initial release

ggml/examples/yolo/CMakeLists.txt

@@ -0,0 +1,6 @@
+#
+# yolov3-tiny
+
+set(TEST_TARGET yolov3-tiny)
+add_executable(${TEST_TARGET} yolov3-tiny.cpp yolo-image.cpp)
+target_link_libraries(${TEST_TARGET} PRIVATE ggml common)

ggml/examples/yolo/README.md

@@ -0,0 +1,59 @@
+This example shows how to implement YOLO object detection with ggml using pretrained model.
+
+# YOLOv3-tiny
+
+Download the model weights:
+
+```bash
+$ wget https://pjreddie.com/media/files/yolov3-tiny.weights
+$ sha1sum yolov3-tiny.weights 
+40f3c11883bef62fd850213bc14266632ed4414f  yolov3-tiny.weights
+```
+
+Convert the weights to GGUF format:
+
+```bash
+$ ./convert-yolov3-tiny.py yolov3-tiny.weights
+yolov3-tiny.weights converted to yolov3-tiny.gguf
+```
+
+Alternatively, you can download the converted model from [HuggingFace](https://huggingface.co/rgerganov/yolo-gguf/resolve/main/yolov3-tiny.gguf)
+
+Object detection:
+
+```bash
+$ wget https://raw.githubusercontent.com/pjreddie/darknet/master/data/dog.jpg
+$ ./yolov3-tiny -m yolov3-tiny.gguf -i dog.jpg
+load_model: using CUDA backend
+ggml_cuda_init: GGML_CUDA_FORCE_MMQ:    no
+ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
+ggml_cuda_init: found 1 CUDA devices:
+  Device 0: NVIDIA T1200 Laptop GPU, compute capability 7.5, VMM: yes
+Layer  0 output shape:  416 x 416 x   16 x   1
+Layer  1 output shape:  208 x 208 x   16 x   1
+Layer  2 output shape:  208 x 208 x   32 x   1
+Layer  3 output shape:  104 x 104 x   32 x   1
+Layer  4 output shape:  104 x 104 x   64 x   1
+Layer  5 output shape:   52 x  52 x   64 x   1
+Layer  6 output shape:   52 x  52 x  128 x   1
+Layer  7 output shape:   26 x  26 x  128 x   1
+Layer  8 output shape:   26 x  26 x  256 x   1
+Layer  9 output shape:   13 x  13 x  256 x   1
+Layer 10 output shape:   13 x  13 x  512 x   1
+Layer 11 output shape:   13 x  13 x  512 x   1
+Layer 12 output shape:   13 x  13 x 1024 x   1
+Layer 13 output shape:   13 x  13 x  256 x   1
+Layer 14 output shape:   13 x  13 x  512 x   1
+Layer 15 output shape:   13 x  13 x  255 x   1
+Layer 18 output shape:   13 x  13 x  128 x   1
+Layer 19 output shape:   26 x  26 x  128 x   1
+Layer 20 output shape:   26 x  26 x  384 x   1
+Layer 21 output shape:   26 x  26 x  256 x   1
+Layer 22 output shape:   26 x  26 x  255 x   1
+dog: 57%
+car: 52%
+truck: 56%
+car: 62%
+bicycle: 59%
+Detected objects saved in 'predictions.jpg' (time: 0.057000 sec.)
+```

