Local installation: quickstart 2020 - Revision history

Nicola: Feedback from Thomas Sprinkmeier - thanks!

2020-01-13T06:06:19Z

Feedback from Thomas Sprinkmeier - thanks!

← Older revision		Revision as of 06:06, 13 January 2020
Line 26:		Line 26:
	'''Install Tensorflow for machine learning'''		'''Install Tensorflow for machine learning'''

	~~For tensorflow-cpu~~		* conda install tensorflow
			* conda env create -f install/envs/ubuntu.yml or conda env create -f install/envs/windows.yml or conda env create -f install/envs/mac.yml (on a different environment? Take a look at what's in install/envs and find one that's right for you)
	* conda install tensorflow~~-cpu~~
	* conda env create -f install/envs/ubuntu~~-cpu~~.yml

	~~For tensorflow~~-~~gpu~~

	* conda install ~~tensorflow-gpu~~
	* conda env create -f install/envs/~~ubuntu-gpu~~.yml


	'''Install Dingocar'''		'''Install Dingocar'''

Nicola: Tried to merge in stuff from the tall josh page, but now I'm nervous it's all a bit busted.

2020-01-13T02:25:20Z

Tried to merge in stuff from the tall josh page, but now I'm nervous it's all a bit busted.

← Older revision		Revision as of 02:25, 13 January 2020
Line 26:		Line 26:
	'''Install Tensorflow for machine learning'''		'''Install Tensorflow for machine learning'''

	* Ubuntu		For tensorflow-cpu
	** apt-get install -y virtualenv # Note: You may be using a different software installer
	** mkvirtualenv donkeycar -p python3
	** pip install tensorflow~~==1.8.0 # Note: Probably requires Python 3.5 or 3.6. People are having problems with Python 3.7~~
	~~(if you get errors, you can try (re-) installing pip: python -m pip install -~~-~~upgrade pip )~~

	* ~~Debian, if virtualenv isn't there, try this instead~~		* conda install tensorflow-cpu
	** virtualenv donkeycar -~~p python3~~		* conda env create -f install/envs/ubuntu-cpu.yml
	** cd donkeycar
	** export PATH=`pwd`/bin:$PATH		For tensorflow-gpu
	** pip install ~~tensorflow==1.8~~.0
			* conda install tensorflow-gpu
			* conda env create -f install/envs/ubuntu-gpu.yml

	~~(This seems to be v2, but 2019 instructions use 1.8?)~~
	* conda install tensorflow-cpu

	'''Install Dingocar'''		'''Install Dingocar'''

			* conda activate dingo
	* pip install -e ./dingocar		* pip install -e ./dingocar

Line 53:		Line 50:
	Run these commands on your laptop / desktop to train the Neural Network ...		Run these commands on your laptop / desktop to train the Neural Network ...

	* conda ~~donkeycar~~		* conda activate dingo
	* cd ohmc_car		* cd ohmc_car
	* python manage.py train --tub $HOME/ohmc_car/tub_$DATE --model ./models/model_$DATE.hdf5		* python manage.py train --tub $HOME/ohmc_car/tub_$DATE --model ./models/model_$DATE.hdf5

Nicola: Nicola moved page Quickstart guide to Local installation: quickstart 2020: It's not a general quickstart but one for setting up a local environment

2020-01-13T00:47:36Z

Nicola moved page Quickstart guide to Local installation: quickstart 2020: It's not a general quickstart but one for setting up a local environment

← Older revision	Revision as of 00:47, 13 January 2020
(No difference)

Nicola at 11:51, 11 January 2020

2020-01-11T11:51:43Z

← Older revision		Revision as of 11:51, 11 January 2020
Line 53:		Line 53:
	Run these commands on your laptop / desktop to train the Neural Network ...		Run these commands on your laptop / desktop to train the Neural Network ...

	* ~~workon~~ donkeycar ~~# For those who have set-up a virtualenv~~		* conda donkeycar
	* cd ohmc_car		* cd ohmc_car
	* python manage.py train --tub $HOME/ohmc_car/tub_$DATE --model ./models/model_$DATE.hdf5		* python manage.py train --tub $HOME/ohmc_car/tub_$DATE --model ./models/model_$DATE.hdf5

Nicola at 12:01, 28 December 2019

2019-12-28T12:01:10Z

← Older revision		Revision as of 12:01, 28 December 2019
Line 1:		Line 1:
	== Local installation ==		== Local installation ==

			This is trying to be a short setup guide: a minimal guide to what you need to get your Dingocar running. The [https://docs.donkeycar.com/ DonkeyCar docs] have a more complete guide. If you get stuck or need more information, that's the place to go.

