mnist : update the README (#498)

diff --git a/examples/mnist/README.md b/examples/mnist/README.md
index 3bb436cb5c144141d28ca6b7763940cf37f0afef..f6b66f74304fdb728eddce3b617f709f3566d298 100644 (file)
--- a/examples/mnist/README.md
+++ b/examples/mnist/README.md
@@ -1,17 +1,93 @@
-# MNIST Example for GGML
+# MNIST Examples for GGML
 
-This is a simple example of how to use GGML for inferencing.
+These are simple examples of how to use GGML for inferencing.
+The first example uses convolutional neural network (CNN), the second one uses fully connected neural network.
 
-## Training the Model
+## Building the examples
+
+```bash
+git clone https://github.com/ggerganov/ggml
+cd ggml
+mkdir build && cd build
+cmake ..
+make -j4 mnist-cnn mnist
+```
+
+## MNIST with CNN
+
+This implementation achieves ~99% accuracy on the MNIST test set.
+
+### Training the model
+
+Use the `mnist-cnn.py` script to train the model and convert it to GGUF format:
+
+```
+$ python3 ../examples/mnist/mnist-cnn.py train mnist-cnn-model
+...
+Keras model saved to 'mnist-cnn-model'
+```
+
+Convert the model to GGUF format:
+
+```
+$ python3 ../examples/mnist/mnist-cnn.py convert mnist-cnn-model
+...
+Model converted and saved to 'mnist-cnn-model.gguf'
+```
+
+### Running the example
+
+```bash
+$ ./bin/mnist-cnn mnist-cnn-model.gguf ../examples/mnist/models/mnist/t10k-images.idx3-ubyte
+main: loaded model in     5.17 ms
+_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 
+_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 
+_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 
+_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 
+_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ * * * * * _ _ _ _ _ _ _ 
+_ _ _ _ _ _ _ _ _ _ _ _ _ _ * * * * * * * * _ _ _ _ _ _ 
+_ _ _ _ _ _ _ _ _ _ _ _ * * * * * _ _ _ * * _ _ _ _ _ _ 
+_ _ _ _ _ _ _ _ _ _ _ _ * * _ _ _ _ _ _ _ _ _ _ _ _ _ _ 
+_ _ _ _ _ _ _ _ _ _ _ * * * _ _ _ _ _ _ _ _ _ _ _ _ _ _ 
+_ _ _ _ _ _ _ _ _ _ _ * * * _ _ _ _ _ _ _ _ * _ _ _ _ _ 
+_ _ _ _ _ _ _ _ _ _ _ * * * _ _ _ _ _ _ _ _ * * _ _ _ _ 
+_ _ _ _ _ _ _ _ _ _ _ * * * _ _ _ _ _ _ _ _ * * _ _ _ _ 
+_ _ _ _ _ _ _ _ _ _ _ _ * * * _ _ _ _ * * * * * _ _ _ _ 
+_ _ _ _ _ _ _ _ _ _ _ _ * * * * * * * * * _ _ _ _ _ _ _ 
+_ _ _ _ _ _ _ _ * * * * * * * * * * _ _ _ _ _ _ _ _ _ _ 
+_ _ _ _ _ _ _ * * * * * * _ _ * * * _ _ _ _ _ _ _ _ _ _ 
+_ _ _ _ _ _ * * * _ _ _ _ _ _ _ * * * _ _ _ _ _ _ _ _ _ 
+_ _ _ _ _ _ * * _ _ _ _ _ _ _ _ _ * * _ _ _ _ _ _ _ _ _ 
+_ _ _ _ _ _ * * _ _ _ _ _ _ _ _ _ * * * _ _ _ _ _ _ _ _ 
+_ _ _ _ _ _ * * _ _ _ _ _ _ _ _ _ * * * _ _ _ _ _ _ _ _ 
+_ _ _ _ _ _ * * * _ _ _ _ _ _ _ _ * * * _ _ _ _ _ _ _ _ 
+_ _ _ _ _ _ _ _ * * * _ _ _ _ _ _ * * * _ _ _ _ _ _ _ _ 
+_ _ _ _ _ _ _ _ _ * * * * * * * * * * _ _ _ _ _ _ _ _ _ 
+_ _ _ _ _ _ _ _ _ _ _ * * * * * * _ _ _ _ _ _ _ _ _ _ _ 
+_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 
+_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 
+_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 
+_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 
+
+ggml_graph_dump_dot: dot -Tpng mnist-cnn.dot -o mnist-cnn.dot.png && open mnist-cnn.dot.png
+main: predicted digit is 8
+```
+
+Computation graph:
+
+![mnist dot](https://user-images.githubusercontent.com/1991296/263763842-3b679b45-7ca1-4ee9-b19a-82e34396624f.png)
+
+## MNIST with fully connected network
+
+A fully connected layer + relu, followed by a fully connected layer + softmax.
+
+### Training the Model
 
 A Google Colab notebook for training a simple two-layer network to recognize digits is located here. You can
 use this to save a pytorch model to be converted to ggml format.
 
