), batch_size=batch_size, class_mode=”binary”, subset=”validation”) # … Read more
TL;DR Despite their similar names, these arguments have quite difference meanings. The buffer_size in Dataset.shuffle() can affect the randomness of your dataset, and hence the order in which elements are produced. The buffer_size in Dataset.prefetch() only affects the time it takes to produce the next element. The buffer_size argument in tf.data.Dataset.prefetch() and the output_buffer_size argument … Read more
Try this: with tf.Session() as sess: saver = tf.train.import_meta_graph(‘/tmp/model.ckpt.meta’) saver.restore(sess, “/tmp/model.ckpt”) The TensorFlow save method saves three kinds of files because it stores the graph structure separately from the variable values. The .meta file describes the saved graph structure, so you need to import it before restoring the checkpoint (otherwise it doesn’t know what variables … Read more
It appears that the network hasn’t learned anything in the layers one to three. The last layer does change, so that means that there either may be something wrong with the gradients (if you’re tampering with them manually), you’re constraining learning to the last layer by optimizing only its weights or the last layer really … Read more
Here is what I do to avoid the issues of making the remote server accept your local external IP: when I ssh into the machine, I use the option -L to transfer the port 6006 of the remote server into the port 16006 of my machine (for instance): ssh -L 16006:127.0.0.1:6006 olivier@my_server_ip What it does … Read more
Just type the command you want execute with the user permission, if you don’t want to change the permission: pip3 install –upgrade tensorflow-gpu –user
TL;DR) See this table: https://www.tensorflow.org/install/source#gpu Generally: Check the CUDA version: cat /usr/local/cuda/version.txt and cuDNN version: grep CUDNN_MAJOR -A 2 /usr/local/cuda/include/cudnn.h and install a combination as given below in the images or here. The following images and the link provide an overview of the officially supported/tested combinations of CUDA and TensorFlow on Linux, macOS and Windows: … Read more