v0.32.0

See https://github.com/quic/ai-hub-models/releases/v0.32.0 for changelog.

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+DEPLOYMENT_MODEL_LICENSE.pdf filter=lfs diff=lfs merge=lfs -text

DEPLOYMENT_MODEL_LICENSE.pdf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4409f93b0e82531303b3e10f52f1fdfb56467a25f05b7441c6bbd8bb8a64b42c
+size 109629

First-Order-Motion-Model_FOMMDetector.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90ac69c9eaf6cffa659b09e40b0e3f27e841e0859d9b2ae2dc9103c14c9d67ad
-size 56881890
+oid sha256:2675963be1f3e81a82e211fb4b91e152162caee5276e17ab10d39d0e2962f5d4
+size 56883359

First-Order-Motion-Model_FOMMGenerator.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d2081f3e5bc5c96c6813ef69cbc0db9de2b20cca150085cf659f18933e00ff08
-size 182680467
+oid sha256:c5bbfecce0dc4f3039d07d8309aa71c7c8f3efc0c47963afab53073130be4577
+size 182685287

LICENSE

@@ -0,0 +1,2 @@
+The license of the original trained model can be found at https://github.com/AliaksandrSiarohin/first-order-model/blob/master/LICENSE.md.
+The license for the deployable model files (.tflite, .onnx, .dlc, .bin, etc.) can be found in DEPLOYMENT_MODEL_LICENSE.pdf.

README.md

@@ -29,21 +29,19 @@ More details on model performance across various devices, can be found
 - **Model Stats:**
   - Model checkpoint: vox-256
   - Input resolution: 256x256
-  - Number of parameters (FOMM_KpDetector): 14.3M
-  - Model size (FOMM_KpDetector): 54.5 MB
-  - Number of parameters (FOMM_Generator): 45.7M
-  - Model size (FOMM_Generator): 174 MB
+  - Model size (FOMMDetector) (float): 54.2 MB
+  - Model size (FOMMGenerator) (float): 174 MB
 
 | Model | Precision | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit | Target Model
 |---|---|---|---|---|---|---|---|---|
-| FOMMDetector | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 4.765 ms | 0 - 80 MB | NPU | [First-Order-Motion-Model.onnx](https://huggingface.co/qualcomm/First-Order-Motion-Model/blob/main/First-Order-Motion-Model.onnx) |
-| FOMMDetector | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 3.516 ms | 0 - 22 MB | NPU | [First-Order-Motion-Model.onnx](https://huggingface.co/qualcomm/First-Order-Motion-Model/blob/main/First-Order-Motion-Model.onnx) |
-| FOMMDetector | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 3.225 ms | 1 - 18 MB | NPU | [First-Order-Motion-Model.onnx](https://huggingface.co/qualcomm/First-Order-Motion-Model/blob/main/First-Order-Motion-Model.onnx) |
-| FOMMDetector | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 4.98 ms | 27 - 27 MB | NPU | [First-Order-Motion-Model.onnx](https://huggingface.co/qualcomm/First-Order-Motion-Model/blob/main/First-Order-Motion-Model.onnx) |
-| FOMMGenerator | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 26.631 ms | 11 - 235 MB | NPU | [First-Order-Motion-Model.onnx](https://huggingface.co/qualcomm/First-Order-Motion-Model/blob/main/First-Order-Motion-Model.onnx) |
-| FOMMGenerator | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 18.776 ms | 20 - 77 MB | NPU | [First-Order-Motion-Model.onnx](https://huggingface.co/qualcomm/First-Order-Motion-Model/blob/main/First-Order-Motion-Model.onnx) |
-| FOMMGenerator | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 18.656 ms | 1 - 69 MB | NPU | [First-Order-Motion-Model.onnx](https://huggingface.co/qualcomm/First-Order-Motion-Model/blob/main/First-Order-Motion-Model.onnx) |
-| FOMMGenerator | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 24.695 ms | 89 - 89 MB | NPU | [First-Order-Motion-Model.onnx](https://huggingface.co/qualcomm/First-Order-Motion-Model/blob/main/First-Order-Motion-Model.onnx) |
+| FOMMDetector | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 4.822 ms | 0 - 78 MB | NPU | [First-Order-Motion-Model.onnx](https://huggingface.co/qualcomm/First-Order-Motion-Model/blob/main/First-Order-Motion-Model.onnx) |
+| FOMMDetector | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 3.548 ms | 0 - 24 MB | NPU | [First-Order-Motion-Model.onnx](https://huggingface.co/qualcomm/First-Order-Motion-Model/blob/main/First-Order-Motion-Model.onnx) |
+| FOMMDetector | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 3.169 ms | 1 - 18 MB | NPU | [First-Order-Motion-Model.onnx](https://huggingface.co/qualcomm/First-Order-Motion-Model/blob/main/First-Order-Motion-Model.onnx) |
+| FOMMDetector | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 4.944 ms | 28 - 28 MB | NPU | [First-Order-Motion-Model.onnx](https://huggingface.co/qualcomm/First-Order-Motion-Model/blob/main/First-Order-Motion-Model.onnx) |
+| FOMMGenerator | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 26.01 ms | 12 - 200 MB | NPU | [First-Order-Motion-Model.onnx](https://huggingface.co/qualcomm/First-Order-Motion-Model/blob/main/First-Order-Motion-Model.onnx) |
+| FOMMGenerator | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 19.155 ms | 20 - 75 MB | NPU | [First-Order-Motion-Model.onnx](https://huggingface.co/qualcomm/First-Order-Motion-Model/blob/main/First-Order-Motion-Model.onnx) |
+| FOMMGenerator | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 15.895 ms | 14 - 81 MB | NPU | [First-Order-Motion-Model.onnx](https://huggingface.co/qualcomm/First-Order-Motion-Model/blob/main/First-Order-Motion-Model.onnx) |
+| FOMMGenerator | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 25.374 ms | 89 - 89 MB | NPU | [First-Order-Motion-Model.onnx](https://huggingface.co/qualcomm/First-Order-Motion-Model/blob/main/First-Order-Motion-Model.onnx) |
 
 
 
@@ -108,7 +106,7 @@ FOMMDetector
 Device                          : cs_8_gen_2 (ANDROID 13)             
 Runtime                         : ONNX                                
 Estimated inference time (ms)   : 4.8                                 
-Estimated peak memory usage (MB): [0, 80]                             
+Estimated peak memory usage (MB): [0, 78]                             
 Total # Ops                     : 56                                  
 Compute Unit(s)                 : npu (56 ops) gpu (0 ops) cpu (0 ops)
 
@@ -116,8 +114,8 @@ Compute Unit(s)                 : npu (56 ops) gpu (0 ops) cpu (0 ops)
 FOMMGenerator
 Device                          : cs_8_gen_2 (ANDROID 13)               
 Runtime                         : ONNX                                  
-Estimated inference time (ms)   : 26.6                                  
-Estimated peak memory usage (MB): [11, 235]                             
+Estimated inference time (ms)   : 26.0                                  
+Estimated peak memory usage (MB): [12, 200]                             
 Total # Ops                     : 150                                   
 Compute Unit(s)                 : npu (138 ops) gpu (0 ops) cpu (12 ops)
 ```