Super helpful series. Doesn't just tell you how to build SOME PARTICULAR model, but how to build any basic/canned model. Best mini-tutorial I've seen so far.
There is a big mistake in the code shown in the video. The function _parse_csv_rows() is incorrect, it should be def _parse_csv_rows(*vals): soil_type_t = tf.convert_to_tensor(vals[14:54]) feat_vals = vals[:10] + (soil_type_t, vals[54]) features = dict(zip(col_names_features, feat_vals)) class_label = tf.argmax(vals[10:14], axis=0) labels = {col_names_label: class_label} return features, labels where col_names_features, col_names_label are col_names_features = [ "Elevation", "Aspect", "Slope", "Horizontal_Distance_To_Hydrology", "Vertical_Distance_To_Hydrology", "Horizontal_Distance_To_Roadways", "Hillshade_9am", "Hillshade_Noon", "Hillshade_3pm", "Horizontal_Distance_To_Fire_Points", "Soil_Type (40 binary columns)", "Cover_Type (7 types)" ] col_names_label = "Wilderness_Area (4 binary columns)"
There is a bug in the code snippet on Parsing data - 'row_vals' is not defined, this should be replace by ' vals' . Better to share working code and provide links with the video.
Many things to do only for read a datafile. It will be more easy do a function to aggreate all possibilities and the end user set the options in according with your own needs. In fact this demo is useful only if you knows the structure of your data. If you can not open the file with a simple editor you don't know the structure of your data, so you can not setup TF to read the data if you do not know the structure of the data.
Can you tell me how to get each token vector when using both feature column and TF HUB? Because feature column gives average of token vector in a sentence. I am struck with the problem now
my csv files have a string at the end of each row, and this is causing error in my code, how would I setup defaults to account that I have a row of 10 floats and the very last feature is a string?
How can I use model final output to compute a prediction..so that I can compare prediction to ground truth value to compute loss function and fine tune my model
Is this supposed to be TF 2.0? when I issue a print version I get "tensorflow_core._api.v2.version'". Unbelievable how much pain these guys cause, by changing stuff every release. Google... can you please Google the term "backwards compatibility?" I'm just trying to read in a two column csv. I agree it looked great while I was watching it, but its next to useless when I get errors about contrib and enable_eager arnt part of the tf module. Guys please release more of this style, but add more detail around what versions you need and at the end show us 100% of the code.
Building a ML Model is a multi-stage process = ruclips.net/video/oFFbKogYdfc/видео.html 1. Collect data, clean data and process data 2. Prototype and iterate on model arquitecture 3. Train and evaluate results 4. Prepare your model for production serving 5. Repeat all over again
data example and code : github.com/adderbyte/Tensorflow_Tutorials--tf.Slim_GPU_included/blob/master/NewFeaturesTF/TF_DATA_API/Illustrtation_For_Tensorflow2.ipynb
this probably assumes some level of python knowledge. if you don't know what a dictionary is or what the zip function do, I can see how this might get complicated.
data and code : github.com/adderbyte/Tensorflow_Tutorials--tf.Slim_GPU_included/blob/master/NewFeaturesTF/TF_DATA_API/Illustrtation_For_Tensorflow2.ipynb
data example and code: github.com/adderbyte/Tensorflow_Tutorials--tf.Slim_GPU_included/blob/master/NewFeaturesTF/TF_DATA_API/Illustrtation_For_Tensorflow2.ipynb
data and code example here : github.com/adderbyte/Tensorflow_Tutorials--tf.Slim_GPU_included/blob/master/NewFeaturesTF/TF_DATA_API/Illustrtation_For_Tensorflow2.ipynb
data and code : github.com/adderbyte/Tensorflow_Tutorials--tf.Slim_GPU_included/blob/master/NewFeaturesTF/TF_DATA_API/Illustrtation_For_Tensorflow2.ipynb
@@johndoucette3687 I see your point though. Well, the dataset that is being used might matter less than the actual computation and ability to reproduce the learning pipeline. It is not about forest coverage but about how to preprocess, analyse and build an algorithmic pipeline. The aim of the link is to show the pipeline that does similar thing (though the dataset is different). Feel free to use the forest coverage dataset to replace the dataset used in the link and it will be fine. Best Regards.
Super helpful series. Doesn't just tell you how to build SOME PARTICULAR model, but how to build any basic/canned model. Best mini-tutorial I've seen so far.
Thanks this was incredibly well put together easy to understand and so so useful.
Typo in 5:24. 'row_vals' should be 'vals'
Thanks for that. I was wondering were the row_vals came from
You are rite
There is a big mistake in the code shown in the video. The function _parse_csv_rows() is incorrect, it should be
def _parse_csv_rows(*vals):
soil_type_t = tf.convert_to_tensor(vals[14:54])
feat_vals = vals[:10] + (soil_type_t, vals[54])
features = dict(zip(col_names_features, feat_vals))
class_label = tf.argmax(vals[10:14], axis=0)
labels = {col_names_label: class_label}
return features, labels
where col_names_features, col_names_label are
col_names_features = [
"Elevation",
"Aspect",
"Slope",
"Horizontal_Distance_To_Hydrology",
"Vertical_Distance_To_Hydrology",
"Horizontal_Distance_To_Roadways",
"Hillshade_9am",
"Hillshade_Noon",
"Hillshade_3pm",
"Horizontal_Distance_To_Fire_Points",
"Soil_Type (40 binary columns)",
"Cover_Type (7 types)"
]
col_names_label = "Wilderness_Area (4 binary columns)"
What can we do to solve the problem of memory leaking when cooperating tf.keras with tf?
Immaculately described and concise at once. Thank you!
There is a bug in the code snippet on Parsing data - 'row_vals' is not defined, this should be replace by ' vals' . Better to share working code and provide links with the video.
A lot of changes happened in the last 3 years. Maybe some update would be appreciated :-) Thank You!
In Tensorflow updated versions, numpy is removed from tensor, then how we will extract value from that tensor
This is not a very good example as you were using tf.contrib which will soon be deprecated in TensorFlow 2.0.
Many things to do only for read a datafile. It will be more easy do a function to aggreate all possibilities and the end user set the options in according with your own needs. In fact this demo is useful only if you knows the structure of your data. If you can not open the file with a simple editor you don't know the structure of your data, so you can not setup TF to read the data if you do not know the structure of the data.
Can you tell me how to get each token vector when using both feature column and TF HUB? Because feature column gives average of token vector in a sentence. I am struck with the problem now
my csv files have a string at the end of each row, and this is causing error in my code, how would I setup defaults to account that I have a row of 10 floats and the very last feature is a string?
How can I use model final output to compute a prediction..so that I can compare prediction to ground truth value to compute loss function and fine tune my model
Is this supposed to be TF 2.0? when I issue a print version I get "tensorflow_core._api.v2.version'". Unbelievable how much pain these guys cause, by changing stuff every release. Google... can you please Google the term "backwards compatibility?" I'm just trying to read in a two column csv. I agree it looked great while I was watching it, but its next to useless when I get errors about contrib and enable_eager arnt part of the tf module. Guys please release more of this style, but add more detail around what versions you need and at the end show us 100% of the code.
Very good presentation
تحياتي الخالصة شكرا جزيلا
great vedio. Finally tensorflow make some vedio I can unstand. Good job
good vedio
Building a ML Model is a multi-stage process =
ruclips.net/video/oFFbKogYdfc/видео.html
1. Collect data, clean data and process data
2. Prototype and iterate on model arquitecture
3. Train and evaluate results
4. Prepare your model for production serving
5. Repeat all over again
Is this for Tensorflow 2.0?
Please share your code and the data so that we can follow along this great tutorial!
data example and code : github.com/adderbyte/Tensorflow_Tutorials--tf.Slim_GPU_included/blob/master/NewFeaturesTF/TF_DATA_API/Illustrtation_For_Tensorflow2.ipynb
Thank you very much
Good and well presented
looking for coode and examples.
github.com/adderbyte/Tensorflow_Tutorials--tf.Slim_GPU_included/blob/master/NewFeaturesTF/TF_DATA_API/Illustrtation_For_Tensorflow2.ipynb
Excellent presentation!
where are the codes sources?
hello,
thanks for the wonderful explanation of tensorflow usage. Could you please point me to the guide for i/o optimization @5:51 ?
Thank u for this awesome video
Good one, Karmel!
un csv puede contener imagenes?
highly confusing demo
this probably assumes some level of python knowledge. if you don't know what a dictionary is or what the zip function do, I can see how this might get complicated.
tf.contrib.data.CsvDataset is planned to be deprecated. the new API will be tf.data.experimental.CsvDataset
Hi, great tutorial! Any chance to have the code? I am STRUGGLING to start with the data set!!! (8hours later... :( )
SAME! ME WANT GITHUB CODE!
data and code : github.com/adderbyte/Tensorflow_Tutorials--tf.Slim_GPU_included/blob/master/NewFeaturesTF/TF_DATA_API/Illustrtation_For_Tensorflow2.ipynb
Karmel are you sitting down while making this video? JW 😊
Very interesting.
why isn't contrib in TF2.0????
Hi , Great video to learn from :) Will it be possible to get the access of dataset ?
data example and code: github.com/adderbyte/Tensorflow_Tutorials--tf.Slim_GPU_included/blob/master/NewFeaturesTF/TF_DATA_API/Illustrtation_For_Tensorflow2.ipynb
this is tensorflow 1.0 correct?
Please point us to the code and the demo data.
tf.contrib is deprecated now.
Github code ?
how about a little bit of API sugar here?
Good tutorial but no git hub link here to view code
mini-series on TensorFlow high-level APIs! In this 3 part mini-series is in wrong order ... first (I presume should be part 1, not part 3
Github?
please i need code and dataset?good presentation
data and code example here : github.com/adderbyte/Tensorflow_Tutorials--tf.Slim_GPU_included/blob/master/NewFeaturesTF/TF_DATA_API/Illustrtation_For_Tensorflow2.ipynb
you don't show step by step how you import the data gg. GG engineer
Way too much work for something so basic
This should be removed or updated, there is no contrib within TF 2.x
Use tf.data.experimental.CsvDataset
I have created a notebook to follow the video along if anyone is interested: gist.github.com/malkayo/71e483c6f234dd5aca0eaaa52a5c24e0
Very confusing
FIRST :P
Please share your code and the data so that we can follow along this great tutorial!
data: www.kaggle.com/uciml/forest-cover-type-dataset
data and code : github.com/adderbyte/Tensorflow_Tutorials--tf.Slim_GPU_included/blob/master/NewFeaturesTF/TF_DATA_API/Illustrtation_For_Tensorflow2.ipynb
@@simplysmile8573
This link does not seem to have anything to do with this video.
@@johndoucette3687 it is the code implementation of what is discussed in the video. This might help follow the tutorial. I hope this helps.
@@johndoucette3687 I see your point though. Well, the dataset that is being used might matter less than the actual computation and ability to reproduce the learning pipeline. It is not about forest coverage but about how to preprocess, analyse and build an algorithmic pipeline. The aim of the link is to show the pipeline that does similar thing (though the dataset is different). Feel free to use the forest coverage dataset to replace the dataset used in the link and it will be fine. Best Regards.
Please share your code and the data so that we can follow along with this great tutorial!
github.com/adderbyte/Tensorflow_Tutorials--tf.Slim_GPU_included/blob/master/NewFeaturesTF/TF_DATA_API/Illustrtation_For_Tensorflow2.ipynb