ggml/examples/yolo/convert-yolov3-tiny.py

@@ -0,0 +1,53 @@
+#!/usr/bin/env python3
+import sys
+import gguf
+import numpy as np
+
+def save_conv2d_layer(f, gguf_writer, prefix, inp_c, filters, size, batch_normalize=True):
+    biases = np.fromfile(f, dtype=np.float32, count=filters)
+    gguf_writer.add_tensor(prefix + "_biases", biases, raw_shape=(1, filters, 1, 1))
+
+    if batch_normalize:
+        scales = np.fromfile(f, dtype=np.float32, count=filters)
+        gguf_writer.add_tensor(prefix + "_scales", scales, raw_shape=(1, filters, 1, 1))
+        rolling_mean = np.fromfile(f, dtype=np.float32, count=filters)
+        gguf_writer.add_tensor(prefix + "_rolling_mean", rolling_mean, raw_shape=(1, filters, 1, 1))
+        rolling_variance = np.fromfile(f, dtype=np.float32, count=filters)
+        gguf_writer.add_tensor(prefix + "_rolling_variance", rolling_variance, raw_shape=(1, filters, 1, 1))
+
+    weights_count = filters * inp_c * size * size
+    l0_weights = np.fromfile(f, dtype=np.float32, count=weights_count)
+    ## ggml doesn't support f32 convolution yet, use f16 instead
+    l0_weights = l0_weights.astype(np.float16)
+    gguf_writer.add_tensor(prefix + "_weights", l0_weights, raw_shape=(filters, inp_c, size, size))
+
+
+if __name__ == '__main__':
+    if len(sys.argv) != 2:
+        print("Usage: %s <yolov3-tiny.weights>" % sys.argv[0])
+        sys.exit(1)
+    outfile = 'yolov3-tiny.gguf'
+    gguf_writer = gguf.GGUFWriter(outfile, 'yolov3-tiny')
+
+    f = open(sys.argv[1], 'rb')
+    f.read(20) # skip header
+    save_conv2d_layer(f, gguf_writer, "l0", 3, 16, 3)
+    save_conv2d_layer(f, gguf_writer, "l1", 16, 32, 3)
+    save_conv2d_layer(f, gguf_writer, "l2", 32, 64, 3)
+    save_conv2d_layer(f, gguf_writer, "l3", 64, 128, 3)
+    save_conv2d_layer(f, gguf_writer, "l4", 128, 256, 3)
+    save_conv2d_layer(f, gguf_writer, "l5", 256, 512, 3)
+    save_conv2d_layer(f, gguf_writer, "l6", 512, 1024, 3)
+    save_conv2d_layer(f, gguf_writer, "l7", 1024, 256, 1)
+    save_conv2d_layer(f, gguf_writer, "l8", 256, 512, 3)
+    save_conv2d_layer(f, gguf_writer, "l9", 512, 255, 1, batch_normalize=False)
+    save_conv2d_layer(f, gguf_writer, "l10", 256, 128, 1)
+    save_conv2d_layer(f, gguf_writer, "l11", 384, 256, 3)
+    save_conv2d_layer(f, gguf_writer, "l12", 256, 255, 1, batch_normalize=False)
+    f.close()
+    
+    gguf_writer.write_header_to_file()
+    gguf_writer.write_kv_data_to_file()
+    gguf_writer.write_tensors_to_file()
+    gguf_writer.close()
+    print("{} converted to {}".format(sys.argv[1], outfile))

ggml/examples/yolo/data/coco.names

@@ -0,0 +1,80 @@
+person
+bicycle
+car
+motorbike
+aeroplane
+bus
+train
+truck
+boat
+traffic light
+fire hydrant
+stop sign
+parking meter
+bench
+bird
+cat
+dog
+horse
+sheep
+cow
+elephant
+bear
+zebra
+giraffe
+backpack
+umbrella
+handbag
+tie
+suitcase
+frisbee
+skis
+snowboard
+sports ball
+kite
+baseball bat
+baseball glove
+skateboard
+surfboard
+tennis racket
+bottle
+wine glass
+cup
+fork
+knife
+spoon
+bowl
+banana
+apple
+sandwich
+orange
+broccoli
+carrot
+hot dog
+pizza
+donut
+cake
+chair
+sofa
+pottedplant
+bed
+diningtable
+toilet
+tvmonitor
+laptop
+mouse
+remote
+keyboard
+cell phone
+microwave
+oven
+toaster
+sink
+refrigerator
+book
+clock
+vase
+scissors
+teddy bear
+hair drier
+toothbrush