 [Colab](https://colab.research.google.com/drive/12n_8VNJnolBnX5dVS0HNWubnOjyEaFSb?usp=sharing)
 
-
-## GGML Format Conversion
-
 GGML "format" is whatever you choose for efficient loading. In our case, we just save the hyperparameters used
 plus the model weights and biases. Run convert-h5-to-ggml.py to convert your pytorch model. The output format is:
 
@@ -24,72 +100,15 @@ plus the model weights and biases. Run convert-h5-to-ggml.py to convert your pyt
 Run ```convert-h5-to-ggml.py mnist_model.state_dict``` where `mnist_model.state_dict` is the saved pytorch model from the Google Colab. For
 quickstart, it is included in the mnist/models directory.
 
-## MNIST Network
-
-The MNIST recognizer network is extremely simple. A fully connected layer + relu, followed by a fully connected layer + softmax. This
-version of the MNIST network doesn't use convolutions.
-
-## Running the example
-
-Here is how to run the example programs:
-
 ```bash
-# Build ggml + examples
-git clone https://github.com/ggerganov/ggml
-cd ggml
-mkdir build && cd build
-cmake ..
-make -j4 mnist
-
-# Generate ggml model
 mkdir -p models/mnist
 python3 ../examples/mnist/convert-h5-to-ggml.py ../examples/mnist/models/mnist/mnist_model.state_dict
-
-# Run the MNIST model
-
-./bin/mnist ./models/mnist/ggml-model-f32.bin ../examples/mnist/models/mnist/t10k-images.idx3-ubyte
 ```
 
-For more information, checkout the corresponding programs in the [examples](examples) folder.
+### Running the example
 
-# Sample output
-
-
-```
-$  ./bin/mnist ./models/mnist/ggml-model-f32.bin ../examples/mnist/models/mnist/t10k-images.idx3-ubyte
-mnist_model_load: loading model from './models/mnist/ggml-model-f32.bin'
-mnist_model_load: ggml ctx size =   1.52 MB
-_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
-_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
-_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
-_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
-_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
-_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
-_ _ _ _ _ _ _ _ _ _ _ _ _ * * _ _ _ _ _ _ _ _ _ _ _ _ _
-_ _ _ _ _ _ _ _ _ _ _ _ * * * * _ _ _ _ _ _ _ _ _ _ _ _
-_ _ _ _ _ _ _ _ _ _ * * * _ _ _ * _ * * _ _ _ _ _ _ _ _
-_ _ _ _ _ _ _ _ _ * * _ _ _ _ _ * _ * _ _ _ _ _ _ _ _ _
-_ _ _ _ _ _ _ _ _ * * _ _ _ _ _ _ * * _ _ _ _ _ _ _ _ _
-_ _ _ _ _ _ _ _ * * _ _ _ _ _ _ * * * * _ _ _ _ _ _ _ _
-_ _ _ _ _ _ _ * * _ _ _ _ _ _ _ * * * * _ _ _ _ _ _ _ _
-_ _ _ _ _ _ _ * * _ _ _ _ _ * * _ _ * * _ _ _ _ _ _ _ _
-_ _ _ _ _ _ _ * * _ _ _ _ * * _ _ _ _ * _ _ _ _ _ _ _ _
-_ _ _ _ _ _ _ * * * * * * _ _ _ _ _ _ * _ _ _ _ _ _ _ _
-_ _ _ _ _ _ _ _ _ * _ _ _ _ _ _ _ _ _ * _ _ _ _ _ _ _ _
-_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ * _ _ _ _ _ _ _ _
-_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ * * _ _ _ _ _ _ _
-_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ * * _ _ _ _ _ _ _
-_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ * * _ _ _ _ _ _ _
-_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ * * _ _ _ _ _ _ _ _
-_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ * * * _ _ _ _ _ _ _ _
-_ _ _ _ _ _ _ _ _ _ _ _ * _ _ * * * _ _ _ _ _ _ _ _ _ _
-_ _ _ _ _ _ _ _ _ _ _ _ * * * * * _ _ _ _ _ _ _ _ _ _ _
-_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
-_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
-_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _
-
-ggml_graph_dump_dot: dot -Tpng mnist.dot -o mnist.dot.png && open mnist.dot.png
-Predicted digit is 9
+```bash
+./bin/mnist ./models/mnist/ggml-model-f32.bin ../examples/mnist/models/mnist/t10k-images.idx3-ubyte
 ```
 
 Computation graph: