georgeyiasemis commited on
Commit
143e207
·
verified ·
1 Parent(s): 6146088

Remove internal checkpoint conversion note from model card

Browse files
Files changed (1) hide show
  1. README.md +1 -9
README.md CHANGED
@@ -30,21 +30,13 @@ built on [vSHARP](https://arxiv.org/abs/2309.09954) inside the
30
 
31
  | File | Role |
32
  |------|------|
33
- | `uniform_vsharp.pt` | **Inference-ready** weights (current DIRECT layout **no remapping**) |
34
  | `uniform_brain.yaml` | Brain inference (default **4×** FastMRIRandom, ACS 0.08) |
35
  | `uniform_knee.yaml` | Knee inference (default **4×** FastMRIEquispaced, ACS 0.08) |
36
  | `uniform_prostate.yaml` | Prostate inference (default **4×** FastMRIEquispaced, ACS 0.08) |
37
  | `uniform_cardiac.yaml` | Cardiac / CMRxRecon inference (default **4×** FastMRIEquispaced, ACS 0.08) |
38
  | `uniform_overview.png` | Overview figure |
39
 
40
- ### Checkpoint note
41
-
42
- `uniform_vsharp.pt` was converted from the original Kosmos training checkpoint
43
- (`model_686000.pt`) to the ModConv U-Net key layout used by current DIRECT, **including**
44
- denoiser `conv_out.bias` tensors. Load it with the shipped YAMLs
45
- (`image_unet_conv_out_bias: true`). You do **not** need
46
- `convert_uniform_checkpoint.py` for Hub weights.
47
-
48
  ## Install DIRECT
49
 
50
  ```bash
 
30
 
31
  | File | Role |
32
  |------|------|
33
+ | `uniform_vsharp.pt` | Pretrained weights use with the YAMLs below |
34
  | `uniform_brain.yaml` | Brain inference (default **4×** FastMRIRandom, ACS 0.08) |
35
  | `uniform_knee.yaml` | Knee inference (default **4×** FastMRIEquispaced, ACS 0.08) |
36
  | `uniform_prostate.yaml` | Prostate inference (default **4×** FastMRIEquispaced, ACS 0.08) |
37
  | `uniform_cardiac.yaml` | Cardiac / CMRxRecon inference (default **4×** FastMRIEquispaced, ACS 0.08) |
38
  | `uniform_overview.png` | Overview figure |
39
 
 
 
 
 
 
 
 
 
40
  ## Install DIRECT
41
 
42
  ```bash