Merge branch 'main' into book-trainin-simplified

candle-book/src/SUMMARY.md

@@ -10,10 +10,10 @@
 
 # Reference Guide
 
-- [Running a model](inference/README.md)
+- [Running a model](inference/inference.md)
     - [Using the hub](inference/hub.md)
 - [Error management](error_manage.md)
-- [Training](training/README.md)
+- [Training](training/training.md)
     - [Simplified](training/simplified.md)
     - [MNIST](training/mnist.md)
     - [Fine-tuning]()

candle-book/src/error_manage.md

@@ -29,7 +29,7 @@ After adding `RUST_BACKTRACE=1`:
 Error: WithBacktrace { inner: ShapeMismatchBinaryOp { lhs: [1, 784], rhs: [1, 784], op: "matmul" }, backtrace: Backtrace [{ fn: "candle::error::Error::bt", file: "/home/nicolas/.cargo/git/checkouts/candle-5bb8ef7e0626d693/f291065/candle-core/src/error.rs", line: 200 }, { fn: "candle::tensor::Tensor::matmul", file: "/home/nicolas/.cargo/git/checkouts/candle-5bb8ef7e0626d693/f291065/candle-core/src/tensor.rs", line: 816 }, { fn: "myapp::main", file: "./src/main.rs", line: 29 }, { fn: "core::ops::function::FnOnce::call_once", file: "/rustc/8ede3aae28fe6e4d52b38157d7bfe0d3bceef225/library/core/src/ops/function.rs", line: 250 }, { fn: "std::sys_common::backtrace::__rust_begin_short_backtrace", file: "/rustc/8ede3aae28fe6e4d52b38157d7bfe0d3bceef225/library/std/src/sys_common/backtrace.rs", line: 135 }, { fn: "std::rt::lang_start::{{closure}}", file: "/rustc/8ede3aae28fe6e4d52b38157d7bfe0d3bceef225/library/std/src/rt.rs", line: 166 }, { fn: "core::ops::function::impls::<impl core::ops::function::FnOnce<A> for &F>::call_once", file: "/rustc/8ede3aae28fe6e4d52b38157d7bfe0d3bceef225/library/core/src/ops/function.rs", line: 284 }, { fn: "std::panicking::try::do_call", file: "/rustc/8ede3aae28fe6e4d52b38157d7bfe0d3bceef225/library/std/src/panicking.rs", line: 500 }, { fn: "std::panicking::try", file: "/rustc/8ede3aae28fe6e4d52b38157d7bfe0d3bceef225/library/std/src/panicking.rs", line: 464 }, { fn: "std::panic::catch_unwind", file: "/rustc/8ede3aae28fe6e4d52b38157d7bfe0d3bceef225/library/std/src/panic.rs", line: 142 }, { fn: "std::rt::lang_start_internal::{{closure}}", file: "/rustc/8ede3aae28fe6e4d52b38157d7bfe0d3bceef225/library/std/src/rt.rs", line: 148 }, { fn: "std::panicking::try::do_call", file: "/rustc/8ede3aae28fe6e4d52b38157d7bfe0d3bceef225/library/std/src/panicking.rs", line: 500 }, { fn: "std::panicking::try", file: "/rustc/8ede3aae28fe6e4d52b38157d7bfe0d3bceef225/library/std/src/panicking.rs", line: 464 }, { fn: "std::panic::catch_unwind", file: "/rustc/8ede3aae28fe6e4d52b38157d7bfe0d3bceef225/library/std/src/panic.rs", line: 142 }, { fn: "std::rt::lang_start_internal", file: "/rustc/8ede3aae28fe6e4d52b38157d7bfe0d3bceef225/library/std/src/rt.rs", line: 148 }, { fn: "std::rt::lang_start", file: "/rustc/8ede3aae28fe6e4d52b38157d7bfe0d3bceef225/library/std/src/rt.rs", line: 165 }, { fn: "main" }, { fn: "__libc_start_main" }, { fn: "_start" }] }
 ```
 
-Not super pretty at the moment, but we can see error occured on `{ fn: "myapp::main", file: "./src/main.rs", line: 29 }`
+Not super pretty at the moment, but we can see error occurred on `{ fn: "myapp::main", file: "./src/main.rs", line: 29 }`
 
 
 Another thing to note, is that since Rust is compiled it is not necessarily as easy to recover proper stacktraces

candle-book/src/guide/hello_world.md

@@ -6,7 +6,7 @@ Open `src/main.rs` and fill in this content:
 
 ```rust
 # extern crate candle_core;
-use candle_core::{DType, Device, Result, Tensor};
+use candle_core::{Device, Result, Tensor};
 
 struct Model {
     first: Tensor,
@@ -25,11 +25,11 @@ fn main() -> Result<()> {
     // Use Device::new_cuda(0)?; to use the GPU.
     let device = Device::Cpu;
 
