onnx: fix pad, unsqueeze (#2317)

* onnx: fix pad, unsqueeze

both implementations have off-by-one errors:
- Pad 'reflect' cycle for eg `dim==3` is `[0,1,2,1]` which has length of
  4 (or `dim*2 - 2`) not 5 (current code `dim*2 - 1`)
- Unsqueeze(-1) for tensor with `dim==3` should be 3 (ie `dim+index+1`)
  not 2 (ie currently `dim+index`)

in addition, Pad is incorrectly calculating the starting padding.
If we want to pad out 2 elements to the start, and we have this cycle
of indices of length 6, then we should skip 4 elements, but currently
we skip 2. A more visual representation of what's going on is below:

```
pad_start: 2
data:      [a,b,c,d]
indices:   [0, 1, 2, 3, 2, 1, 0, 1, 2, 3, 2, 1, 0, ..] // zigzag between 0..4
actual:    skip [ c  d| c  b  a  b]
expected:  ~  skip  ~ [ c  b| a  b  c  d]
```

The values between `[` and `|` are padding and the values between
`|` and `]` in the example should match the original data being padded.

* Fix clippy lints.

---------

Co-authored-by: Laurent <laurent.mazare@gmail.com>

candle-examples/examples/llava/main.rs

@@ -57,7 +57,7 @@ fn load_image<T: AsRef<std::path::Path>>(
     llava_config: &LLaVAConfig,
     dtype: DType,
 ) -> Result<((u32, u32), Tensor)> {
-    let img = image::io::Reader::open(path)?.decode()?;
+    let img = image::ImageReader::open(path)?.decode()?;
     let img_tensor = process_image(&img, processor, llava_config)?;
     Ok(((img.width(), img.height()), img_tensor.to_dtype(dtype)?))
 }