Lesson 1 Discussion ✅


#689

nice one! thanks!
more info on 1 cycle policy: https://sgugger.github.io/the-1cycle-policy.html


(Sandeep Singh) #691

No, for inference GPU is not needed. CPU’s is good for most of inference on most of trained models.


(Andrew Ayres) #695

nor me, I’m pleased to know this


(Arnab Biswas) #696

This may also be helpful : https://forums.fast.ai/t/platform-gcp/27375


(Jeremy Howard (Admin)) #697

FYI I’ve removed the various questions about setup, since they should go in to the dedicated topics listed in the FAQ. I’ve also removed a lot of the “thanks” etc posts. Hopefully the thread is a little easier to read now.


(Mat M) #699

There are quite a few forum posts on collecting your own images

https://forums.fast.ai/search?q=%22google%20image%22


#700

Validation set


(Marc Carrion) #701

I’m having the same issue with the padding_mode needs to be ‘zeros’ or ‘border’ but got reflection… I’ll try the update of the pytorch as the next posts indicates, see if that works better


(Lankinen) #702

I got this error:

ImportError                               Traceback (most recent call last)
<ipython-input-4-67a75a9cc9b3> in <module>()
      1 # Import necessary libraries
----> 2 from fastai import *
      3 from fastai.vision import *
      4 import matplotlib.pyplot as plt

~/anaconda3/lib/python3.6/site-packages/fastai/__init__.py in <module>()
----> 1 from .basic_train import *
      2 from .callback import *
      3 from .callbacks import *
      4 from .core import *
      5 from .basic_data import *

~/anaconda3/lib/python3.6/site-packages/fastai/basic_train.py in <module>()
      1 "Provides basic training and validation with `Learner`"
----> 2 from .torch_core import *
      3 from .basic_data import *
      4 from .callback import *
      5 

~/anaconda3/lib/python3.6/site-packages/fastai/torch_core.py in <module>()
      1 "Utility functions to help deal with tensors"
----> 2 from .imports.torch import *
      3 from .core import *
      4 
      5 AffineMatrix = Tensor

~/anaconda3/lib/python3.6/site-packages/fastai/imports/__init__.py in <module>()
      1 from .core import *
----> 2 from .torch import *

~/anaconda3/lib/python3.6/site-packages/fastai/imports/torch.py in <module>()
      1 import torch, torch.nn.functional as F
      2 from torch import ByteTensor, DoubleTensor, FloatTensor, HalfTensor, LongTensor, ShortTensor, Tensor
----> 3 from torch import nn, optim, as_tensor
      4 from torch.utils.data import BatchSampler, DataLoader, Dataset, Sampler, TensorDataset

ImportError: cannot import name 'as_tensor'

I have ubuntu local machine. I tested pip install fastai==0.7.0 which worked for some people (ImportError: cannot import name 'as_tensor'?) but not for me.


(Willismar Medeiros) #703

Open a terminal and try this

python3 -c "import torch;from torch import nn, optim, as_tensor"

(Lankinen) #704

File “”, line 1
“import
^
SyntaxError: invalid character in identifier
from: can’t read /var/mail/torch


(Willismar Medeiros) #705

The forum changed the character… its double or single quotes


(Lankinen) #706

Traceback (most recent call last):
File “”, line 1, in
ImportError: cannot import name ‘as_tensor’


(Willismar Medeiros) #707

What pytorch version are you using ?


(Lankinen) #708

pytorch version is 0.3.1


(Pierre Guillou) #709

Hello,

Here is a timeline of the video of the lesson 1 of yesterday (with the links to the corresponding parts in the video).

Welcome

Jeremy Howard

Notebook 1
(https://github.com/fastai/course-v3/blob/master/nbs/dl1/lesson1-pets.ipynb)

  • Step 2: create the model (https://www.youtube.com/watch?v=7hX8yKCX6xM&t=5274)
    – creation of the learn model which contains the neural network architecture and the databunch dataset (we can add the error evaluation metric on the val set as argument if we want)
    – Learning Transfer: we use the parameters of a model already trained to recognize objects in images (resnet34)
    – Overfitting: to check that during his training our model does not specialize on the train set but learns well to recognize the general characteristics of the objects to detect, we use a val set on which we calculate the error (see metric above) in the learn model
  • Step 3: train the model with the fit_one_cycle() method and not fit() as in the previous version of the course (explication of the Leslie Smith paper in the article of @sgugger : The 1cycle policy)

After the break: https://www.youtube.com/watch?v=7hX8yKCX6xM&t=6536

  • Step 4: analyze the predictions made by the model to understand how it works and possibly improve it (https://www.youtube.com/watch?v=7hX8yKCX6xM&t=7922)
    – use of the interp object instantiated by the ClassificationInterpretation.from_learner (learn) method
    – 3 methods to use on the interp object:
    plot_top_losse() to view the images on which the model generates a big error (loss),
    plot_confusion_matrix() which displays the Matrix Confusion,
    most_confused() which publishes the list of labels (classes) predicted with the greatest number of errors

  • Step 5: improve the model (https://www.youtube.com/watch?v=7hX8yKCX6xM&t=8310)
    – find the best Learning Rate with the lr_find() method and then recorder.plot() (to display the loss-vs-lr curve)
    – then use the unfreeze() method on the learn model in order to be able to train all the layers of the resnet34 network and not only those added at the end of the model in order to have an architecture capable of giving a probability for each of the 37 classes … BUT using different Learning Rate according to the layers via learn.fit_one_cycle(2, max_lr=slice(1e-6,1e-4)): the idea is that the first layers do not need to be much modified because they have already been trained to detect simple geometric shapes that are found in all images.

  • Step 6: we can still get a better result (a lower error) by changing the model and using a more complicated (deeper) model like resnet50 (https://www.youtube.com/watch?v=7hX8yKCX6xM&t=9018)


(Lankinen) #710

Thank you @willismar !
Pip wasn’t updating the latest version of pytorch for some reason so I runned this command:
conda install pytorch torchvision -c pytorch
and now it is working! Current version 0.4.1.post2


(Sam) #711

@paul

I am very interested.

Please start one.


(Sam) #712

I use code from this repository:


(Mirodil) #714

How did you fixed this issue?