intro-to-dl
intro-to-dl copied to clipboard
hse-aml
Resources for "Introduction to Deep Learning" course.
I tried running on my local computer `model.fit( x_train2, y_train2, # prepared data batch_size=BATCH_SIZE, epochs=EPOCHS, callbacks=[keras.callbacks.LearningRateScheduler(lr_scheduler), LrHistory(), keras_utils.TqdmProgressCallback(), keras_utils.ModelSaveCallback(model_filename)], validation_data=(x_test2, y_test2), shuffle=True, verbose=0, initial_epoch=last_finished_epoch or 0 )` But it returned...
I'm having problems with week3/week3_task1_first_cnn_cifar10_clean.ipynb One of the last cells tries to access inbound_nodes attribute of LeakyReLU and aparently it doesn't exist anymore TF 1.12.0 Keras 2.2.4 It's extremely easy...
In one of the last cells, ``` model.compile( loss='categorical_crossentropy', # we train 102-way classification optimizer=keras.optimizers.adamax(lr=1e-2), # we can take big lr here because we fixed first layers metrics=['accuracy'] # report...
Which version of anaconda/python should we use? When I install 3.7 I cannot get certain packages to install. When I use 3.6, there are dependency conflicts. EDIT: Just noticed instructions...
Hi there, I face a lot of problem to create the environment. I want to use my GPU as I used to do but here, to run your environment I...
added pip install command for appropriate version Keras to run on colab. This will solve the problem for many MOOC learners.
The original code does not work fine in the Google colab. Please add following code: **!pip install q keras==2.0.6** to these lines of codes: ! shred -u setup_google_colab.py ! wget...
Strangely in RMSProp `w` vector is float while in other blocks it is an int vector