-    let first = Tensor::zeros((784, 100), DType::F32, &device)?;
-    let second = Tensor::zeros((100, 10), DType::F32, &device)?;
+    let first = Tensor::randn(0f32, 1.0, (784, 100), &device)?;
+    let second = Tensor::randn(0f32, 1.0, (100, 10), &device)?;
     let model = Model { first, second };
 
-    let dummy_image = Tensor::zeros((1, 784), DType::F32, &device)?;
+    let dummy_image = Tensor::randn(0f32, 1.0, (1, 784), &device)?;
 
     let digit = model.forward(&dummy_image)?;
     println!("Digit {digit:?} digit");
@@ -50,7 +50,7 @@ the classical `Linear` layer. We can do as such
 
 ```rust
 # extern crate candle_core;
-# use candle_core::{DType, Device, Result, Tensor};
+# use candle_core::{Device, Result, Tensor};
 struct Linear{
     weight: Tensor,
     bias: Tensor,
@@ -80,7 +80,7 @@ This will change the model running code into a new function
 
 ```rust
 # extern crate candle_core;
-# use candle_core::{DType, Device, Result, Tensor};
+# use candle_core::{Device, Result, Tensor};
 # struct Linear{
 #     weight: Tensor,
 #     bias: Tensor,
@@ -110,15 +110,15 @@ fn main() -> Result<()> {
     let device = Device::cuda_if_available(0)?;
 
     // Creating a dummy model
-    let weight = Tensor::zeros((784, 100), DType::F32, &device)?;
-    let bias = Tensor::zeros((100, ), DType::F32, &device)?;
+    let weight = Tensor::randn(0f32, 1.0, (784, 100), &device)?;
+    let bias = Tensor::randn(0f32, 1.0, (100, ), &device)?;
     let first = Linear{weight, bias};
-    let weight = Tensor::zeros((100, 10), DType::F32, &device)?;
-    let bias = Tensor::zeros((10, ), DType::F32, &device)?;
+    let weight = Tensor::randn(0f32, 1.0, (100, 10), &device)?;
+    let bias = Tensor::randn(0f32, 1.0, (10, ), &device)?;
     let second = Linear{weight, bias};
     let model = Model { first, second };
 
-    let dummy_image = Tensor::zeros((1, 784), DType::F32, &device)?;
+    let dummy_image = Tensor::randn(0f32, 1.0, (1, 784), &device)?;
 
     // Inference on the model
     let digit = model.forward(&dummy_image)?;
@@ -146,7 +146,7 @@ And rewrite our examples using it
 ```rust
 # extern crate candle_core;
 # extern crate candle_nn;
-use candle_core::{DType, Device, Result, Tensor};
+use candle_core::{Device, Result, Tensor};
 use candle_nn::{Linear, Module};
 
 struct Model {
@@ -167,15 +167,15 @@ fn main() -> Result<()> {
     let device = Device::Cpu;
 
     // This has changed (784, 100) -> (100, 784) !
-    let weight = Tensor::zeros((100, 784), DType::F32, &device)?;
-    let bias = Tensor::zeros((100, ), DType::F32, &device)?;
+    let weight = Tensor::randn(0f32, 1.0, (100, 784), &device)?;
+    let bias = Tensor::randn(0f32, 1.0, (100, ), &device)?;
     let first = Linear::new(weight, Some(bias));
-    let weight = Tensor::zeros((10, 100), DType::F32, &device)?;
-    let bias = Tensor::zeros((10, ), DType::F32, &device)?;
+    let weight = Tensor::randn(0f32, 1.0, (10, 100), &device)?;
+    let bias = Tensor::randn(0f32, 1.0, (10, ), &device)?;
     let second = Linear::new(weight, Some(bias));
     let model = Model { first, second };
 
-    let dummy_image = Tensor::zeros((1, 784), DType::F32, &device)?;
+    let dummy_image = Tensor::randn(0f32, 1.0, (1, 784), &device)?;
 
     let digit = model.forward(&dummy_image)?;
     println!("Digit {digit:?} digit");
@@ -188,8 +188,8 @@ Feel free to modify this example to use `Conv2d` to create a classical convnet i
 
 Now that we have the running dummy code we can get to more advanced topics:
 
-- [For PyTorch users](./guide/cheatsheet.md)
-- [Running existing models](./inference/README.md)
-- [Training models](./training/README.md)
+- [For PyTorch users](../guide/cheatsheet.md)
+- [Running existing models](../inference/inference.md)
+- [Training models](../training/training.md)