Merge pull request ayooshkathuria#48 from id9502/master

made some bug fixing and added support for tiny Yolo-v3

config/yolov3-tiny.cfg

@@ -0,0 +1,206 @@
+[net]
+# Testing
+batch=1
+subdivisions=1
+# Training
+# batch=64
+# subdivisions=2
+width=416
+height=416
+channels=3
+momentum=0.9
+decay=0.0005
+angle=0
+saturation = 1.5
+exposure = 1.5
+hue=.1
+
+learning_rate=0.001
+burn_in=1000
+max_batches = 500200
+policy=steps
+steps=400000,450000
+scales=.1,.1
+
+# 0
+[convolutional]
+batch_normalize=1
+filters=16
+size=3
+stride=1
+pad=1
+activation=leaky
+
+# 1
+[maxpool]
+size=2
+stride=2
+
+# 2
+[convolutional]
+batch_normalize=1
+filters=32
+size=3
+stride=1
+pad=1
+activation=leaky
+
+# 3
+[maxpool]
+size=2
+stride=2
+
+# 4
+[convolutional]
+batch_normalize=1
+filters=64
+size=3
+stride=1
+pad=1
+activation=leaky
+
+# 5
+[maxpool]
+size=2
+stride=2
+
+# 6
+[convolutional]
+batch_normalize=1
+filters=128
+size=3
+stride=1
+pad=1
+activation=leaky
+
+# 7
+[maxpool]
+size=2
+stride=2
+
+# 8
+[convolutional]
+batch_normalize=1
+filters=256
+size=3
+stride=1
+pad=1
+activation=leaky
+
+# 9
+[maxpool]
+size=2
+stride=2
+
+# 10
+[convolutional]
+batch_normalize=1
+filters=512
+size=3
+stride=1
+pad=1
+activation=leaky
+
+# 11
+[maxpool]
+size=2
+stride=1
+
+# 12
+[convolutional]
+batch_normalize=1
+filters=1024
+size=3
+stride=1
+pad=1
+activation=leaky
+
+###########
+
+# 13
+[convolutional]
+batch_normalize=1
+filters=256
+size=1
+stride=1
+pad=1
+activation=leaky
+
+# 14
+[convolutional]
+batch_normalize=1
+filters=512
+size=3
+stride=1
+pad=1
+activation=leaky
+
+# 15
+[convolutional]
+size=1
+stride=1
+pad=1
+filters=255
+activation=linear
+
+
+
+# 16
+[yolo]
+mask = 3,4,5
+anchors = 10,14,  23,27,  37,58,  81,82,  135,169,  344,319
+classes=80
+num=6
+jitter=.3
+ignore_thresh = .7
+truth_thresh = 1
+random=1
+
+# 17
+[route]
+layers = -4
+
+# 18
+[convolutional]
+batch_normalize=1
+filters=128
+size=1
+stride=1
+pad=1
+activation=leaky
+
+# 19
+[upsample]
+stride=2
+
+# 20
+[route]
+layers = -1, 8
+
+# 21
+[convolutional]
+batch_normalize=1
+filters=256
+size=3
+stride=1
+pad=1
+activation=leaky
+
+# 22
+[convolutional]
+size=1
+stride=1
+pad=1
+filters=255
+activation=linear
+
+# 23
+[yolo]
+mask = 1,2,3
+anchors = 10,14,  23,27,  37,58,  81,82,  135,169,  344,319
+classes=80
+num=6
+jitter=.3
+ignore_thresh = .7
+truth_thresh = 1
+random=1

models.py

@@ -20,7 +20,7 @@ def create_modules(module_defs):
     Constructs module list of layer blocks from module configuration in module_defs
     """
     hyperparams = module_defs.pop(0)
-    output_filters = [int(hyperparams['channels'])]
+    output_filters = []
     module_list = nn.ModuleList()
     for i, module_def in enumerate(module_defs):
         modules = nn.Sequential()
@@ -30,7 +30,8 @@ def create_modules(module_defs):
             filters = int(module_def['filters'])
             kernel_size = int(module_def['size'])
             pad = (kernel_size - 1) // 2 if int(module_def['pad']) else 0
-            modules.add_module('conv_%d' % i, nn.Conv2d(in_channels=output_filters[-1],
+            modules.add_module('conv_%d' % i, nn.Conv2d(in_channels=(output_filters[-1] if len(output_filters) > 0
+                                                                     else int(hyperparams['channels'])),
                                                         out_channels=filters,
                                                         kernel_size=kernel_size,
                                                         stride=int(module_def['stride']),
@@ -41,6 +42,16 @@ def create_modules(module_defs):
             if module_def['activation'] == 'leaky':
                 modules.add_module('leaky_%d' % i, nn.LeakyReLU(0.1))
 
+        elif module_def['type'] == 'maxpool':
+            kernel_size = int(module_def['size'])
+            stride = int(module_def['stride'])
+            if kernel_size == 2 and stride == 1:
+                padding = nn.ZeroPad2d((0, 1, 0, 1))
+                modules.add_module('_debug_padding_%d' % i, padding)
+            maxpool = nn.MaxPool2d(kernel_size=int(module_def['size']),
+                                   stride=int(module_def['stride']), padding=int((kernel_size-1)//2))
+            modules.add_module('maxpool_%d' % i, maxpool)
+
         elif module_def['type'] == 'upsample':
             upsample = nn.Upsample( scale_factor=int(module_def['stride']),
                                     mode='nearest')
@@ -192,7 +203,7 @@ def forward(self, x, targets=None):
         self.losses = defaultdict(float)
         layer_outputs = []
         for i, (module_def, module) in enumerate(zip(self.module_defs, self.module_list)):
-            if module_def['type'] in ['convolutional', 'upsample']:
+            if module_def['type'] in ['convolutional', 'upsample', 'maxpool']:
                 x = module(x)
             elif module_def['type'] == 'route':
                 layer_i = [int(x) for x in module_def['layers'].split(',')]

weights/download_weights_tiny.sh

@@ -0,0 +1,3 @@
+#! /usr/bin/env bash
+
+wget https://pjreddie.com/media/files/yolov3-tiny.weights