Add TensorFlow and TFLite export (#1127)

* Add models/tf.py for TensorFlow and TFLite export

* Set auto=False for int8 calibration

* Update requirements.txt for TensorFlow and TFLite export

* Read anchors directly from PyTorch weights

* Add --tf-nms to append NMS in TensorFlow SavedModel and GraphDef export

* Remove check_anchor_order, check_file, set_logging from import

* Reformat code and optimize imports

* Autodownload model and check cfg

* update --source path, img-size to 320, single output

* Adjust representative_dataset

* Put representative dataset in tfl_int8 block

* detect.py TF inference

* weights to string

* weights to string

* cleanup tf.py

* Add --dynamic-batch-size

* Add xywh normalization to reduce calibration error

* Update requirements.txt

TensorFlow 2.3.1 -> 2.4.0 to avoid int8 quantization error

* Fix imports

Move C3 from models.experimental to models.common

* Add models/tf.py for TensorFlow and TFLite export

* Set auto=False for int8 calibration

* Update requirements.txt for TensorFlow and TFLite export

* Read anchors directly from PyTorch weights

* Add --tf-nms to append NMS in TensorFlow SavedModel and GraphDef export

* Remove check_anchor_order, check_file, set_logging from import

* Reformat code and optimize imports

* Autodownload model and check cfg

* update --source path, img-size to 320, single output

* Adjust representative_dataset

* detect.py TF inference

* Put representative dataset in tfl_int8 block

* weights to string

* weights to string

* cleanup tf.py

* Add --dynamic-batch-size

* Add xywh normalization to reduce calibration error

* Update requirements.txt

TensorFlow 2.3.1 -> 2.4.0 to avoid int8 quantization error

* Fix imports

Move C3 from models.experimental to models.common

* implement C3() and SiLU()

* Fix reshape dim to support dynamic batching

* Add epsilon argument in tf_BN, which is different between TF and PT

* Set stride to None if not using PyTorch, and do not warmup without PyTorch

* Add list support in check_img_size()

* Add list input support in detect.py

* sys.path.append('./') to run from yolov5/

* Add int8 quantization support for TensorFlow 2.5

* Add get_coco128.sh

* Remove --no-tfl-detect in models/tf.py (Use tf-android-tfl-detect branch for EdgeTPU)

* Update requirements.txt

* Replace torch.load() with attempt_load()

* Update requirements.txt

* Add --tf-raw-resize to set half_pixel_centers=False

* Add --agnostic-nms for TF class-agnostic NMS

* Cleanup after merge

* Cleanup2 after merge

* Cleanup3 after merge

* Add tf.py docstring with credit and usage

* pb saved_model and tflite use only one model in detect.py

* Add use cases in docstring of tf.py

* Remove redundant `stride` definition

* Remove keras direct import

* Fix `check_requirements(('tensorflow>=2.4.1',))`

Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>

utils/datasets.py

@@ -155,7 +155,7 @@ class _RepeatSampler(object):
 
 
 class LoadImages:  # for inference
-    def __init__(self, path, img_size=640, stride=32):
+    def __init__(self, path, img_size=640, stride=32, auto=True):
         p = str(Path(path).absolute())  # os-agnostic absolute path
         if '*' in p:
             files = sorted(glob.glob(p, recursive=True))  # glob
@@ -176,6 +176,7 @@ class LoadImages:  # for inference
         self.nf = ni + nv  # number of files
         self.video_flag = [False] * ni + [True] * nv
         self.mode = 'image'
+        self.auto = auto
         if any(videos):
             self.new_video(videos[0])  # new video
         else:
@@ -217,7 +218,7 @@ class LoadImages:  # for inference
             print(f'image {self.count}/{self.nf} {path}: ', end='')
 
         # Padded resize
-        img = letterbox(img0, self.img_size, stride=self.stride)[0]
+        img = letterbox(img0, self.img_size, stride=self.stride, auto=self.auto)[0]
 
         # Convert
         img = img.transpose((2, 0, 1))[::-1]  # HWC to CHW, BGR to RGB
@@ -276,7 +277,7 @@ class LoadWebcam:  # for inference
 
 
 class LoadStreams:  # multiple IP or RTSP cameras
-    def __init__(self, sources='streams.txt', img_size=640, stride=32):
+    def __init__(self, sources='streams.txt', img_size=640, stride=32, auto=True):
         self.mode = 'stream'
         self.img_size = img_size
         self.stride = stride
@@ -290,6 +291,7 @@ class LoadStreams:  # multiple IP or RTSP cameras
         n = len(sources)
         self.imgs, self.fps, self.frames, self.threads = [None] * n, [0] * n, [0] * n, [None] * n
         self.sources = [clean_str(x) for x in sources]  # clean source names for later
+        self.auto = auto
         for i, s in enumerate(sources):  # index, source
             # Start thread to read frames from video stream
             print(f'{i + 1}/{n}: {s}... ', end='')
@@ -312,7 +314,7 @@ class LoadStreams:  # multiple IP or RTSP cameras
         print('')  # newline
 
         # check for common shapes
-        s = np.stack([letterbox(x, self.img_size, stride=self.stride)[0].shape for x in self.imgs], 0)  # shapes
+        s = np.stack([letterbox(x, self.img_size, stride=self.stride, auto=self.auto)[0].shape for x in self.imgs], 0)  # shapes
         self.rect = np.unique(s, axis=0).shape[0] == 1  # rect inference if all shapes equal
         if not self.rect:
             print('WARNING: Different stream shapes detected. For optimal performance supply similarly-shaped streams.')
@@ -341,7 +343,7 @@ class LoadStreams:  # multiple IP or RTSP cameras
 
         # Letterbox
         img0 = self.imgs.copy()
-        img = [letterbox(x, self.img_size, auto=self.rect, stride=self.stride)[0] for x in img0]
+        img = [letterbox(x, self.img_size, stride=self.stride, auto=self.rect and self.auto)[0] for x in img0]
 
         # Stack
         img = np.stack(img, 0)