	We don't want Python 2, and people have reported problems with Python 3.7 or later. So we currently use Python 3.6.		We don't want Python 2, and people have reported problems with Python 3.7 or later. So we currently use Python 3.6.

Nicola at 11:35, 28 December 2019

2019-12-28T11:35:18Z

← Older revision		Revision as of 11:35, 28 December 2019
Line 1:		Line 1:
			== Local installation ==

	We don't want Python 2, and people have reported problems with Python 3.7 or later. So we currently use Python 3.6.		We don't want Python 2, and people have reported problems with Python 3.7 or later. So we currently use Python 3.6.
Line 45:		Line 46:

	* donkey createcar --path ~/mycar #give your car its own unique name here!		* donkey createcar --path ~/mycar #give your car its own unique name here!

			== Training ==

			Run these commands on your laptop / desktop to train the Neural Network ...

			* workon donkeycar # For those who have set-up a virtualenv
			* cd ohmc_car
			* python manage.py train --tub $HOME/ohmc_car/tub_$DATE --model ./models/model_$DATE.hdf5

			using donkey version: 2.5.7 ...
			loading config file: /Users/andyg/play/ai/roba_car/config.py
			config loaded
			tub_names ./tub_2019-01-15c
			train: 5740, validation: 1436
			steps_per_epoch 44
			Epoch 1/100
			2019-01-21 13:08:49.507048: I tensorflow/core/platform/cpu_feature_guard.cc:140] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA
			43/44 [============================>.] - ETA: 0s - loss: 58.5130 - angle_out_loss: 30.3421 - throttle_out_loss: 86.6839
			Epoch 00001: val_loss improved from inf to 0.19699, saving model to ./models/roba0_2019-01-16c.hdf5
			44/44 [==============================] - 38s 874ms/step - loss: 57.1887 - angle_out_loss: 29.6601 - throttle_out_loss: 84.7172 - val_loss: 0.1970 - val_angle_out_loss: 0.3230 - val_throttle_out_loss: 0.0710

			On a modern laptop, each epoch will take around 30 seconds to complete. For up-to 100 epochs. Typically, you can expect around 20 to 40 epochs before the Neural Network stop learning. That is around 10 to 20 minutes of training time.

			The training command creates the Neural Network weights that represent what your DingoCar has "learned".

Nicola: Created page with " We don't want Python 2, and people have reported problems with Python 3.7 or later. So we currently use Python 3.6. Miniconda instructions: * Go to the [https://repo.contin..."

2019-12-28T11:29:15Z

Created page with " We don't want Python 2, and people have reported problems with Python 3.7 or later. So we currently use Python 3.6. Miniconda instructions: * Go to the [https://repo.contin..."

New page

We don't want Python 2, and people have reported problems with Python 3.7 or later. So we currently use Python 3.6.

Miniconda instructions:

* Go to the [https://repo.continuum.io/miniconda/ Miniconda archive]
* Download Miniconda3-4.5.4 in the right system for you.
* In your command line prompt, go to the directory holding the file
* Run the script: ./Miniconda3-4.5.4-Linux-x86_64.sh (or equivalent)

This will by default add the Miniconda directory to your path. Now you can check you have Python 3.6 installed and available:
* python3 -i
* This should show you Python 3.6.5 | Anaconda Inc.
* Use quit() to get out of the python shell

'''Get Dingocar'''

Go to which directory you like to keep your coding projects in.
* git clone https://github.com/tall-josh/dingocar.git
* cd dingocar
* git checkout master

'''Install Tensorflow for machine learning'''

* Ubuntu
** apt-get install -y virtualenv # Note: You may be using a different software installer
** mkvirtualenv donkeycar -p python3
** pip install tensorflow==1.8.0 # Note: Probably requires Python 3.5 or 3.6. People are having problems with Python 3.7
(if you get errors, you can try (re-) installing pip: python -m pip install --upgrade pip )

* Debian, if virtualenv isn't there, try this instead
** virtualenv donkeycar -p python3
** cd donkeycar
** export PATH=`pwd`/bin:$PATH
** pip install tensorflow==1.8.0

(This seems to be v2, but 2019 instructions use 1.8?)
* conda install tensorflow-cpu

'''Install Dingocar'''

* pip install -e ./dingocar

'''Create an instance for your specific car'''

* donkey createcar --path ~/mycar #give your car its own unique name here!